Kui Ren

Chao Shuai, Jieming Zhong, Shuang Wu et al.

Deepfake has taken the world by storm, triggering a trust crisis. Current deepfake detection methods are typically inadequate in generalizability, with a tendency to overfit to image contents such as the background, which are frequently occurring but relatively unimportant in the training dataset. Furthermore, current methods heavily rely on a few dominant forgery regions and may ignore other equally important regions, leading to inadequate uncovering of forgery cues. In this paper, we strive to address these shortcomings from three aspects: (1) We propose an innovative two-stream network that effectively enlarges the potential regions from which the model extracts forgery evidence. (2) We devise three functional modules to handle the multi-stream and multi-scale features in a collaborative learning scheme. (3) Confronted with the challenge of obtaining forgery annotations, we propose a Semi-supervised Patch Similarity Learning strategy to estimate patch-level forged location annotations. Empirically, our method demonstrates significantly improved robustness and generalizability, outperforming previous methods on six benchmarks, and improving the frame-level AUC on Deepfake Detection Challenge preview dataset from 0.797 to 0.835 and video-level AUC on CelebDF$\_$v1 dataset from 0.811 to 0.847. Our implementation is available at https://github.com/sccsok/Locate-and-Verify.

Yuheng Yang, Haipeng Chen, Zhenguang Liu et al.

Action recognition has long been a fundamental and intriguing problem in artificial intelligence. The task is challenging due to the high dimensionality nature of an action, as well as the subtle motion details to be considered. Current state-of-the-art approaches typically learn from articulated motion sequences in the straightforward 3D Euclidean space. However, the vanilla Euclidean space is not efficient for modeling important motion characteristics such as the joint-wise angular acceleration, which reveals the driving force behind the motion. Moreover, current methods typically attend to each channel equally and lack theoretical constrains on extracting task-relevant features from the input. In this paper, we seek to tackle these challenges from three aspects: (1) We propose to incorporate an acceleration representation, explicitly modeling the higher-order variations in motion. (2) We introduce a novel Stream-GCN network equipped with multi-stream components and channel attention, where different representations (i.e., streams) supplement each other towards a more precise action recognition while attention capitalizes on those important channels. (3) We explore feature-level supervision for maximizing the extraction of task-relevant information and formulate this into a mutual information loss. Empirically, our approach sets the new state-of-the-art performance on three benchmark datasets, NTU RGB+D, NTU RGB+D 120, and NW-UCLA. Our code is anonymously released at https://github.com/ActionR-Group/Stream-GCN, hoping to inspire the community.

Jiachen Lei, Qinglong Wang, Peng Cheng et al.

Diffusion model has emerged as the \emph{de-facto} model for image generation, yet the heavy training overhead hinders its broader adoption in the research community. We observe that diffusion models are commonly trained to learn all fine-grained visual information from scratch. This paradigm may cause unnecessary training costs hence requiring in-depth investigation. In this work, we show that it suffices to train a strong diffusion model by first pre-training the model to learn some primer distribution that loosely characterizes the unknown real image distribution. Then the pre-trained model can be fine-tuned for various generation tasks efficiently. In the pre-training stage, we propose to mask a high proportion (e.g., up to 90\%) of input images to approximately represent the primer distribution and introduce a masked denoising score matching objective to train a model to denoise visible areas. In subsequent fine-tuning stage, we efficiently train diffusion model without masking. Utilizing the two-stage training framework, we achieves significant training acceleration and a new FID score record of 6.27 on CelebA-HQ $256 \times 256$ for ViT-based diffusion models. The generalizability of a pre-trained model further helps building models that perform better than ones trained from scratch on different downstream datasets. For instance, a diffusion model pre-trained on VGGFace2 attains a 46\% quality improvement when fine-tuned on a different dataset that contains only 3000 images. Our code is available at \url{https://github.com/jiachenlei/maskdm}.

Zhongjie Ba, Jieming Zhong, Jiachen Lei et al.

Advanced text-to-image models such as DALL$\cdot$E 2 and Midjourney possess the capacity to generate highly realistic images, raising significant concerns regarding the potential proliferation of unsafe content. This includes adult, violent, or deceptive imagery of political figures. Despite claims of rigorous safety mechanisms implemented in these models to restrict the generation of not-safe-for-work (NSFW) content, we successfully devise and exhibit the first prompt attacks on Midjourney, resulting in the production of abundant photorealistic NSFW images. We reveal the fundamental principles of such prompt attacks and suggest strategically substituting high-risk sections within a suspect prompt to evade closed-source safety measures. Our novel framework, SurrogatePrompt, systematically generates attack prompts, utilizing large language models, image-to-text, and image-to-image modules to automate attack prompt creation at scale. Evaluation results disclose an 88% success rate in bypassing Midjourney's proprietary safety filter with our attack prompts, leading to the generation of counterfeit images depicting political figures in violent scenarios. Both subjective and objective assessments validate that the images generated from our attack prompts present considerable safety hazards.

Jiachen Lei, Shuang Ma, Zhongjie Ba et al.

In this report, we present our approach and empirical results of applying masked autoencoders in two egocentric video understanding tasks, namely, Object State Change Classification and PNR Temporal Localization, of Ego4D Challenge 2022. As team TheSSVL, we ranked 2nd place in both tasks. Our code will be made available.

Hongwei Yao, Zheng Li, Haiqin Weng et al.

Machine Learning as a Service (MLaaS) platforms have gained popularity due to their accessibility, cost-efficiency, scalability, and rapid development capabilities. However, recent research has highlighted the vulnerability of cloud-based models in MLaaS to model extraction attacks. In this paper, we introduce FDINET, a novel defense mechanism that leverages the feature distribution of deep neural network (DNN) models. Concretely, by analyzing the feature distribution from the adversary's queries, we reveal that the feature distribution of these queries deviates from that of the model's training set. Based on this key observation, we propose Feature Distortion Index (FDI), a metric designed to quantitatively measure the feature distribution deviation of received queries. The proposed FDINET utilizes FDI to train a binary detector and exploits FDI similarity to identify colluding adversaries from distributed extraction attacks. We conduct extensive experiments to evaluate FDINET against six state-of-the-art extraction attacks on four benchmark datasets and four popular model architectures. Empirical results demonstrate the following findings FDINET proves to be highly effective in detecting model extraction, achieving a 100% detection accuracy on DFME and DaST. FDINET is highly efficient, using just 50 queries to raise an extraction alarm with an average confidence of 96.08% for GTSRB. FDINET exhibits the capability to identify colluding adversaries with an accuracy exceeding 91%. Additionally, it demonstrates the ability to detect two types of adaptive attacks.

Jian Liu, Rui Zhang, Sebastian Szyller et al.

Deep neural network (DNN) models are valuable intellectual property of model owners, constituting a competitive advantage. Therefore, it is crucial to develop techniques to protect against model theft. Model ownership resolution (MOR) is a class of techniques that can deter model theft. A MOR scheme enables an accuser to assert an ownership claim for a suspect model by presenting evidence, such as a watermark or fingerprint, to show that the suspect model was stolen or derived from a source model owned by the accuser. Most of the existing MOR schemes prioritize robustness against malicious suspects, ensuring that the accuser will win if the suspect model is indeed a stolen model. In this paper, we show that common MOR schemes in the literature are vulnerable to a different, equally important but insufficiently explored, robustness concern: a malicious accuser. We show how malicious accusers can successfully make false claims against independent suspect models that were not stolen. Our core idea is that a malicious accuser can deviate (without detection) from the specified MOR process by finding (transferable) adversarial examples that successfully serve as evidence against independent suspect models. To this end, we first generalize the procedures of common MOR schemes and show that, under this generalization, defending against false claims is as challenging as preventing (transferable) adversarial examples. Via systematic empirical evaluation, we show that our false claim attacks always succeed in the MOR schemes that follow our generalization, including in a real-world model: Amazon's Rekognition API.

Yiling He, Jian Lou, Zhan Qin et al.

Deep learning classifiers achieve state-of-the-art performance in various risk detection applications. They explore rich semantic representations and are supposed to automatically discover risk behaviors. However, due to the lack of transparency, the behavioral semantics cannot be conveyed to downstream security experts to reduce their heavy workload in security analysis. Although feature attribution (FA) methods can be used to explain deep learning, the underlying classifier is still blind to what behavior is suspicious, and the generated explanation cannot adapt to downstream tasks, incurring poor explanation fidelity and intelligibility. In this paper, we propose FINER, the first framework for risk detection classifiers to generate high-fidelity and high-intelligibility explanations. The high-level idea is to gather explanation efforts from model developer, FA designer, and security experts. To improve fidelity, we fine-tune the classifier with an explanation-guided multi-task learning strategy. To improve intelligibility, we engage task knowledge to adjust and ensemble FA methods. Extensive evaluations show that FINER improves explanation quality for risk detection. Moreover, we demonstrate that FINER outperforms a state-of-the-art tool in facilitating malware analysis.

Guodong Cao, Zhibo Wang, Xiaowei Dong et al.

Adversarial training has been widely explored for mitigating attacks against deep models. However, most existing works are still trapped in the dilemma between higher accuracy and stronger robustness since they tend to fit a model towards robust features (not easily tampered with by adversaries) while ignoring those non-robust but highly predictive features. To achieve a better robustness-accuracy trade-off, we propose the Vanilla Feature Distillation Adversarial Training (VFD-Adv), which conducts knowledge distillation from a pre-trained model (optimized towards high accuracy) to guide adversarial training towards higher accuracy, i.e., preserving those non-robust but predictive features. More specifically, both adversarial examples and their clean counterparts are forced to be aligned in the feature space by distilling predictive representations from the pre-trained/clean model, while previous works barely utilize predictive features from clean models. Therefore, the adversarial training model is updated towards maximally preserving the accuracy as gaining robustness. A key advantage of our method is that it can be universally adapted to and boost existing works. Exhaustive experiments on various datasets, classification models, and adversarial training algorithms demonstrate the effectiveness of our proposed method.

Peng Cheng, Yuwei Wang, Peng Huang et al.

Extensive research has revealed that adversarial examples (AE) pose a significant threat to voice-controllable smart devices. Recent studies have proposed black-box adversarial attacks that require only the final transcription from an automatic speech recognition (ASR) system. However, these attacks typically involve many queries to the ASR, resulting in substantial costs. Moreover, AE-based adversarial audio samples are susceptible to ASR updates. In this paper, we identify the root cause of these limitations, namely the inability to construct AE attack samples directly around the decision boundary of deep learning (DL) models. Building on this observation, we propose ALIF, the first black-box adversarial linguistic feature-based attack pipeline. We leverage the reciprocal process of text-to-speech (TTS) and ASR models to generate perturbations in the linguistic embedding space where the decision boundary resides. Based on the ALIF pipeline, we present the ALIF-OTL and ALIF-OTA schemes for launching attacks in both the digital domain and the physical playback environment on four commercial ASRs and voice assistants. Extensive evaluations demonstrate that ALIF-OTL and -OTA significantly improve query efficiency by 97.7% and 73.3%, respectively, while achieving competitive performance compared to existing methods. Notably, ALIF-OTL can generate an attack sample with only one query. Furthermore, our test-of-time experiment validates the robustness of our approach against ASR updates.

Binhao Ma, Tianhang Zheng, Hongsheng Hu et al.

Machine learning models trained on vast amounts of real or synthetic data often achieve outstanding predictive performance across various domains. However, this utility comes with increasing concerns about privacy, as the training data may include sensitive information. To address these concerns, machine unlearning has been proposed to erase specific data samples from models. While some unlearning techniques efficiently remove data at low costs, recent research highlights vulnerabilities where malicious users could request unlearning on manipulated data to compromise the model. Despite these attacks' effectiveness, perturbed data differs from original training data, failing hash verification. Existing attacks on machine unlearning also suffer from practical limitations and require substantial additional knowledge and resources. To fill the gaps in current unlearning attacks, we introduce the Unlearning Usability Attack. This model-agnostic, unlearning-agnostic, and budget-friendly attack distills data distribution information into a small set of benign data. These data are identified as benign by automatic poisoning detection tools due to their positive impact on model training. While benign for machine learning, unlearning these data significantly degrades model information. Our evaluation demonstrates that unlearning this benign data, comprising no more than 1% of the total training data, can reduce model accuracy by up to 50%. Furthermore, our findings show that well-prepared benign data poses challenges for recent unlearning techniques, as erasing these synthetic instances demands higher resources than regular data. These insights underscore the need for future research to reconsider "data poisoning" in the context of machine unlearning.

Meng Chen, Li Lu, Jiadi Yu et al.

Faced with the threat of identity leakage during voice data publishing, users are engaged in a privacy-utility dilemma when enjoying convenient voice services. Existing studies employ direct modification or text-based re-synthesis to de-identify users' voices, but resulting in inconsistent audibility in the presence of human participants. In this paper, we propose a voice de-identification system, which uses adversarial examples to balance the privacy and utility of voice services. Instead of typical additive examples inducing perceivable distortions, we design a novel convolutional adversarial example that modulates perturbations into real-world room impulse responses. Benefit from this, our system could preserve user identity from exposure by Automatic Speaker Identification (ASI) while remaining the voice perceptual quality for non-intrusive de-identification. Moreover, our system learns a compact speaker distribution through a conditional variational auto-encoder to sample diverse target embeddings on demand. Combining diverse target generation and input-specific perturbation construction, our system enables any-to-any identify transformation for adaptive de-identification. Experimental results show that our system could achieve 98% and 79% successful de-identification on mainstream ASIs and commercial systems with an objective Mel cepstral distortion of 4.31dB and a subjective mean opinion score of 4.48.

Pingchuan Ma, Zhenlan Ji, Peisen Yao et al.

Causal discovery is a powerful technique for identifying causal relationships among variables in data. It has been widely used in various applications in software engineering. Causal discovery extensively involves conditional independence (CI) tests. Hence, its output quality highly depends on the performance of CI tests, which can often be unreliable in practice. Moreover, privacy concerns arise when excessive CI tests are performed. Despite the distinct nature between unreliable and excessive CI tests, this paper identifies a unified and principled approach to addressing both of them. Generally, CI statements, the outputs of CI tests, adhere to Pearl's axioms, which are a set of well-established integrity constraints on conditional independence. Hence, we can either detect erroneous CI statements if they violate Pearl's axioms or prune excessive CI statements if they are logically entailed by Pearl's axioms. Holistically, both problems boil down to reasoning about the consistency of CI statements under Pearl's axioms (referred to as CIR problem). We propose a runtime verification tool called CICheck, designed to harden causal discovery algorithms from reliability and privacy perspectives. CICheck employs a sound and decidable encoding scheme that translates CIR into SMT problems. To solve the CIR problem efficiently, CICheck introduces a four-stage decision procedure with three lightweight optimizations that actively prove or refute consistency, and only resort to costly SMT-based reasoning when necessary. Based on the decision procedure to CIR, CICheck includes two variants: ED-CICheck and ED-CICheck, which detect erroneous CI tests (to enhance reliability) and prune excessive CI tests (to enhance privacy), respectively. [abridged due to length limit]

Kui Ren, Lu Zhang

The task of simultaneously reconstructing multiple physical coefficients in partial differential equations (PDEs) from observed data is ubiquitous in applications. In this work, we propose an integrated data-driven and model-based iterative reconstruction framework for such joint inversion problems where additional data on the unknown coefficients are supplemented for better reconstructions. Our method couples the supplementary data with the PDE model to make the data-driven modeling process consistent with the model-based reconstruction procedure. We characterize the impact of learning uncertainty on the joint inversion results for two typical inverse problems. Numerical evidence is provided to demonstrate the feasibility of using data-driven models to improve the joint inversion of multiple coefficients in PDEs.

Shaoyu Dou, Kai Yang, Yang Jiao et al.

Time series analysis has achieved great success in diverse applications such as network security, environmental monitoring, and medical informatics. Learning similarities among different time series is a crucial problem since it serves as the foundation for downstream analysis such as clustering and anomaly detection. It often remains unclear what kind of distance metric is suitable for similarity learning due to the complex temporal dynamics of the time series generated from event-triggered sensing, which is common in diverse applications, including automated driving, interactive healthcare, and smart home automation. The overarching goal of this paper is to develop an unsupervised learning framework that is capable of learning task-aware similarities among unlabeled event-triggered time series. From the machine learning vantage point, the proposed framework harnesses the power of both hierarchical multi-scale sequence autoencoders and Gaussian Mixture Model (GMM) to effectively learn the low-dimensional representations from the time series. Finally, the obtained similarity measure can be easily visualized for explaining. The proposed framework aspires to offer a stepping stone that gives rise to a systematic approach to model and learn similarities among a multitude of event-triggered time series. Through extensive qualitative and quantitative experiments, it is revealed that the proposed method outperforms state-of-the-art methods considerably.

Xiaohan Yuan, Jinfeng Li, Dongxia Wang et al.

Generative large language models (LLMs) have revolutionized natural language processing with their transformative and emergent capabilities. However, recent evidence indicates that LLMs can produce harmful content that violates social norms, raising significant concerns regarding the safety and ethical ramifications of deploying these advanced models. Thus, it is both critical and imperative to perform a rigorous and comprehensive safety evaluation of LLMs before deployment. Despite this need, owing to the extensiveness of LLM generation space, it still lacks a unified and standardized risk taxonomy to systematically reflect the LLM content safety, as well as automated safety assessment techniques to explore the potential risk efficiently. To bridge the striking gap, we propose S-Eval, a novel LLM-based automated Safety Evaluation framework with a newly defined comprehensive risk taxonomy. S-Eval incorporates two key components, i.e., an expert testing LLM ${M}_t$ and a novel safety critique LLM ${M}_c$. ${M}_t$ is responsible for automatically generating test cases in accordance with the proposed risk taxonomy. ${M}_c$ can provide quantitative and explainable safety evaluations for better risk awareness of LLMs. In contrast to prior works, S-Eval is efficient and effective in test generation and safety evaluation. Moreover, S-Eval can be flexibly configured and adapted to the rapid evolution of LLMs and accompanying new safety threats, test generation methods and safety critique methods thanks to the LLM-based architecture. S-Eval has been deployed in our industrial partner for the automated safety evaluation of multiple LLMs serving millions of users, demonstrating its effectiveness in real-world scenarios. Our benchmark is publicly available at https://github.com/IS2Lab/S-Eval.

Yu He, Boheng Li, Liu Liu et al.

Membership Inference Attacks (MIAs) aim to predict whether a data sample belongs to the model's training set or not. Although prior research has extensively explored MIAs in Large Language Models (LLMs), they typically require accessing to complete output logits (\ie, \textit{logits-based attacks}), which are usually not available in practice. In this paper, we study the vulnerability of pre-trained LLMs to MIAs in the \textit{label-only setting}, where the adversary can only access generated tokens (text). We first reveal that existing label-only MIAs have minor effects in attacking pre-trained LLMs, although they are highly effective in inferring fine-tuning datasets used for personalized LLMs. We find that their failure stems from two main reasons, including better generalization and overly coarse perturbation. Specifically, due to the extensive pre-training corpora and exposing each sample only a few times, LLMs exhibit minimal robustness differences between members and non-members. This makes token-level perturbations too coarse to capture such differences. To alleviate these problems, we propose \textbf{PETAL}: a label-only membership inference attack based on \textbf{PE}r-\textbf{T}oken sem\textbf{A}ntic simi\textbf{L}arity. Specifically, PETAL leverages token-level semantic similarity to approximate output probabilities and subsequently calculate the perplexity. It finally exposes membership based on the common assumption that members are `better' memorized and have smaller perplexity. We conduct extensive experiments on the WikiMIA benchmark and the more challenging MIMIR benchmark. Empirically, our PETAL performs better than the extensions of existing label-only attacks against personalized LLMs and even on par with other advanced logit-based attacks across all metrics on five prevalent open-source LLMs.

Zhenjie Xu, Wenqing Chen, Yi Tang et al.

Natural language processing (NLP) has seen remarkable advancements with the development of large language models (LLMs). Despite these advancements, LLMs often produce socially biased outputs. Recent studies have mainly addressed this problem by prompting LLMs to behave ethically, but this approach results in unacceptable performance degradation. In this paper, we propose a multi-objective approach within a multi-agent framework (MOMA) to mitigate social bias in LLMs without significantly compromising their performance. The key idea of MOMA involves deploying multiple agents to perform causal interventions on bias-related contents of the input questions, breaking the shortcut connection between these contents and the corresponding answers. Unlike traditional debiasing techniques leading to performance degradation, MOMA substantially reduces bias while maintaining accuracy in downstream tasks. Our experiments conducted on two datasets and two models demonstrate that MOMA reduces bias scores by up to 87.7%, with only a marginal performance degradation of up to 6.8% in the BBQ dataset. Additionally, it significantly enhances the multi-objective metric icat in the StereoSet dataset by up to 58.1%. Code will be made available at https://github.com/Cortantse/MOMA.

Yukun Chen, Boheng Li, Yu Yuan et al.

Knowledge distillation (KD) is a vital technique for deploying deep neural networks (DNNs) on resource-constrained devices by transferring knowledge from large teacher models to lightweight student models. While teacher models from third-party platforms may undergo security verification (\eg, backdoor detection), we uncover a novel and critical threat: distillation-conditional backdoor attacks (DCBAs). DCBA injects dormant and undetectable backdoors into teacher models, which become activated in student models via the KD process, even with clean distillation datasets. While the direct extension of existing methods is ineffective for DCBA, we implement this attack by formulating it as a bilevel optimization problem and proposing a simple yet effective method (\ie, SCAR). Specifically, the inner optimization simulates the KD process by optimizing a surrogate student model, while the outer optimization leverages outputs from this surrogate to optimize the teacher model for implanting the conditional backdoor. Our SCAR addresses this complex optimization utilizing an implicit differentiation algorithm with a pre-optimized trigger injection function. Extensive experiments across diverse datasets, model architectures, and KD techniques validate the effectiveness of our SCAR and its resistance against existing backdoor detection, highlighting a significant yet previously overlooked vulnerability in the KD process. Our code is available at https://github.com/WhitolfChen/SCAR.

Jiachen Lei, Julius Berner, Jiongxiao Wang et al.

Robustness is essential for deep neural networks, especially in security-sensitive applications. To this end, randomized smoothing provides theoretical guarantees for certifying robustness against adversarial perturbations. Recently, diffusion models have been successfully employed for randomized smoothing to purify noise-perturbed samples before making predictions with a standard classifier. While these methods excel at small perturbation radii, they struggle with larger perturbations and incur a significant computational overhead during inference compared to classical methods. To address this, we reformulate the generative modeling task along the diffusion trajectories in pixel space as a discriminative task in the latent space. Specifically, we use instance discrimination to achieve consistent representations along the trajectories by aligning temporally adjacent points. After fine-tuning based on the learned representations, our model enables implicit denoising-then-classification via a single prediction, substantially reducing inference costs. We conduct extensive experiments on various datasets and achieve state-of-the-art performance with minimal computation budget during inference. For example, our method outperforms the certified accuracy of diffusion-based methods on ImageNet across all perturbation radii by 5.3% on average, with up to 11.6% at larger radii, while reducing inference costs by 85$\times$ on average. Codes are available at: https://github.com/jiachenlei/rRCM.

Yichen Sun, Zhixuan Chu, Zhan Qin et al.

The rapid advancement of Text-to-Image(T2I) generative models has enabled the synthesis of high-quality images guided by textual descriptions. Despite this significant progress, these models are often susceptible in generating contents that contradict the input text, which poses a challenge to their reliability and practical deployment. To address this problem, we introduce a novel diffusion-based framework to significantly enhance the alignment of generated images with their corresponding descriptions, addressing the inconsistency between visual output and textual input. Our framework is built upon a comprehensive analysis of inconsistency phenomena, categorizing them based on their manifestation in the image. Leveraging a state-of-the-art large language module, we first extract objects and construct a knowledge graph to predict the locations of these objects in potentially generated images. We then integrate a state-of-the-art controllable image generation model with a visual text generation module to generate an image that is consistent with the original prompt, guided by the predicted object locations. Through extensive experiments on an advanced multimodal hallucination benchmark, we demonstrate the efficacy of our approach in accurately generating the images without the inconsistency with the original prompt. The code can be accessed via https://github.com/TruthAI-Lab/PCIG.

Tianhang Zheng, Changyou Chen, Kui Ren

Recent work on adversarial attack has shown that Projected Gradient Descent (PGD) Adversary is a universal first-order adversary, and the classifier adversarially trained by PGD is robust against a wide range of first-order attacks. It is worth noting that the original objective of an attack/defense model relies on a data distribution $p(\mathbf{x})$, typically in the form of risk maximization/minimization, e.g., $\max/\min\mathbb{E}_{p(\mathbf(x))}\mathcal{L}(\mathbf{x})$ with $p(\mathbf{x})$ some unknown data distribution and $\mathcal{L}(\cdot)$ a loss function. However, since PGD generates attack samples independently for each data sample based on $\mathcal{L}(\cdot)$, the procedure does not necessarily lead to good generalization in terms of risk optimization. In this paper, we achieve the goal by proposing distributionally adversarial attack (DAA), a framework to solve an optimal {\em adversarial-data distribution}, a perturbed distribution that satisfies the $L_\infty$ constraint but deviates from the original data distribution to increase the generalization risk maximally. Algorithmically, DAA performs optimization on the space of potential data distributions, which introduces direct dependency between all data points when generating adversarial samples. DAA is evaluated by attacking state-of-the-art defense models, including the adversarially-trained models provided by {\em MIT MadryLab}. Notably, DAA ranks {\em the first place} on MadryLab's white-box leaderboards, reducing the accuracy of their secret MNIST model to $88.79\%$ (with $l_\infty$ perturbations of $ε= 0.3$) and the accuracy of their secret CIFAR model to $44.71\%$ (with $l_\infty$ perturbations of $ε= 8.0$). Code for the experiments is released on \url{https://github.com/tianzheng4/Distributionally-Adversarial-Attack}.

Shuo Shao, Yiming Li, Hongwei Yao et al.

Ownership verification is currently the most critical and widely adopted post-hoc method to safeguard model copyright. In general, model owners exploit it to identify whether a given suspicious third-party model is stolen from them by examining whether it has particular properties `inherited' from their released models. Currently, backdoor-based model watermarks are the primary and cutting-edge methods to implant such properties in the released models. However, backdoor-based methods have two fatal drawbacks, including harmfulness and ambiguity. The former indicates that they introduce maliciously controllable misclassification behaviors ($i.e.$, backdoor) to the watermarked released models. The latter denotes that malicious users can easily pass the verification by finding other misclassified samples, leading to ownership ambiguity. In this paper, we argue that both limitations stem from the `zero-bit' nature of existing watermarking schemes, where they exploit the status ($i.e.$, misclassified) of predictions for verification. Motivated by this understanding, we design a new watermarking paradigm, $i.e.$, Explanation as a Watermark (EaaW), that implants verification behaviors into the explanation of feature attribution instead of model predictions. Specifically, EaaW embeds a `multi-bit' watermark into the feature attribution explanation of specific trigger samples without changing the original prediction. We correspondingly design the watermark embedding and extraction algorithms inspired by explainable artificial intelligence. In particular, our approach can be used for different tasks ($e.g.$, image classification and text generation). Extensive experiments verify the effectiveness and harmlessness of our EaaW and its resistance to potential attacks.

Jiaqi Liu, Jian Lou, Zhan Qin et al.

We study the problem of $(ε,δ)$-certified machine unlearning for minimax models. Most of the existing works focus on unlearning from standard statistical learning models that have a single variable and their unlearning steps hinge on the direct Hessian-based conventional Newton update. We develop a new $(ε,δ)$-certified machine unlearning algorithm for minimax models. It proposes a minimax unlearning step consisting of a total-Hessian-based complete Newton update and the Gaussian mechanism borrowed from differential privacy. To obtain the unlearning certification, our method injects calibrated Gaussian noises by carefully analyzing the "sensitivity" of the minimax unlearning step (i.e., the closeness between the minimax unlearning variables and the retraining-from-scratch variables). We derive the generalization rates in terms of population strong and weak primal-dual risk for three different cases of loss functions, i.e., (strongly-)convex-(strongly-)concave losses. We also provide the deletion capacity to guarantee that a desired population risk can be maintained as long as the number of deleted samples does not exceed the derived amount. With training samples $n$ and model dimension $d$, it yields the order $\mathcal O(n/d^{1/4})$, which shows a strict gap over the baseline method of differentially private minimax learning that has $\mathcal O(n/d^{1/2})$. In addition, our rates of generalization and deletion capacity match the state-of-the-art rates derived previously for standard statistical learning models.

Zhixuan Chu, Lei Zhang, Yichen Sun et al.

The rapid advancement in text-to-video (T2V) generative models has enabled the synthesis of high-fidelity video content guided by textual descriptions. Despite this significant progress, these models are often susceptible to hallucination, generating contents that contradict the input text, which poses a challenge to their reliability and practical deployment. To address this critical issue, we introduce the SoraDetector, a novel unified framework designed to detect hallucinations across diverse large T2V models, including the cutting-edge Sora model. Our framework is built upon a comprehensive analysis of hallucination phenomena, categorizing them based on their manifestation in the video content. Leveraging the state-of-the-art keyframe extraction techniques and multimodal large language models, SoraDetector first evaluates the consistency between extracted video content summary and textual prompts, then constructs static and dynamic knowledge graphs (KGs) from frames to detect hallucination both in single frames and across frames. Sora Detector provides a robust and quantifiable measure of consistency, static and dynamic hallucination. In addition, we have developed the Sora Detector Agent to automate the hallucination detection process and generate a complete video quality report for each input video. Lastly, we present a novel meta-evaluation benchmark, T2VHaluBench, meticulously crafted to facilitate the evaluation of advancements in T2V hallucination detection. Through extensive experiments on videos generated by Sora and other large T2V models, we demonstrate the efficacy of our approach in accurately detecting hallucinations. The code and dataset can be accessed via GitHub.

Yukun Chen, Shuo Shao, Enhao Huang et al.

Backdoor attacks on deep neural networks (DNNs) have emerged as a significant security threat, allowing adversaries to implant hidden malicious behaviors during the model training phase. Pre-processing-based defense, which is one of the most important defense paradigms, typically focuses on input transformations or backdoor trigger inversion (BTI) to deactivate or eliminate embedded backdoor triggers during the inference process. However, these methods suffer from inherent limitations: transformation-based defenses often fail to balance model utility and defense performance, while BTI-based defenses struggle to accurately reconstruct trigger patterns without prior knowledge. In this paper, we propose REFINE, an inversion-free backdoor defense method based on model reprogramming. REFINE consists of two key components: \textbf{(1)} an input transformation module that disrupts both benign and backdoor patterns, generating new benign features; and \textbf{(2)} an output remapping module that redefines the model's output domain to guide the input transformations effectively. By further integrating supervised contrastive loss, REFINE enhances the defense capabilities while maintaining model utility. Extensive experiments on various benchmark datasets demonstrate the effectiveness of our REFINE and its resistance to potential adaptive attacks.

Yuke Hu, Zheng Li, Zhihao Liu et al.

Vision-Language Models (VLMs), built on pre-trained vision encoders and large language models (LLMs), have shown exceptional multi-modal understanding and dialog capabilities, positioning them as catalysts for the next technological revolution. However, while most VLM research focuses on enhancing multi-modal interaction, the risks of data misuse and leakage have been largely unexplored. This prompts the need for a comprehensive investigation of such risks in VLMs. In this paper, we conduct the first analysis of misuse and leakage detection in VLMs through the lens of membership inference attack (MIA). In specific, we focus on the instruction tuning data of VLMs, which is more likely to contain sensitive or unauthorized information. To address the limitation of existing MIA methods, we introduce a novel approach that infers membership based on a set of samples and their sensitivity to temperature, a unique parameter in VLMs. Based on this, we propose four membership inference methods, each tailored to different levels of background knowledge, ultimately arriving at the most challenging scenario. Our comprehensive evaluations show that these methods can accurately determine membership status, e.g., achieving an AUC greater than 0.8 targeting a small set consisting of only 5 samples on LLaVA.

Zhihua Tian, Yuan Ding, Wenjie Qu et al.

Money laundering is the process that intends to legalize the income derived from illicit activities, thus facilitating their entry into the monetary flow of the economy without jeopardizing their source. It is crucial to identify such activities accurately and reliably in order to enforce anti-money laundering (AML). Despite considerable efforts to AML, a large number of such activities still go undetected. Rule-based methods were first introduced and are still widely used in current detection systems. With the rise of machine learning, graph-based learning methods have gained prominence in detecting illicit accounts through the analysis of money transfer graphs. Nevertheless, these methods generally assume that the transaction graph is centralized, whereas in practice, money laundering activities usually span multiple financial institutions. Due to regulatory, legal, commercial, and customer privacy concerns, institutions tend not to share data, restricting their utility in practical usage. In this paper, we propose the first algorithm that supports performing AML over multiple institutions while protecting the security and privacy of local data. To evaluate, we construct Alipay-ECB, a real-world dataset comprising digital transactions from Alipay, the world's largest mobile payment platform, alongside transactions from E-Commerce Bank (ECB). The dataset includes over 200 million accounts and 300 million transactions, covering both intra-institution transactions and those between Alipay and ECB. This makes it the largest real-world transaction graph available for analysis. The experimental results demonstrate that our methods can effectively identify cross-institution money laundering subgroups. Additionally, experiments on synthetic datasets also demonstrate that our method is efficient, requiring only a few minutes on datasets with millions of transactions.

Yiling He, Junchi Lei, Zhan Qin et al.

Machine learning-based Android malware classifiers achieve high accuracy in stationary environments but struggle with concept drift. The rapid evolution of malware, especially with new families, can depress classification accuracy to near-random levels. Previous research has largely centered on detecting drift samples, with expert-led label revisions on these samples to guide model retraining. However, these methods often lack a comprehensive understanding of malware concepts and provide limited guidance for effective drift adaptation, leading to unstable detection performance and high human labeling costs. To combat concept drift, we propose DREAM, a novel system that improves drift detection and establishes an explanatory adaptation process. Our core idea is to integrate classifier and expert knowledge within a unified model. To achieve this, we embed malware explanations (or concepts) within the latent space of a contrastive autoencoder, while constraining sample reconstruction based on classifier predictions. This approach enhances classifier retraining in two key ways: 1) capturing the target classifier's characteristics to select more effective samples in drift detection and 2) enabling concept revisions that extend the classifier's semantics to provide stronger guidance for adaptation. Additionally, DREAM eliminates reliance on training data during real-time drift detection and provides a behavior-based drift explainer to support concept revision. Our evaluation shows that DREAM effectively improves the drift detection accuracy and reduces the expert analysis effort in adaptation across different malware datasets and classifiers. Notably, when updating a widely-used Drebin classifier, DREAM achieves the same accuracy with 76.6% fewer newly labeled samples compared to the best existing methods.

Chao Shuai, Gaojian Wang, Kun Pan et al.

While the pursuit of higher accuracy in deepfake detection remains a central goal, there is an increasing demand for precise localization of manipulated regions. Despite the remarkable progress made in classification-based detection, accurately localizing forged areas remains a significant challenge. A common strategy is to incorporate forged region annotations during model training alongside manipulated images. However, such approaches often neglect the complementary nature of local detail and global semantic context, resulting in suboptimal localization performance. Moreover, an often-overlooked aspect is the fusion strategy between local and global predictions. Naively combining the outputs from both branches can amplify noise and errors, thereby undermining the effectiveness of the localization. To address these issues, we propose a novel approach that independently predicts manipulated regions using both local and global perspectives. We employ morphological operations to fuse the outputs, effectively suppressing noise while enhancing spatial coherence. Extensive experiments reveal the effectiveness of each module in improving the accuracy and robustness of forgery localization.

Tianpei Lu, Bingsheng Zhang, Lekun Peng et al.

With the increasing deployment of generative machine learning models in privacy-sensitive domains such as healthcare and personalized services, ensuring secure inference has become a critical challenge. Secure multi-party computation (MPC) enables privacy-preserving model inference but suffers from high communication and computation overhead. The main bottleneck lies in the expensive secure evaluation of floating-point operations. Quantization offers a promising solution by converting floating-point operations into lower-precision integer computations, significantly reducing overhead. However, existing MPC-based quantized inference methods either rely on public quantization parameters-posing privacy risks-or suffer from inefficiencies, particularly in handling nonlinear functions such as activations and softmax. In this work, we propose a fine-grained, layer-wise quantization scheme and support 1-bit weight fully connected layers in a secure setting. We design a multi-input lookup table protocol to evaluate softmax efficiently and securely. Furthermore, we use dual secret sharing schemes and perform precision conversions via lookup tables, eliminating truncation overhead entirely. Experimental evaluation on BERT-base models demonstrates that our approach achieves up to $8\times$ speedup compared to Lu \emph{et al}. (NDSS 25), $9\times$ speedup compared to Gupta \emph{et al}. (PETS 24) and $22 \times$ speedup compared to Knott \emph{et al}. (NeurIPS 21).

Mingjie Chen, Tiancheng Zhu, Mingxue Zhang et al.

Binary code similarity detection (BCSD) serves as a fundamental technique for various software engineering tasks, e.g., vulnerability detection and classification. Attacks against such models have therefore drawn extensive attention, aiming at misleading the models to generate erroneous predictions. Prior works have explored various approaches to generating semantic-preserving variants, i.e., adversarial samples, to evaluate the robustness of the models against adversarial attacks. However, they have mainly relied on heuristic criteria or iterative greedy algorithms to locate salient code influencing the model output, failing to operate on a solid theoretical basis. Moreover, when processing programs with high complexities, such attacks tend to be time-consuming. In this work, we propose a novel optimization for adversarial attacks against BCSD models. In particular, we aim to improve the attacks in a challenging scenario, where the attack goal is to limit the model predictions to a specific range, i.e., the targeted attacks. Our attack leverages the superior capability of black-box, model-agnostic explainers in interpreting the model decision boundaries, thereby pinpointing the critical code snippet to apply semantic-preserving perturbations. The evaluation results demonstrate that compared with the state-of-the-art attacks, the proposed attacks achieve higher attack success rate in almost all scenarios, while also improving the efficiency and transferability. Our real-world case studies on vulnerability detection and classification further demonstrate the security implications of our attacks, highlighting the urgent need to further enhance the robustness of existing BCSD models.

Rui Zhang, Xiaoyang Hou, Zhihua Tian et al.

Graph clustering is an unsupervised machine learning method that partitions the nodes in a graph into different groups. Despite achieving significant progress in exploiting both attributed and structured data information, graph clustering methods often face practical challenges related to data isolation. Moreover, the absence of collaborative methods for graph clustering limits their effectiveness. In this paper, we propose a collaborative graph clustering framework for attributed graphs, supporting attributed graph clustering over vertically partitioned data with different participants holding distinct features of the same data. Our method leverages a novel technique that reduces the sample space, improving the efficiency of the attributed graph clustering method. Furthermore, we compare our method to its centralized counterpart under a proximity condition, demonstrating that the successful local results of each participant contribute to the overall success of the collaboration. We fully implement our approach and evaluate its utility and efficiency by conducting experiments on four public datasets. The results demonstrate that our method achieves comparable accuracy levels to centralized attributed graph clustering methods. Our collaborative graph clustering framework provides an efficient and effective solution for graph clustering challenges related to data isolation.

Shaoke Xi, Jiaqi Gao, Mengqi Liu et al.

With the growing performance requirements on networked applications, there is a new trend of offloading stateful network applications to SmartNICs to improve performance and reduce the total cost of ownership. However, offloading stateful network applications is non-trivial due to state operation complexity, state resource consumption, and the complicated relationship between traffic and state. Naively partitioning the program by state or traffic can result in a suboptimal partition plan with higher CPU usage or even packet drops. In this paper, we propose Cora, a compiler and runtime that offloads stateful network applications to SmartNIC-accelerated hosts. Cora compiler introduces an accurate performance model for each SmartNIC and employs an efficient compiling algorithm to search the offloading plan. Cora runtime can monitor traffic dynamics and adapt to minimize CPU usage. Cora is built atop Netronome Agilio and BlueField 2 SmartNICs. Our evaluation shows that for the same throughput target, Cora can propose partition plans saving up to 94.0% CPU cores, 1.9 times more than baseline solutions. Under the same resource constraint, Cora can accelerate network functions by 44.9%-82.3%. Cora runtime can adapt to traffic changes and keep CPU usage low.

Yihao Zheng, Haocheng Xia, Junyuan Pang et al.

Watermarking is broadly utilized to protect ownership of shared data while preserving data utility. However, existing watermarking methods for tabular datasets fall short on the desired properties (detectability, non-intrusiveness, and robustness) and only preserve data utility from the perspective of data statistics, ignoring the performance of downstream ML models trained on the datasets. Can we watermark tabular datasets without significantly compromising their utility for training ML models while preventing attackers from training usable ML models on attacked datasets? In this paper, we propose a hypothesis testing-based watermarking scheme, TabularMark. Data noise partitioning is utilized for data perturbation during embedding, which is adaptable for numerical and categorical attributes while preserving the data utility. For detection, a custom-threshold one proportion z-test is employed, which can reliably determine the presence of the watermark. Experiments on real-world and synthetic datasets demonstrate the superiority of TabularMark in detectability, non-intrusiveness, and robustness.

Zhibo Wang, He Wang, Shuaifan Jin et al.

Face recognition service providers protect face privacy by extracting compact and discriminative facial features (representations) from images, and storing the facial features for real-time recognition. However, such features can still be exploited to recover the appearance of the original face by building a reconstruction network. Although several privacy-preserving methods have been proposed, the enhancement of face privacy protection is at the expense of accuracy degradation. In this paper, we propose an adversarial features-based face privacy protection (AdvFace) approach to generate privacy-preserving adversarial features, which can disrupt the mapping from adversarial features to facial images to defend against reconstruction attacks. To this end, we design a shadow model which simulates the attackers' behavior to capture the mapping function from facial features to images and generate adversarial latent noise to disrupt the mapping. The adversarial features rather than the original features are stored in the server's database to prevent leaked features from exposing facial information. Moreover, the AdvFace requires no changes to the face recognition network and can be implemented as a privacy-enhancing plugin in deployed face recognition systems. Extensive experimental results demonstrate that AdvFace outperforms the state-of-the-art face privacy-preserving methods in defending against reconstruction attacks while maintaining face recognition accuracy.

Zhou Yu, Lixiang Zheng, Zhou Zhao et al.

Building benchmarks to systemically analyze different capabilities of video question answering (VideoQA) models is challenging yet crucial. Existing benchmarks often use non-compositional simple questions and suffer from language biases, making it difficult to diagnose model weaknesses incisively. A recent benchmark AGQA poses a promising paradigm to generate QA pairs automatically from pre-annotated scene graphs, enabling it to measure diverse reasoning abilities with granular control. However, its questions have limitations in reasoning about the fine-grained semantics in videos as such information is absent in its scene graphs. To this end, we present ANetQA, a large-scale benchmark that supports fine-grained compositional reasoning over the challenging untrimmed videos from ActivityNet. Similar to AGQA, the QA pairs in ANetQA are automatically generated from annotated video scene graphs. The fine-grained properties of ANetQA are reflected in the following: (i) untrimmed videos with fine-grained semantics; (ii) spatio-temporal scene graphs with fine-grained taxonomies; and (iii) diverse questions generated from fine-grained templates. ANetQA attains 1.4 billion unbalanced and 13.4 million balanced QA pairs, which is an order of magnitude larger than AGQA with a similar number of videos. Comprehensive experiments are performed for state-of-the-art methods. The best model achieves 44.5% accuracy while human performance tops out at 84.5%, leaving sufficient room for improvement.

Rui Zhang, Jian Liu, Yuan Ding et al.

In S&P '21, Jia et al. proposed a new concept/mechanism named proof-of-learning (PoL), which allows a prover to demonstrate ownership of a machine learning model by proving integrity of the training procedure. It guarantees that an adversary cannot construct a valid proof with less cost (in both computation and storage) than that made by the prover in generating the proof. A PoL proof includes a set of intermediate models recorded during training, together with the corresponding data points used to obtain each recorded model. Jia et al. claimed that an adversary merely knowing the final model and training dataset cannot efficiently find a set of intermediate models with correct data points. In this paper, however, we show that PoL is vulnerable to ``adversarial examples''! Specifically, in a similar way as optimizing an adversarial example, we could make an arbitrarily-chosen data point ``generate'' a given model, hence efficiently generating intermediate models with correct data points. We demonstrate, both theoretically and empirically, that we are able to generate a valid proof with significantly less cost than generating a proof by the prover.

Muhui Jiang, Tianyi Xu, Yajin Zhou et al.

Emulator is widely used to build dynamic analysis frameworks due to its fine-grained tracing capability, full system monitoring functionality, and scalability of running on different operating systemsand architectures. However, whether the emulator is consistent with real devices is unknown. To understand this problem, we aim to automatically locate inconsistent instructions, which behave differently between emulators and real devices. We target ARM architecture, which provides machine readable specification. Based on the specification, we propose a test case generator by designing and implementing the first symbolic execution engine for ARM architecture specification language (ASL). We generate 2,774,649 representative instruction streams and conduct differential testing with these instruction streams between four ARM real devices in different architecture versions (i.e., ARMv5, ARMv6, ARMv7-a, and ARMv8-a) and the state-of-the-art emulators (i.e., QEMU). We locate 155,642 inconsistent instruction streams, which cover 30% of all instruction encodings and 47.8% of the instructions. We find undefined implementation in ARM manual and implementation bugs of QEMU are the major causes of inconsistencies. Furthermore, we discover four QEMU bugs, which are confirmed and patched by thedevelopers, covering 13 instruction encodings including the most commonly used ones (e.g.,STR,BLX). With the inconsistent instructions, we build three security applications and demonstrate thecapability of these instructions on detecting emulators, anti-emulation, and anti-fuzzing.

Yuan Chen, Jiaqi Li, Guorui Xu et al.

Since its debut, SGX has been used in many applications, e.g., secure data processing. However, previous systems usually assume a trusted enclave and ignore the security issues caused by an untrusted enclave. For instance, a vulnerable (or even malicious) third-party enclave can be exploited to attack the host application and the rest of the system. In this paper, we propose an efficient mechanism to confine an untrusted enclave's behaviors. The threats of an untrusted enclave come from the enclave-host asymmetries. They can be abused to access arbitrary memory regions of its host application, jump to any code location after leaving the enclave and forge the stack register to manipulate the saved context. Our solution breaks such asymmetries and establishes mutual distrust between the host application and the enclave. It leverages Intel MPK for efficient memory isolation and the x86 single-step debugging mechanism to capture the event when an enclave is existing. It then performs the integrity check for the jump target and the stack pointer. We have solved two practical challenges and implemented a prototype system. The evaluation with multiple micro-benchmarks and representative real-world applications demonstrated the efficiency of our system, with less than 4% performance overhead.

Xiaochen Li, Weiran Liu, Hanwen Feng et al.

The shuffle model is recently proposed to address the issue of severe utility loss in Local Differential Privacy (LDP) due to distributed data randomization.In the shuffle model, a shuffler is utilized to break the link between the user identity and the message uploaded to the data analyst. Since less noise needs to be introduced to achieve the same privacy guarantee, following this paradigm, the utility of privacy-preserving data collection is improved. We propose DUMP (\underline{DUM}my-\underline{P}oint-based), a framework for privacy-preserving histogram estimation in the shuffle model. The core of DUMP is a new concept of \emph{dummy blanket}, which enables enhancing privacy by just introducing \textit{points }on the user side and further improving the utility of the shuffle model.We instantiate DUMP by proposing two protocols: pureDUMP and mixDUMP, and conduct a comprehensive experimental evaluation to compare them with existing protocols. The experimental results show that, under the same privacy guarantee, (1) the proposed protocols have significant improvements in communication efficiency over all existing multi-message protocols, by at least 3 orders of magnitude; (2) they achieve competitive utility, while the only known protocol (Ghazi \textit{et al.}, PMLR 2020) having better utility than ours employs hard-to-exactly-sample distributions which are vulnerable to floating-point attacks (CCS 2012).

Jianwei Liu, Jinsong Han, Feng Lin et al.

Wireless signal-based gesture recognition has promoted the developments of VR game, smart home, etc. However, traditional approaches suffer from the influence of the domain gap. Low recognition accuracy occurs when the recognition model is trained in one domain but is used in another domain. Though some solutions, such as adversarial learning, transfer learning and body-coordinate velocity profile, have been proposed to achieve cross-domain recognition, these solutions more or less have flaws. In this paper, we define the concept of domain gap and then propose a more promising solution, namely DI, to eliminate domain gap and further achieve domain-independent gesture recognition. DI leverages the sign map of the gradient map as the domain gap eliminator to improve the recognition accuracy. We conduct experiments with ten domains and ten gestures. The experiment results show that DI can achieve the recognition accuracies of 87.13%, 90.12% and 94.45% on KNN, SVM and CNN, which outperforms existing solutions.

Yang Liu, Zhuo Ma, Ximeng Liu et al.

Nowadays, machine learning models, especially neural networks, become prevalent in many real-world applications.These models are trained based on a one-way trip from user data: as long as users contribute their data, there is no way to withdraw; and it is well-known that a neural network memorizes its training data. This contradicts the "right to be forgotten" clause of GDPR, potentially leading to law violations. To this end, machine unlearning becomes a popular research topic, which allows users to eliminate memorization of their private data from a trained machine learning model.In this paper, we propose the first uniform metric called for-getting rate to measure the effectiveness of a machine unlearning method. It is based on the concept of membership inference and describes the transformation rate of the eliminated data from "memorized" to "unknown" after conducting unlearning. We also propose a novel unlearning method calledForsaken. It is superior to previous work in either utility or efficiency (when achieving the same forgetting rate). We benchmark Forsaken with eight standard datasets to evaluate its performance. The experimental results show that it can achieve more than 90\% forgetting rate on average and only causeless than 5\% accuracy loss.

Tianhang Zheng, Zhi Sun, Kui Ren

Trusted identification is critical to secure IoT devices. However, the limited memory and computation power of low-end IoT devices prevent the direct usage of conventional identification systems. RF fingerprinting is a promising technique to identify low-end IoT devices since it only requires the RF signals that most IoT devices can produce for communication. However, most existing RF fingerprinting systems are data-dependent and/or not robust to impacts from wireless channels. To address the above problems, we propose to exploit the mathematical expression of the physical-layer process, regarded as a function $\mathbf{\mathcal{F}(\cdot)}$, for device identification. $\mathbf{\mathcal{F}(\cdot)}$ is not directly derivable, so we further propose a model to learn it and employ this function model as the device fingerprint in our system, namely $\mathcal{F}$ID. Our proposed function model characterizes the unique physical-layer process of a device that is independent of the transmitted data, and hence, our system $\mathcal{F}$ID is data-independent and thus resilient against signal replay attacks. Modeling and further separating channel effects from the function model makes $\mathcal{F}$ID channel-robust. We evaluate $\mathcal{F}$ID on thousands of random signal packets from $33$ different devices in different environments and scenarios, and the overall identification accuracy is over $99\%$.

Yaliang Li, Houping Xiao, Zhan Qin et al.

Nowadays, crowd sensing becomes increasingly more popular due to the ubiquitous usage of mobile devices. However, the quality of such human-generated sensory data varies significantly among different users. To better utilize sensory data, the problem of truth discovery, whose goal is to estimate user quality and infer reliable aggregated results through quality-aware data aggregation, has emerged as a hot topic. Although the existing truth discovery approaches can provide reliable aggregated results, they fail to protect the private information of individual users. Moreover, crowd sensing systems typically involve a large number of participants, making encryption or secure multi-party computation based solutions difficult to deploy. To address these challenges, in this paper, we propose an efficient privacy-preserving truth discovery mechanism with theoretical guarantees of both utility and privacy. The key idea of the proposed mechanism is to perturb data from each user independently and then conduct weighted aggregation among users' perturbed data. The proposed approach is able to assign user weights based on information quality, and thus the aggregated results will not deviate much from the true results even when large noise is added. We adapt local differential privacy definition to this privacy-preserving task and demonstrate the proposed mechanism can satisfy local differential privacy while preserving high aggregation accuracy. We formally quantify utility and privacy trade-off and further verify the claim by experiments on both synthetic data and a real-world crowd sensing system.

Xiao Chen, Chaoran Li, Derui Wang et al.

Machine learning based solutions have been successfully employed for automatic detection of malware on Android. However, machine learning models lack robustness to adversarial examples, which are crafted by adding carefully chosen perturbations to the normal inputs. So far, the adversarial examples can only deceive detectors that rely on syntactic features (e.g., requested permissions, API calls, etc), and the perturbations can only be implemented by simply modifying application's manifest. While recent Android malware detectors rely more on semantic features from Dalvik bytecode rather than manifest, existing attacking/defending methods are no longer effective. In this paper, we introduce a new attacking method that generates adversarial examples of Android malware and evades being detected by the current models. To this end, we propose a method of applying optimal perturbations onto Android APK that can successfully deceive the machine learning detectors. We develop an automated tool to generate the adversarial examples without human intervention. In contrast to existing works, the adversarial examples crafted by our method can also deceive recent machine learning based detectors that rely on semantic features such as control-flow-graph. The perturbations can also be implemented directly onto APK's Dalvik bytecode rather than Android manifest to evade from recent detectors. We demonstrate our attack on two state-of-the-art Android malware detection schemes, MaMaDroid and Drebin. Our results show that the malware detection rates decreased from 96% to 0% in MaMaDroid, and from 97% to 0% in Drebin, with just a small number of codes to be inserted into the APK.

Huayi Duan, Cong Wang, Xingliang Yuan et al.

Running off-site software middleboxes at third-party service providers has been a popular practice. However, routing large volumes of raw traffic, which may carry sensitive information, to a remote site for processing raises severe security concerns. Prior solutions often abstract away important factors pertinent to real-world deployment. In particular, they overlook the significance of metadata protection and stateful processing. Unprotected traffic metadata like low-level headers, size and count, can be exploited to learn supposedly encrypted application contents. Meanwhile, tracking the states of 100,000s of flows concurrently is often indispensable in production-level middleboxes deployed at real networks. We present LightBox, the first system that can drive off-site middleboxes at near-native speed with stateful processing and the most comprehensive protection to date. Built upon commodity trusted hardware, Intel SGX, LightBox is the product of our systematic investigation of how to overcome the inherent limitations of secure enclaves using domain knowledge and customization. First, we introduce an elegant virtual network interface that allows convenient access to fully protected packets at line rate without leaving the enclave, as if from the trusted source network. Second, we provide complete flow state management for efficient stateful processing, by tailoring a set of data structures and algorithms optimized for the highly constrained enclave space. Extensive evaluations demonstrate that LightBox, with all security benefits, can achieve 10Gbps packet I/O, and that with case studies on three stateful middleboxes, it can operate at near-native speed.

Wenhao Wang, Zhi Sun, Kui Ren et al.

Wireless Physical Layer Identification (WPLI) system aims at identifying or classifying authorized devices based on the unique Radio Frequency Fingerprints (RFFs) extracted from their radio frequency signals at the physical layer. Current works of WPLI focus on demonstrating system feasibility based on experimental error performance of WPLI with a fixed number of users. While an important question remains to be answered: what's the user number that WPLI can accommodate using different RFFs and receiving equipment. The user capacity of the WPLI can be a major concern for practical system designers and can also be a key metric to evaluate the classification performance of WPLI. In this work, we establish a theoretical understanding on user capacity of WPLI in an information-theoretic perspective. We apply information-theoretic modeling on RFF features of WPLI. An information-theoretic approach is consequently proposed based on mutual information between RFF and user identity to characterize the user capacity of WPLI. Based on this theoretical tool, the achievable user capacity of WPLI is characterized under practical constrains of off-the-shelf receiving devices. Field experiments on classification error performance are conducted for the validation of the information-theoretic user capacity characterization.

Wenhao Wang, Zhi Sun, Kui Ren et al.

The wireless physical-layer identification (WPLI) techniques utilize the unique features of the physical waveforms of wireless signals to identify and classify authorized devices. As the inherent physical layer features are difficult to forge, WPLI is deemed as a promising technique for wireless security solutions. However, as of today it still remains unclear whether existing WPLI techniques can be applied under real-world requirements and constraints. In this paper, through both theoretical modeling and experiment validation, the reliability and differentiability of WPLI techniques are rigorously evaluated, especially under the constraints of state-of-art wireless devices, real operation environments, as well as wireless protocols and regulations. Specifically, a theoretical model is first established to systematically describe the complete procedure of WPLI. More importantly, the proposed model is then implemented to thoroughly characterize various WPLI techniques that utilize the spectrum features coming from the non-linear RF-front-end, under the influences from different transmitters, receivers, and wireless channels. Subsequently, the limitations of existing WPLI techniques are revealed and evaluated in details using both the developed theoretical model and in-lab experiments. The real-world requirements and constraints are characterized along each step in WPLI, including i) the signal processing at the transmitter (device to be identified), ii) the various physical layer features that originate from circuits, antenna, and environments, iii) the signal propagation in various wireless channels, iv) the signal reception and processing at the receiver (the identifier), and v) the fingerprint extraction and classification at the receiver.

Muyuan Li, Haojin Zhu, Zhaoyu Gao et al.

Many popular location-based social networks (LBSNs) support built-in location-based social discovery with hundreds of millions of users around the world. While user (near) realtime geographical information is essential to enable location-based social discovery in LBSNs, the importance of user location privacy has also been recognized by leading real-world LBSNs. To protect user's exact geographical location from being exposed, a number of location protection approaches have been adopted by the industry so that only relative location information are publicly disclosed. These techniques are assumed to be secure and are exercised on the daily base. In this paper, we question the safety of these location-obfuscation techniques used by existing LBSNs. We show, for the first time, through real world attacks that they can all be easily destroyed by an attacker with the capability of no more than a regular LBSN user. In particular, by manipulating location information fed to LBSN client app, an ill-intended regular user can easily deduce the exact location information by running LBSN apps as location oracle and performing a series of attacking strategies. We develop an automated user location tracking system and test it on the most popular LBSNs including Wechat, Skout and Momo. We demonstrate its effectiveness and efficiency via a 3 week real-world experiment with 30 volunteers. Our evaluation results show that we could geo-locate a target with high accuracy and can readily recover users' Top 5 locations. We also propose to use grid reference system and location classification to mitigate the attacks. Our work shows that the current industrial best practices on user location privacy protection are completely broken, and it is critical to address this immediate threat.