Kaidi Xu

Huan Zhang, Shiqi Wang, Kaidi Xu et al. · amazon-science

Bound propagation methods, when combined with branch and bound, are among the most effective methods to formally verify properties of deep neural networks such as correctness, robustness, and safety. However, existing works cannot handle the general form of cutting plane constraints widely accepted in traditional solvers, which are crucial for strengthening verifiers with tightened convex relaxations. In this paper, we generalize the bound propagation procedure to allow the addition of arbitrary cutting plane constraints, including those involving relaxed integer variables that do not appear in existing bound propagation formulations. Our generalized bound propagation method, GCP-CROWN, opens up the opportunity to apply general cutting plane methods for neural network verification while benefiting from the efficiency and GPU acceleration of bound propagation methods. As a case study, we investigate the use of cutting planes generated by off-the-shelf mixed integer programming (MIP) solver. We find that MIP solvers can generate high-quality cutting planes for strengthening bound-propagation-based verifiers using our new formulation. Since the branching-focused bound propagation procedure and the cutting-plane-focused MIP solver can run in parallel utilizing different types of hardware (GPUs and CPUs), their combination can quickly explore a large number of branches with strong cutting planes, leading to strong verification performance. Experiments demonstrate that our method is the first verifier that can completely solve the oval20 benchmark and verify twice as many instances on the oval21 benchmark compared to the best tool in VNN-COMP 2021, and also noticeably outperforms state-of-the-art verifiers on a wide range of benchmarks. GCP-CROWN is part of the $α,\!β$-CROWN verifier, the VNN-COMP 2022 winner. Code is available at http://PaperCode.cc/GCP-CROWN

Jinhao Duan, Fei Kong, Shiqi Wang et al. · amazon-science

Diffusion-based generative models have shown great potential for image synthesis, but there is a lack of research on the security and privacy risks they may pose. In this paper, we investigate the vulnerability of diffusion models to Membership Inference Attacks (MIAs), a common privacy concern. Our results indicate that existing MIAs designed for GANs or VAE are largely ineffective on diffusion models, either due to inapplicable scenarios (e.g., requiring the discriminator of GANs) or inappropriate assumptions (e.g., closer distances between synthetic samples and member samples). To address this gap, we propose Step-wise Error Comparing Membership Inference (SecMI), a query-based MIA that infers memberships by assessing the matching of forward process posterior estimation at each timestep. SecMI follows the common overfitting assumption in MIA where member samples normally have smaller estimation errors, compared with hold-out samples. We consider both the standard diffusion models, e.g., DDPM, and the text-to-image diffusion models, e.g., Latent Diffusion Models and Stable Diffusion. Experimental results demonstrate that our methods precisely infer the membership with high confidence on both of the two scenarios across multiple different datasets. Code is available at https://github.com/jinhaoduan/SecMI.

Jinhao Duan, Hao Cheng, Shiqi Wang et al.

Large Language Models (LLMs) show promising results in language generation and instruction following but frequently "hallucinate", making their outputs less reliable. Despite Uncertainty Quantification's (UQ) potential solutions, implementing it accurately within LLMs is challenging. Our research introduces a simple heuristic: not all tokens in auto-regressive LLM text equally represent the underlying meaning, as "linguistic redundancy" often allows a few keywords to convey the essence of long sentences. However, current methods underestimate this inequality when assessing uncertainty, causing tokens with limited semantics to be equally or excessively weighted in UQ. To correct this, we propose Shifting Attention to more Relevant (SAR) components at both token- and sentence-levels for better UQ. We conduct extensive experiments involving a range of popular "off-the-shelf" LLMs, such as Vicuna, WizardLM, and LLaMA-2-chat, with model sizes extending up to 33B parameters. We evaluate various free-form question-answering tasks, encompassing domains such as reading comprehension, science Q&A, and medical Q&A. Our experimental results, coupled with a comprehensive demographic analysis, demonstrate the superior performance of SAR. The code is available at https://github.com/jinhaoduan/SAR.

Jinhao Duan, Quanfu Fan, Hao Cheng et al.

Recent works reveal that adversarial augmentation benefits the generalization of neural networks (NNs) if used in an appropriate manner. In this paper, we introduce Temporal Adversarial Augmentation (TA), a novel video augmentation technique that utilizes temporal attention. Unlike conventional adversarial augmentation, TA is specifically designed to shift the attention distributions of neural networks with respect to video clips by maximizing a temporal-related loss function. We demonstrate that TA will obtain diverse temporal views, which significantly affect the focus of neural networks. Training with these examples remedies the flaw of unbalanced temporal information perception and enhances the ability to defend against temporal shifts, ultimately leading to better generalization. To leverage TA, we propose Temporal Video Adversarial Fine-tuning (TAF) framework for improving video representations. TAF is a model-agnostic, generic, and interpretability-friendly training strategy. We evaluate TAF with four powerful models (TSM, GST, TAM, and TPN) over three challenging temporal-related benchmarks (Something-something V1&V2 and diving48). Experimental results demonstrate that TAF effectively improves the test accuracy of these models with notable margins without introducing additional parameters or computational costs. As a byproduct, TAF also improves the robustness under out-of-distribution (OOD) settings. Code is available at https://github.com/jinhaoduan/TAF.

Chenan Wang, Jinhao Duan, Chaowei Xiao et al.

Traditional adversarial attacks concentrate on manipulating clean examples in the pixel space by adding adversarial perturbations. By contrast, semantic adversarial attacks focus on changing semantic attributes of clean examples, such as color, context, and features, which are more feasible in the real world. In this paper, we propose a framework to quickly generate a semantic adversarial attack by leveraging recent diffusion models since semantic information is included in the latent space of well-trained diffusion models. Then there are two variants of this framework: 1) the Semantic Transformation (ST) approach fine-tunes the latent space of the generated image and/or the diffusion model itself; 2) the Latent Masking (LM) approach masks the latent space with another target image and local backpropagation-based interpretation methods. Additionally, the ST approach can be applied in either white-box or black-box settings. Extensive experiments are conducted on CelebA-HQ and AFHQ datasets, and our framework demonstrates great fidelity, generalizability, and transferability compared to other baselines. Our approaches achieve approximately 100% attack success rate in multiple settings with the best FID as 36.61. Code is available at https://github.com/steven202/semantic_adv_via_dm.

Yixin Liu, Kaidi Xu, Xun Chen et al.

The open source of large amounts of image data promotes the development of deep learning techniques. Along with this comes the privacy risk of these open-source image datasets being exploited by unauthorized third parties to train deep learning models for commercial or illegal purposes. To avoid the abuse of public data, a poisoning-based technique, the unlearnable example, is proposed to significantly degrade the generalization performance of models by adding a kind of imperceptible noise to the data. To further enhance its robustness against adversarial training, existing works leverage iterative adversarial training on both the defensive noise and the surrogate model. However, it still remains unknown whether the robustness of unlearnable examples primarily comes from the effect of enhancement in the surrogate model or the defensive noise. Observing that simply removing the adversarial noise on the training process of the defensive noise can improve the performance of robust unlearnable examples, we identify that solely the surrogate model's robustness contributes to the performance. Furthermore, we found a negative correlation exists between the robustness of defensive noise and the protection performance, indicating defensive noise's instability issue. Motivated by this, to further boost the robust unlearnable example, we introduce stable error-minimizing noise (SEM), which trains the defensive noise against random perturbation instead of the time-consuming adversarial perturbation to improve the stability of defensive noise. Through extensive experiments, we demonstrate that SEM achieves a new state-of-the-art performance on CIFAR-10, CIFAR-100, and ImageNet Subset in terms of both effectiveness and efficiency. The code is available at https://github.com/liuyixin-louis/Stable-Unlearnable-Example.

Fei Kong, Jinhao Duan, Lichao Sun et al.

Though diffusion models excel in image generation, their step-by-step denoising leads to slow generation speeds. Consistency training addresses this issue with single-step sampling but often produces lower-quality generations and requires high training costs. In this paper, we show that optimizing consistency training loss minimizes the Wasserstein distance between target and generated distributions. As timestep increases, the upper bound accumulates previous consistency training losses. Therefore, larger batch sizes are needed to reduce both current and accumulated losses. We propose Adversarial Consistency Training (ACT), which directly minimizes the Jensen-Shannon (JS) divergence between distributions at each timestep using a discriminator. Theoretically, ACT enhances generation quality, and convergence. By incorporating a discriminator into the consistency training framework, our method achieves improved FID scores on CIFAR10 and ImageNet 64$\times$64 and LSUN Cat 256$\times$256 datasets, retains zero-shot image inpainting capabilities, and uses less than $1/6$ of the original batch size and fewer than $1/2$ of the model parameters and training steps compared to the baseline method, this leads to a substantial reduction in resource consumption. Our code is available:https://github.com/kong13661/ACT

Ningfei Wang, Yunpeng Luo, Takami Sato et al.

In autonomous driving (AD), accurate perception is indispensable to achieving safe and secure driving. Due to its safety-criticality, the security of AD perception has been widely studied. Among different attacks on AD perception, the physical adversarial object evasion attacks are especially severe. However, we find that all existing literature only evaluates their attack effect at the targeted AI component level but not at the system level, i.e., with the entire system semantics and context such as the full AD pipeline. Thereby, this raises a critical research question: can these existing researches effectively achieve system-level attack effects (e.g., traffic rule violations) in the real-world AD context? In this work, we conduct the first measurement study on whether and how effectively the existing designs can lead to system-level effects, especially for the STOP sign-evasion attacks due to their popularity and severity. Our evaluation results show that all the representative prior works cannot achieve any system-level effects. We observe two design limitations in the prior works: 1) physical model-inconsistent object size distribution in pixel sampling and 2) lack of vehicle plant model and AD system model consideration. Then, we propose SysAdv, a novel system-driven attack design in the AD context and our evaluation results show that the system-level effects can be significantly improved, i.e., the violation rate increases by around 70%.

Ruipeng Ma, Jinhao Duan, Fei Kong et al.

Image synthesis has seen significant advancements with the advent of diffusion-based generative models like Denoising Diffusion Probabilistic Models (DDPM) and text-to-image diffusion models. Despite their efficacy, there is a dearth of research dedicated to detecting diffusion-generated images, which could pose potential security and privacy risks. This paper addresses this gap by proposing a novel detection method called Stepwise Error for Diffusion-generated Image Detection (SeDID). Comprising statistical-based $\text{SeDID}_{\text{Stat}}$ and neural network-based $\text{SeDID}_{\text{NNs}}$, SeDID exploits the unique attributes of diffusion models, namely deterministic reverse and deterministic denoising computation errors. Our evaluations demonstrate SeDID's superior performance over existing methods when applied to diffusion models. Thus, our work makes a pivotal contribution to distinguishing diffusion model-generated images, marking a significant step in the domain of artificial intelligence security.

Husheng Han, Xing Hu, Kaidi Xu et al.

DNN-based video object detection (VOD) powers autonomous driving and video surveillance industries with rising importance and promising opportunities. However, adversarial patch attack yields huge concern in live vision tasks because of its practicality, feasibility, and powerful attack effectiveness. This work proposes Themis, a software/hardware system to defend against adversarial patches for real-time robust video object detection. We observe that adversarial patches exhibit extremely localized superficial feature importance in a small region with non-robust predictions, and thus propose the adversarial region detection algorithm for adversarial effect elimination. Themis also proposes a systematic design to efficiently support the algorithm by eliminating redundant computations and memory traffics. Experimental results show that the proposed methodology can effectively recover the system from the adversarial attack with negligible hardware overhead.

Jiaqi Xue, Lei Xu, Lin Chen et al.

Performing neural network inference on encrypted data without decryption is one popular method to enable privacy-preserving neural networks (PNet) as a service. Compared with regular neural networks deployed for machine-learning-as-a-service, PNet requires additional encoding, e.g., quantized-precision numbers, and polynomial activation. Encrypted input also introduces novel challenges such as adversarial robustness and security. To the best of our knowledge, we are the first to study questions including (i) Whether PNet is more robust against adversarial inputs than regular neural networks? (ii) How to design a robust PNet given the encrypted input without decryption? We propose PNet-Attack to generate black-box adversarial examples that can successfully attack PNet in both target and untarget manners. The attack results show that PNet robustness against adversarial inputs needs to be improved. This is not a trivial task because the PNet model owner does not have access to the plaintext of the input values, which prevents the application of existing detection and defense methods such as input tuning, model normalization, and adversarial training. To tackle this challenge, we propose a new fast and accurate noise insertion method, called RPNet, to design Robust and Private Neural Networks. Our comprehensive experiments show that PNet-Attack reduces at least $2.5\times$ queries than prior works. We theoretically analyze our RPNet methods and demonstrate that RPNet can decrease $\sim 91.88\%$ attack success rate.

Hao Cheng, Jinhao Duan, Hui Li et al.

Recently, there has been a surge of interest and attention in Transformer-based structures, such as Vision Transformer (ViT) and Vision Multilayer Perceptron (VMLP). Compared with the previous convolution-based structures, the Transformer-based structure under investigation showcases a comparable or superior performance under its distinctive attention-based input token mixer strategy. Introducing adversarial examples as a robustness consideration has had a profound and detrimental impact on the performance of well-established convolution-based structures. This inherent vulnerability to adversarial attacks has also been demonstrated in Transformer-based structures. In this paper, our emphasis lies on investigating the intrinsic robustness of the structure rather than introducing novel defense measures against adversarial attacks. To address the susceptibility to robustness issues, we employ a rational structure design approach to mitigate such vulnerabilities. Specifically, we enhance the adversarial robustness of the structure by increasing the proportion of high-frequency structural robust biases. As a result, we introduce a novel structure called Robust Bias Transformer-based Structure (RBFormer) that shows robust superiority compared to several existing baseline structures. Through a series of extensive experiments, RBFormer outperforms the original structures by a significant margin, achieving an impressive improvement of +16.12% and +5.04% across different evaluation criteria on CIFAR-10 and ImageNet-1k, respectively.

Zhengyue Zhao, Jinhao Duan, Kaidi Xu et al.

Stable Diffusion has established itself as a foundation model in generative AI artistic applications, receiving widespread research and application. Some recent fine-tuning methods have made it feasible for individuals to implant personalized concepts onto the basic Stable Diffusion model with minimal computational costs on small datasets. However, these innovations have also given rise to issues like facial privacy forgery and artistic copyright infringement. In recent studies, researchers have explored the addition of imperceptible adversarial perturbations to images to prevent potential unauthorized exploitation and infringements when personal data is used for fine-tuning Stable Diffusion. Although these studies have demonstrated the ability to protect images, it is essential to consider that these methods may not be entirely applicable in real-world scenarios. In this paper, we systematically evaluate the use of perturbations to protect images within a practical threat model. The results suggest that these approaches may not be sufficient to safeguard image privacy and copyright effectively. Furthermore, we introduce a purification method capable of removing protected perturbations while preserving the original image structure to the greatest extent possible. Experiments reveal that Stable Diffusion can effectively learn from purified images over all protective methods.

Pucheng Dang, Xing Hu, Kaidi Xu et al.

Unlearnable examples are proposed to prevent third parties from exploiting unauthorized data, which generates unlearnable examples by adding imperceptible perturbations to public publishing data. These unlearnable examples proficiently misdirect the model training process, leading it to focus on learning perturbation features while neglecting the semantic features of the image. In this paper, we make an in-depth analysis and observe that models can learn both image features and perturbation features of unlearnable examples at an early training stage, but are rapidly trapped in perturbation features learning since the shallow layers tend to learn on perturbation features and propagate harmful activations to deeper layers. Based on the observations, we propose Progressive Staged Training, a self-adaptive training framework specially designed to break unlearnable examples. The proposed framework effectively prevents models from becoming trapped in learning perturbation features. We evaluated our method on multiple model architectures over diverse datasets, e.g., CIFAR-10, CIFAR-100, and ImageNet-mini. Our method circumvents the unlearnability of all state-of-the-art methods in the literature, revealing that existing unlearnable examples give a false sense of privacy protection and provide a reliable baseline for further evaluation of unlearnable techniques.

Yue Huang, Lichao Sun, Haoran Wang et al.

Large language models (LLMs), exemplified by ChatGPT, have gained considerable attention for their excellent natural language processing capabilities. Nonetheless, these LLMs present many challenges, particularly in the realm of trustworthiness. Therefore, ensuring the trustworthiness of LLMs emerges as an important topic. This paper introduces TrustLLM, a comprehensive study of trustworthiness in LLMs, including principles for different dimensions of trustworthiness, established benchmark, evaluation, and analysis of trustworthiness for mainstream LLMs, and discussion of open challenges and future directions. Specifically, we first propose a set of principles for trustworthy LLMs that span eight different dimensions. Based on these principles, we further establish a benchmark across six dimensions including truthfulness, safety, fairness, robustness, privacy, and machine ethics. We then present a study evaluating 16 mainstream LLMs in TrustLLM, consisting of over 30 datasets. Our findings firstly show that in general trustworthiness and utility (i.e., functional effectiveness) are positively related. Secondly, our observations reveal that proprietary LLMs generally outperform most open-source counterparts in terms of trustworthiness, raising concerns about the potential risks of widely accessible open-source LLMs. However, a few open-source LLMs come very close to proprietary ones. Thirdly, it is important to note that some LLMs may be overly calibrated towards exhibiting trustworthiness, to the extent that they compromise their utility by mistakenly treating benign prompts as harmful and consequently not responding. Finally, we emphasize the importance of ensuring transparency not only in the models themselves but also in the technologies that underpin trustworthiness. Knowing the specific trustworthy technologies that have been employed is crucial for analyzing their effectiveness.

Peng Kuang, Haibo Jin, Xiaoyu Han et al.

Process Reward Models (PRMs) have been proven to be highly effective in guiding test-time scaling (TTS) methods, which significantly boost the capabilities of LLM-based multi-agent systems. However, existing PRMs are text-based: they re-encode the entire trajectory text from scratch. In long multi-agent rollouts, the scoring cost, growing quadratically with respect to sequence length L, creates a severe computational bottleneck, severely limiting PRMs' application in long-context scenarios. To resolve this, we introduce KV-PRM, a highly efficient process reward model that eliminates the heavy text re-encoding by directly reading the KV cache produced naturally during the LLM's generation phase. By processing a single "verify token" against the pre-existing KV cache, KV-PRM reduces the scoring cost from O(L^2) to O(L). We formally prove that the KV cache contains strictly greater information capacity than text, and is more efficient for downstream reward modeling. Empirically, across the MATH, GSM8K, and AIME benchmarks, KV-PRM matches or strictly outperforms text-PRMs under various TTS methods such as Beam Search, MCTS, and Weighted Voting, with up to a 5,000x reduction in scoring FLOPs, a 37x reduction in latency, and a 34x reduction in per-sequence memory footprint compared to text-based PRMs.

Ningfei Wang, Shaoyuan Xie, Takami Sato et al.

Traffic Sign Recognition (TSR) is crucial for safe and correct driving automation. Recent works revealed a general vulnerability of TSR models to physical-world adversarial attacks, which can be low-cost, highly deployable, and capable of causing severe attack effects such as hiding a critical traffic sign or spoofing a fake one. However, so far existing works generally only considered evaluating the attack effects on academic TSR models, leaving the impacts of such attacks on real-world commercial TSR systems largely unclear. In this paper, we conduct the first large-scale measurement of physical-world adversarial attacks against commercial TSR systems. Our testing results reveal that it is possible for existing attack works from academia to have highly reliable (100\%) attack success against certain commercial TSR system functionality, but such attack capabilities are not generalizable, leading to much lower-than-expected attack success rates overall. We find that one potential major factor is a spatial memorization design that commonly exists in today's commercial TSR systems. We design new attack success metrics that can mathematically model the impacts of such design on the TSR system-level attack success, and use them to revisit existing attacks. Through these efforts, we uncover 7 novel observations, some of which directly challenge the observations or claims in prior works due to the introduction of the new metrics.

Hao Cheng, Erjia Xiao, Jindong Gu et al.

Large Vision-Language Models (LVLMs) rely on vision encoders and Large Language Models (LLMs) to exhibit remarkable capabilities on various multi-modal tasks in the joint space of vision and language. However, typographic attacks, which disrupt Vision-Language Models (VLMs) such as Contrastive Language-Image Pretraining (CLIP), have also been expected to be a security threat to LVLMs. Firstly, we verify typographic attacks on current well-known commercial and open-source LVLMs and uncover the widespread existence of this threat. Secondly, to better assess this vulnerability, we propose the most comprehensive and largest-scale Typographic Dataset to date. The Typographic Dataset not only considers the evaluation of typographic attacks under various multi-modal tasks but also evaluates the effects of typographic attacks, influenced by texts generated with diverse factors. Based on the evaluation results, we investigate the causes why typographic attacks impacting VLMs and LVLMs, leading to three highly insightful discoveries. During the process of further validating the rationality of our discoveries, we can reduce the performance degradation caused by typographic attacks from 42.07\% to 13.90\%. Code and Dataset are available in \href{https://github.com/ChaduCheng/TypoDeceptions}

Yifan Yao, Jinhao Duan, Kaidi Xu et al.

Large Language Models (LLMs), such as ChatGPT and Bard, have revolutionized natural language understanding and generation. They possess deep language comprehension, human-like text generation capabilities, contextual awareness, and robust problem-solving skills, making them invaluable in various domains (e.g., search engines, customer support, translation). In the meantime, LLMs have also gained traction in the security community, revealing security vulnerabilities and showcasing their potential in security-related tasks. This paper explores the intersection of LLMs with security and privacy. Specifically, we investigate how LLMs positively impact security and privacy, potential risks and threats associated with their use, and inherent vulnerabilities within LLMs. Through a comprehensive literature review, the paper categorizes the papers into "The Good" (beneficial LLM applications), "The Bad" (offensive applications), and "The Ugly" (vulnerabilities of LLMs and their defenses). We have some interesting findings. For example, LLMs have proven to enhance code security (code vulnerability detection) and data privacy (data confidentiality protection), outperforming traditional methods. However, they can also be harnessed for various attacks (particularly user-level attacks) due to their human-like reasoning abilities. We have identified areas that require further research efforts. For example, Research on model and parameter extraction attacks is limited and often theoretical, hindered by LLM parameter scale and confidentiality. Safe instruction tuning, a recent development, requires more exploration. We hope that our work can shed light on the LLMs' potential to both bolster and jeopardize cybersecurity.

Jinhao Duan, Fei Kong, Hao Cheng et al.

Object Hallucination (OH) has been acknowledged as one of the major trustworthy challenges in Large Vision-Language Models (LVLMs). Recent advancements in Large Language Models (LLMs) indicate that internal states, such as hidden states, encode the "overall truthfulness" of generated responses. However, it remains under-explored how internal states in LVLMs function and whether they could serve as "per-token" hallucination indicators, which is essential for mitigating OH. In this paper, we first conduct an in-depth exploration of LVLM internal states in relation to OH issues and discover that (1) LVLM internal states are high-specificity per-token indicators of hallucination behaviors. Moreover, (2) different LVLMs encode universal patterns of hallucinations in common latent subspaces, indicating that there exist "generic truthful directions" shared by various LVLMs. Based on these discoveries, we propose Truthful-Guided Pre-Intervention (TruthPrInt) that first learns the truthful direction of LVLM decoding and then applies truthful-guided inference-time intervention during LVLM decoding. We further propose ComnHallu to enhance both cross-LVLM and cross-data hallucination detection transferability by constructing and aligning hallucination latent subspaces. We evaluate TruthPrInt in extensive experimental settings, including in-domain and out-of-domain scenarios, over popular LVLMs and OH benchmarks. Experimental results indicate that TruthPrInt significantly outperforms state-of-the-art methods. Codes will be available at https://github.com/jinhaoduan/TruthPrInt.

Hao Cheng, Erjia Xiao, Yichi Wang et al.

Current Cross-Modality Generation Models (GMs) demonstrate remarkable capabilities in various generative tasks. Given the ubiquity and information richness of vision modality inputs in real-world scenarios, Cross-Vision tasks, encompassing Vision-Language Perception (VLP) and Image-to-Image (I2I), have attracted significant attention. Large Vision Language Models (LVLMs) and I2I Generation Models (GMs) are employed to handle VLP and I2I tasks, respectively. Previous research indicates that printing typographic words into input images significantly induces LVLMs and I2I GMs to produce disruptive outputs that are semantically aligned with those words. Additionally, visual prompts, as a more sophisticated form of typography, are also revealed to pose security risks to various applications of cross-vision tasks. However, the specific characteristics of the threats posed by visual prompts remain underexplored. In this paper, to comprehensively investigate the performance impact induced by Typographic Visual Prompt Injection (TVPI) in various LVLMs and I2I GMs, we propose the Typographic Visual Prompts Injection Dataset and thoroughly evaluate the TVPI security risks on various open-source and closed-source LVLMs and I2I GMs under visual prompts with different target semantics, deepening the understanding of TVPI threats.

Xu Zhang, Kaidi Xu, Ziqing Hu et al.

Mixture of Experts (MoE) have shown remarkable success in leveraging specialized expert networks for complex machine learning tasks. However, their susceptibility to adversarial attacks presents a critical challenge for deployment in robust applications. This paper addresses the critical question of how to incorporate robustness into MoEs while maintaining high natural accuracy. We begin by analyzing the vulnerability of MoE components, finding that expert networks are notably more susceptible to adversarial attacks than the router. Based on this insight, we propose a targeted robust training technique that integrates a novel loss function to enhance the adversarial robustness of MoE, requiring only the robustification of one additional expert without compromising training or inference efficiency. Building on this, we introduce a dual-model strategy that linearly combines a standard MoE model with our robustified MoE model using a smoothing parameter. This approach allows for flexible control over the robustness-accuracy trade-off. We further provide theoretical foundations by deriving certified robustness bounds for both the single MoE and the dual-model. To push the boundaries of robustness and accuracy, we propose a novel joint training strategy JTDMoE for the dual-model. This joint training enhances both robustness and accuracy beyond what is achievable with separate models. Experimental results on CIFAR-10 and TinyImageNet datasets using ResNet18 and Vision Transformer (ViT) architectures demonstrate the effectiveness of our proposed methods. The code is publicly available at https://github.com/TIML-Group/Robust-MoE-Dual-Model.

Jin Sun, Xiaoshuang Shi, Zhiyuan Wang et al.

Modeling in Computer Vision has evolved to MLPs. Vision MLPs naturally lack local modeling capability, to which the simplest treatment is combined with convolutional layers. Convolution, famous for its sliding window scheme, also suffers from this scheme of redundancy and lower parallel computation. In this paper, we seek to dispense with the windowing scheme and introduce a more elaborate and parallelizable method to exploit locality. To this end, we propose a new MLP module, namely Shifted-Pillars-Concatenation (SPC), that consists of two steps of processes: (1) Pillars-Shift, which generates four neighboring maps by shifting the input image along four directions, and (2) Pillars-Concatenation, which applies linear transformations and concatenation on the maps to aggregate local features. SPC module offers superior local modeling power and performance gains, making it a promising alternative to the convolutional layer. Then, we build a pure-MLP architecture called Caterpillar by replacing the convolutional layer with the SPC module in a hybrid model of sMLPNet. Extensive experiments show Caterpillar's excellent performance on both small-scale and ImageNet-1k classification benchmarks, with remarkable scalability and transfer capability possessed as well. The code is available at https://github.com/sunjin19126/Caterpillar.

Fei Kong, Jinhao Duan, RuiPeng Ma et al.

Recently, diffusion models have achieved remarkable success in generating tasks, including image and audio generation. However, like other generative models, diffusion models are prone to privacy issues. In this paper, we propose an efficient query-based membership inference attack (MIA), namely Proximal Initialization Attack (PIA), which utilizes groundtruth trajectory obtained by $ε$ initialized in $t=0$ and predicted point to infer memberships. Experimental results indicate that the proposed method can achieve competitive performance with only two queries on both discrete-time and continuous-time diffusion models. Moreover, previous works on the privacy of diffusion models have focused on vision tasks without considering audio tasks. Therefore, we also explore the robustness of diffusion models to MIA in the text-to-speech (TTS) task, which is an audio generation task. To the best of our knowledge, this work is the first to study the robustness of diffusion models to MIA in the TTS task. Experimental results indicate that models with mel-spectrogram (image-like) output are vulnerable to MIA, while models with audio output are relatively robust to MIA. {Code is available at \url{https://github.com/kong13661/PIA}}.

Shiqi Wang, Huan Zhang, Kaidi Xu et al.

Bound propagation based incomplete neural network verifiers such as CROWN are very efficient and can significantly accelerate branch-and-bound (BaB) based complete verification of neural networks. However, bound propagation cannot fully handle the neuron split constraints introduced by BaB commonly handled by expensive linear programming (LP) solvers, leading to loose bounds and hurting verification efficiency. In this work, we develop $β$-CROWN, a new bound propagation based method that can fully encode neuron splits via optimizable parameters $β$ constructed from either primal or dual space. When jointly optimized in intermediate layers, $β$-CROWN generally produces better bounds than typical LP verifiers with neuron split constraints, while being as efficient and parallelizable as CROWN on GPUs. Applied to complete robustness verification benchmarks, $β$-CROWN with BaB is up to three orders of magnitude faster than LP-based BaB methods, and is notably faster than all existing approaches while producing lower timeout rates. By terminating BaB early, our method can also be used for efficient incomplete verification. We consistently achieve higher verified accuracy in many settings compared to powerful incomplete verifiers, including those based on convex barrier breaking techniques. Compared to the typically tightest but very costly semidefinite programming (SDP) based incomplete verifiers, we obtain higher verified accuracy with three orders of magnitudes less verification time. Our algorithm empowered the $α,\!β$-CROWN (alpha-beta-CROWN) verifier, the winning tool in VNN-COMP 2021. Our code is available at http://PaperCode.cc/BetaCROWN

Kaidi Xu, Zhouxing Shi, Huan Zhang et al.

Linear relaxation based perturbation analysis (LiRPA) for neural networks, which computes provable linear bounds of output neurons given a certain amount of input perturbation, has become a core component in robustness verification and certified defense. The majority of LiRPA-based methods focus on simple feed-forward networks and need particular manual derivations and implementations when extended to other architectures. In this paper, we develop an automatic framework to enable perturbation analysis on any neural network structures, by generalizing existing LiRPA algorithms such as CROWN to operate on general computational graphs. The flexibility, differentiability and ease of use of our framework allow us to obtain state-of-the-art results on LiRPA based certified defense on fairly complicated networks like DenseNet, ResNeXt and Transformer that are not supported by prior works. Our framework also enables loss fusion, a technique that significantly reduces the computational complexity of LiRPA for certified defense. For the first time, we demonstrate LiRPA based certified defense on Tiny ImageNet and Downscaled ImageNet where previous approaches cannot scale to due to the relatively large number of classes. Our work also yields an open-source library for the community to apply LiRPA to areas beyond certified defense without much LiRPA expertise, e.g., we create a neural network with a probably flat optimization landscape by applying LiRPA to network parameters. Our opensource library is available at https://github.com/KaidiXu/auto_LiRPA.

Shaokai Ye, Kaidi Xu, Sijia Liu et al.

It is well known that deep neural networks (DNNs) are vulnerable to adversarial attacks, which are implemented by adding crafted perturbations onto benign examples. Min-max robust optimization based adversarial training can provide a notion of security against adversarial attacks. However, adversarial robustness requires a significantly larger capacity of the network than that for the natural training with only benign examples. This paper proposes a framework of concurrent adversarial training and weight pruning that enables model compression while still preserving the adversarial robustness and essentially tackles the dilemma of adversarial training. Furthermore, this work studies two hypotheses about weight pruning in the conventional setting and finds that weight pruning is essential for reducing the network model size in the adversarial setting, training a small model from scratch even with inherited initialization from the large model cannot achieve both adversarial robustness and high standard accuracy. Code is available at https://github.com/yeshaokai/Robustness-Aware-Pruning-ADMM.

Junyuan Hong, Jinhao Duan, Chenhui Zhang et al. · berkeley

Compressing high-capability Large Language Models (LLMs) has emerged as a favored strategy for resource-efficient inferences. While state-of-the-art (SoTA) compression methods boast impressive advancements in preserving benign task performance, the potential risks of compression in terms of safety and trustworthiness have been largely neglected. This study conducts the first, thorough evaluation of three (3) leading LLMs using five (5) SoTA compression techniques across eight (8) trustworthiness dimensions. Our experiments highlight the intricate interplay between compression and trustworthiness, revealing some interesting patterns. We find that quantization is currently a more effective approach than pruning in achieving efficiency and trustworthiness simultaneously. For instance, a 4-bit quantized model retains the trustworthiness of its original counterpart, but model pruning significantly degrades trustworthiness, even at 50% sparsity. Moreover, employing quantization within a moderate bit range could unexpectedly improve certain trustworthiness dimensions such as ethics and fairness. Conversely, extreme quantization to very low bit levels (3 bits) tends to reduce trustworthiness significantly. This increased risk cannot be uncovered by looking at benign performance alone, in turn, mandating comprehensive trustworthiness evaluation in practice. These findings culminate in practical recommendations for simultaneously achieving high utility, efficiency, and trustworthiness in LLMs. Code and models are available at https://decoding-comp-trust.github.io.

Zhiyuan Wang, Jinhao Duan, Chenxi Yuan et al.

Uncertainty estimation is crucial for the reliability of safety-critical human and artificial intelligence (AI) interaction systems, particularly in the domain of healthcare engineering. However, a robust and general uncertainty measure for free-form answers has not been well-established in open-ended medical question-answering (QA) tasks, where generative inequality introduces a large number of irrelevant words and sequences within the generated set for uncertainty quantification (UQ), which can lead to biases. This paper introduces Word-Sequence Entropy (WSE), a method that calibrates uncertainty at both the word and sequence levels, considering semantic relevance. WSE quantifies uncertainty in a way that is more closely aligned with the reliability of LLMs during uncertainty quantification (UQ). We compare WSE with six baseline methods on five free-form medical QA datasets, utilizing seven popular large language models (LLMs). Experimental results demonstrate that WSE exhibits superior performance in UQ under two standard criteria for correctness evaluation. Additionally, in terms of real-world medical QA applications, the performance of LLMs is significantly enhanced (e.g., a 6.36% improvement in model accuracy on the COVID-QA dataset) by employing responses with lower uncertainty that are identified by WSE as final answers, without any additional task-specific fine-tuning or architectural modifications.

Shrey Pandit, Jiawei Xu, Junyuan Hong et al.

Advancements in Large Language Models (LLMs) and their increasing use in medical question-answering necessitate rigorous evaluation of their reliability. A critical challenge lies in hallucination, where models generate plausible yet factually incorrect outputs. In the medical domain, this poses serious risks to patient safety and clinical decision-making. To address this, we introduce MedHallu, the first benchmark specifically designed for medical hallucination detection. MedHallu comprises 10,000 high-quality question-answer pairs derived from PubMedQA, with hallucinated answers systematically generated through a controlled pipeline. Our experiments show that state-of-the-art LLMs, including GPT-4o, Llama-3.1, and the medically fine-tuned UltraMedical, struggle with this binary hallucination detection task, with the best model achieving an F1 score as low as 0.625 for detecting "hard" category hallucinations. Using bidirectional entailment clustering, we show that harder-to-detect hallucinations are semantically closer to ground truth. Through experiments, we also show incorporating domain-specific knowledge and introducing a "not sure" category as one of the answer categories improves the precision and F1 scores by up to 38% relative to baselines.

Aref Azizpour, Tai D. Nguyen, Manil Shrestha et al.

As generative AI progresses rapidly, new synthetic image generators continue to emerge at a swift pace. Traditional detection methods face two main challenges in adapting to these generators: the forensic traces of synthetic images from new techniques can vastly differ from those learned during training, and access to data for these new generators is often limited. To address these issues, we introduce the Ensemble of Expert Embedders (E3), a novel continual learning framework for updating synthetic image detectors. E3 enables the accurate detection of images from newly emerged generators using minimal training data. Our approach does this by first employing transfer learning to develop a suite of expert embedders, each specializing in the forensic traces of a specific generator. Then, all embeddings are jointly analyzed by an Expert Knowledge Fusion Network to produce accurate and reliable detection decisions. Our experiments demonstrate that E3 outperforms existing continual learning methods, including those developed specifically for synthetic image detection.

Weixiang Sun, Yixin Liu, Zhiling Yan et al.

The rapid expansion of AI in healthcare has led to a surge in medical data generation and storage, boosting medical AI development. However, fears of unauthorized use, like training commercial AI models, hinder researchers from sharing their valuable datasets. To encourage data sharing, one promising solution is to introduce imperceptible noise into the data. This method aims to safeguard the data against unauthorized training by inducing degradation in the generalization ability of the trained model. However, they are not effective and efficient when applied to medical data, mainly due to the ignorance of the sparse nature of medical images. To address this problem, we propose the Sparsity-Aware Local Masking (SALM) method, a novel approach that selectively perturbs significant pixel regions rather than the entire image as previously. This simple yet effective approach, by focusing on local areas, significantly narrows down the search space for disturbances and fully leverages the characteristics of sparsity. Our extensive experiments across various datasets and model architectures demonstrate that SALM effectively prevents unauthorized training of different models and outperforms previous SoTA data protection methods.

Pingzhi Li, Morris Yu-Chao Huang, Zhen Tan et al.

Knowledge Distillation (KD) accelerates training of large language models (LLMs) but poses intellectual property protection and LLM diversity risks. Existing KD detection methods based on self-identity or output similarity can be easily evaded through prompt engineering. We present a KD detection framework effective in both white-box and black-box settings by exploiting an overlooked signal: the transfer of MoE "structural habits", especially internal routing patterns. Our approach analyzes how different experts specialize and collaborate across various inputs, creating distinctive fingerprints that persist through the distillation process. To extend beyond the white-box setup and MoE architectures, we further propose Shadow-MoE, a black-box method that constructs proxy MoE representations via auxiliary distillation to compare these patterns between arbitrary model pairs. We establish a comprehensive, reproducible benchmark that offers diverse distilled checkpoints and an extensible framework to facilitate future research. Extensive experiments demonstrate >94% detection accuracy across various scenarios and strong robustness to prompt-based evasion, outperforming existing baselines while highlighting the structural habits transfer in LLMs.

Jinhao Duan, Xinyu Zhao, Zhuoxuan Zhang et al.

Although Large Language Models (LLMs) succeed in human-guided conversations such as instruction following and question answering, the potential of LLM-guided conversations-where LLMs direct the discourse and steer the conversation's objectives-remains under-explored. In this study, we first characterize LLM-guided conversation into three fundamental components: (i) Goal Navigation; (ii) Context Management; (iii) Empathetic Engagement, and propose GuideLLM as an installation. We then implement an interviewing environment for the evaluation of LLM-guided conversation. Specifically, various topics are involved in this environment for comprehensive interviewing evaluation, resulting in around 1.4k turns of utterances, 184k tokens, and over 200 events mentioned during the interviewing for each chatbot evaluation. We compare GuideLLM with 6 state-of-the-art LLMs such as GPT-4o and Llama-3-70b-Instruct, from the perspective of interviewing quality, and autobiography generation quality. For automatic evaluation, we derive user proxies from multiple autobiographies and employ LLM-as-a-judge to score LLM behaviors. We further conduct a human-involved experiment by employing 45 human participants to chat with GuideLLM and baselines. We then collect human feedback, preferences, and ratings regarding the qualities of conversation and autobiography. Experimental results indicate that GuideLLM significantly outperforms baseline LLMs in automatic evaluation and achieves consistent leading performances in human ratings.

Xiaoyun Zhang, Zhengyue Zhao, Wenxuan Shi et al.

With the widespread application of Large Language Models (LLMs), it has become a significant concern to ensure their safety and prevent harmful responses. While current safe-alignment methods based on instruction fine-tuning and Reinforcement Learning from Human Feedback (RLHF) can effectively reduce harmful responses from LLMs, they often require high-quality datasets and heavy computational overhead during model training. Another way to align language models is to modify the logit of tokens in model outputs without heavy training. Recent studies have shown that contrastive decoding can enhance the performance of language models by reducing the likelihood of confused tokens. However, these methods require the manual selection of contrastive models or instruction templates, limiting the degree of contrast. To this end, we propose Adversarial Contrastive Decoding (ACD), an optimization-based framework to generate two opposite soft system prompts, the Safeguarding Prompt (SP) and the Adversarial Prompt (AP), for prompt-based contrastive decoding. The SP aims to promote safer outputs while the AP aims to exploit the harmful parts of the model, providing a strong contrast to align the model with safety. ACD only needs to apply a lightweight prompt tuning on a rather small anchor dataset without training the target model. Experiments conducted on extensive models and benchmarks demonstrate that the proposed method achieves much better safety performance than previous model training-free decoding methods without sacrificing its original generation ability.

Amirhosein Chahe, Chenan Wang, Abhishek Jeyapratap et al.

This paper introduces an attacking mechanism to challenge the resilience of autonomous driving systems. Specifically, we manipulate the decision-making processes of an autonomous vehicle by dynamically displaying adversarial patches on a screen mounted on another moving vehicle. These patches are optimized to deceive the object detection models into misclassifying targeted objects, e.g., traffic signs. Such manipulation has significant implications for critical multi-vehicle interactions such as intersection crossing and lane changing, which are vital for safe and efficient autonomous driving systems. Particularly, we make four major contributions. First, we introduce a novel adversarial attack approach where the patch is not co-located with its target, enabling more versatile and stealthy attacks. Moreover, our method utilizes dynamic patches displayed on a screen, allowing for adaptive changes and movement, enhancing the flexibility and performance of the attack. To do so, we design a Screen Image Transformation Network (SIT-Net), which simulates environmental effects on the displayed images, narrowing the gap between simulated and real-world scenarios. Further, we integrate a positional loss term into the adversarial training process to increase the success rate of the dynamic attack. Finally, we shift the focus from merely attacking perceptual systems to influencing the decision-making algorithms of self-driving systems. Our experiments demonstrate the first successful implementation of such dynamic adversarial attacks in real-world autonomous driving scenarios, paving the way for advancements in the field of robust and secure autonomous driving.

Husheng Han, Kaidi Xu, Xing Hu et al.

Adversarial patch attacks that craft the pixels in a confined region of the input images show their powerful attack effectiveness in physical environments even with noises or deformations. Existing certified defenses towards adversarial patch attacks work well on small images like MNIST and CIFAR-10 datasets, but achieve very poor certified accuracy on higher-resolution images like ImageNet. It is urgent to design both robust and effective defenses against such a practical and harmful attack in industry-level larger images. In this work, we propose the certified defense methodology that achieves high provable robustness for high-resolution images and largely improves the practicality for real adoption of the certified defense. The basic insight of our work is that the adversarial patch intends to leverage localized superficial important neurons (SIN) to manipulate the prediction results. Hence, we leverage the SIN-based DNN compression techniques to significantly improve the certified accuracy, by reducing the adversarial region searching overhead and filtering the prediction noises. Our experimental results show that the certified accuracy is increased from 36.3% (the state-of-the-art certified detection) to 60.4% on the ImageNet dataset, largely pushing the certified defenses for practical use.

Sheng Lin, Wei Jiang, Wei Wang et al.

Compressing Deep Neural Network (DNN) models to alleviate the storage and computation requirements is essential for practical applications, especially for resource limited devices. Although capable of reducing a reasonable amount of model parameters, previous unstructured or structured weight pruning methods can hardly truly accelerate inference, either due to the poor hardware compatibility of the unstructured sparsity or due to the low sparse rate of the structurally pruned network. Aiming at reducing both storage and computation, as well as preserving the original task performance, we propose a generalized weight unification framework at a hardware compatible micro-structured level to achieve high amount of compression and acceleration. Weight coefficients of a selected micro-structured block are unified to reduce the storage and computation of the block without changing the neuron connections, which turns to a micro-structured pruning special case when all unified coefficients are set to zero, where neuron connections (hence storage and computation) are completely removed. In addition, we developed an effective training framework based on the alternating direction method of multipliers (ADMM), which converts our complex constrained optimization into separately solvable subproblems. Through iteratively optimizing the subproblems, the desired micro-structure can be ensured with high compression ratio and low performance degradation. We extensively evaluated our method using a variety of benchmark models and datasets for different applications. Experimental results demonstrate state-of-the-art performance.

Hao Cheng, Kaidi Xu, Chenan Wang et al.

To tackle the susceptibility of deep neural networks to adversarial examples, the adversarial training has been proposed which provides a notion of security through an inner maximization problem presenting the first-order adversaries embedded within the outer minimization of the training loss. To generalize the adversarial robustness over different perturbation types, the adversarial training method has been augmented with the improved inner maximization presenting a union of multiple perturbations e.g., various $\ell_p$ norm-bounded perturbations. However, the improved inner maximization only enjoys limited flexibility in terms of the allowable perturbation types. In this work, through a gating mechanism, we assemble a set of expert networks, each one either adversarially trained to deal with a particular perturbation type or normally trained for boosting accuracy on clean data. The gating module assigns weights dynamically to each expert to achieve superior accuracy under various data types e.g., adversarial examples, adverse weather perturbations, and clean input. In order to deal with the obfuscated gradients issue, the training of the gating module is conducted together with fine-tuning of the last fully connected layers of expert networks through adversarial training approach. Using extensive experiments, we show that our Mixture of Robust Experts (MoRE) approach enables a flexible integration of a broad range of robust experts with superior performance.

Ren Wang, Kaidi Xu, Sijia Liu et al.

Model-agnostic meta-learning (MAML) has emerged as one of the most successful meta-learning techniques in few-shot learning. It enables us to learn a meta-initialization} of model parameters (that we call meta-model) to rapidly adapt to new tasks using a small amount of labeled training data. Despite the generalization power of the meta-model, it remains elusive that how adversarial robustness can be maintained by MAML in few-shot learning. In addition to generalization, robustness is also desired for a meta-model to defend adversarial examples (attacks). Toward promoting adversarial robustness in MAML, we first study WHEN a robustness-promoting regularization should be incorporated, given the fact that MAML adopts a bi-level (fine-tuning vs. meta-update) learning procedure. We show that robustifying the meta-update stage is sufficient to make robustness adapted to the task-specific fine-tuning stage even if the latter uses a standard training protocol. We also make additional justification on the acquired robustness adaptation by peering into the interpretability of neurons' activation maps. Furthermore, we investigate HOW robust regularization can efficiently be designed in MAML. We propose a general but easily-optimized robustness-regularized meta-learning framework, which allows the use of unlabeled data augmentation, fast adversarial attack generation, and computationally-light fine-tuning. In particular, we for the first time show that the auxiliary contrastive learning task can enhance the adversarial robustness of MAML. Finally, extensive experiments are conducted to demonstrate the effectiveness of our proposed methods in robust few-shot learning.

Pranay Sharma, Kaidi Xu, Sijia Liu et al.

In this work, we focus on the study of stochastic zeroth-order (ZO) optimization which does not require first-order gradient information and uses only function evaluations. The problem of ZO optimization has emerged in many recent machine learning applications, where the gradient of the objective function is either unavailable or difficult to compute. In such cases, we can approximate the full gradients or stochastic gradients through function value based gradient estimates. Here, we propose a novel hybrid gradient estimator (HGE), which takes advantage of the query-efficiency of random gradient estimates as well as the variance-reduction of coordinate-wise gradient estimates. We show that with a graceful design in coordinate importance sampling, the proposed HGE-based ZO optimization method is efficient both in terms of iteration complexity as well as function query cost. We provide a thorough theoretical analysis of the convergence of our proposed method for non-convex, convex, and strongly-convex optimization. We show that the convergence rate that we derive generalizes the results for some prominent existing methods in the nonconvex case, and matches the optimal result in the convex case. We also corroborate the theory with a real-world black-box attack generation application to demonstrate the empirical advantage of our method over state-of-the-art ZO optimization approaches.

Kaidi Xu, Huan Zhang, Shiqi Wang et al.

Formal verification of neural networks (NNs) is a challenging and important problem. Existing efficient complete solvers typically require the branch-and-bound (BaB) process, which splits the problem domain into sub-domains and solves each sub-domain using faster but weaker incomplete verifiers, such as Linear Programming (LP) on linearly relaxed sub-domains. In this paper, we propose to use the backward mode linear relaxation based perturbation analysis (LiRPA) to replace LP during the BaB process, which can be efficiently implemented on the typical machine learning accelerators such as GPUs and TPUs. However, unlike LP, LiRPA when applied naively can produce much weaker bounds and even cannot check certain conflicts of sub-domains during splitting, making the entire procedure incomplete after BaB. To address these challenges, we apply a fast gradient based bound tightening procedure combined with batch splits and the design of minimal usage of LP bound procedure, enabling us to effectively use LiRPA on the accelerator hardware for the challenging complete NN verification problem and significantly outperform LP-based approaches. On a single GPU, we demonstrate an order of magnitude speedup compared to existing LP-based approaches.

Hao Cheng, Kaidi Xu, Sijia Liu et al.

Although deep neural networks (DNNs) have achieved a great success in various computer vision tasks, it is recently found that they are vulnerable to adversarial attacks. In this paper, we focus on the so-called \textit{backdoor attack}, which injects a backdoor trigger to a small portion of training data (also known as data poisoning) such that the trained DNN induces misclassification while facing examples with this trigger. To be specific, we carefully study the effect of both real and synthetic backdoor attacks on the internal response of vanilla and backdoored DNNs through the lens of Gard-CAM. Moreover, we show that the backdoor attack induces a significant bias in neuron activation in terms of the $\ell_\infty$ norm of an activation map compared to its $\ell_1$ and $\ell_2$ norm. Spurred by our results, we propose the \textit{$\ell_\infty$-based neuron pruning} to remove the backdoor from the backdoored DNN. Experiments show that our method could effectively decrease the attack success rate, and also hold a high classification accuracy for clean images.

Kaidi Xu, Sijia Liu, Pin-Yu Chen et al.

Graph Neural Networks (GNNs) have made significant advances on several fundamental inference tasks. As a result, there is a surge of interest in using these models for making potentially important decisions in high-regret applications. However, despite GNNs' impressive performance, it has been observed that carefully crafted perturbations on graph structures (or nodes attributes) lead them to make wrong predictions. Presence of these adversarial examples raises serious security concerns. Most of the existing robust GNN design/training methods are only applicable to white-box settings where model parameters are known and gradient based methods can be used by performing convex relaxation of the discrete graph domain. More importantly, these methods are not efficient and scalable which make them infeasible in time sensitive tasks and massive graph datasets. To overcome these limitations, we propose a general framework which leverages the greedy search algorithms and zeroth-order methods to obtain robust GNNs in a generic and an efficient manner. On several applications, we show that the proposed techniques are significantly less computationally expensive and, in some cases, more robust than the state-of-the-art methods making them suitable to large-scale problems which were out of the reach of traditional robust training methods.

Shaokai Ye, Kailu Wu, Mu Zhou et al.

Existing domain adaptation methods aim at learning features that can be generalized among domains. These methods commonly require to update source classifier to adapt to the target domain and do not properly handle the trade off between the source domain and the target domain. In this work, instead of training a classifier to adapt to the target domain, we use a separable component called data calibrator to help the fixed source classifier recover discrimination power in the target domain, while preserving the source domain's performance. When the difference between two domains is small, the source classifier's representation is sufficient to perform well in the target domain and outperforms GAN-based methods in digits. Otherwise, the proposed method can leverage synthetic images generated by GANs to boost performance and achieve state-of-the-art performance in digits datasets and driving scene semantic segmentation. Our method empirically reveals that certain intriguing hints, which can be mitigated by adversarial attack to domain discriminators, are one of the sources for performance degradation under the domain shift.

Kaidi Xu, Gaoyuan Zhang, Sijia Liu et al.

It is known that deep neural networks (DNNs) are vulnerable to adversarial attacks. The so-called physical adversarial examples deceive DNN-based decisionmakers by attaching adversarial patches to real objects. However, most of the existing works on physical adversarial attacks focus on static objects such as glass frames, stop signs and images attached to cardboard. In this work, we proposed adversarial T-shirts, a robust physical adversarial example for evading person detectors even if it could undergo non-rigid deformation due to a moving person's pose changes. To the best of our knowledge, this is the first work that models the effect of deformation for designing physical adversarial examples with respect to-rigid objects such as T-shirts. We show that the proposed method achieves74% and 57% attack success rates in the digital and physical worlds respectively against YOLOv2. In contrast, the state-of-the-art physical attack method to fool a person detector only achieves 18% attack success rate. Furthermore, by leveraging min-max optimization, we extend our method to the ensemble attack setting against two object detectors YOLO-v2 and Faster R-CNN simultaneously.

Xiangyi Chen, Sijia Liu, Kaidi Xu et al.

The adaptive momentum method (AdaMM), which uses past gradients to update descent directions and learning rates simultaneously, has become one of the most popular first-order optimization methods for solving machine learning problems. However, AdaMM is not suited for solving black-box optimization problems, where explicit gradient forms are difficult or infeasible to obtain. In this paper, we propose a zeroth-order AdaMM (ZO-AdaMM) algorithm, that generalizes AdaMM to the gradient-free regime. We show that the convergence rate of ZO-AdaMM for both convex and nonconvex optimization is roughly a factor of $O(\sqrt{d})$ worse than that of the first-order AdaMM algorithm, where $d$ is problem size. In particular, we provide a deep understanding on why Mahalanobis distance matters in convergence of ZO-AdaMM and other AdaMM-type methods. As a byproduct, our analysis makes the first step toward understanding adaptive learning rate methods for nonconvex constrained optimization. Furthermore, we demonstrate two applications, designing per-image and universal adversarial attacks from black-box neural networks, respectively. We perform extensive experiments on ImageNet and empirically show that ZO-AdaMM converges much faster to a solution of high accuracy compared with $6$ state-of-the-art ZO optimization methods.

Sijia Liu, Songtao Lu, Xiangyi Chen et al.

In this paper, we study the problem of constrained robust (min-max) optimization ina black-box setting, where the desired optimizer cannot access the gradients of the objective function but may query its values. We present a principled optimization framework, integrating a zeroth-order (ZO) gradient estimator with an alternating projected stochastic gradient descent-ascent method, where the former only requires a small number of function queries and the later needs just one-step descent/ascent update. We show that the proposed framework, referred to as ZO-Min-Max, has a sub-linear convergence rate under mild conditions and scales gracefully with problem size. From an application side, we explore a promising connection between black-box min-max optimization and black-box evasion and poisoning attacks in adversarial machine learning (ML). Our empirical evaluations on these use cases demonstrate the effectiveness of our approach and its scalability to dimensions that prohibit using recent black-box solvers.

Caiwen Ding, Shuo Wang, Ning Liu et al.

Deep neural networks (DNNs), as the basis of object detection, will play a key role in the development of future autonomous systems with full autonomy. The autonomous systems have special requirements of real-time, energy-efficient implementations of DNNs on a power-constrained system. Two research thrusts are dedicated to performance and energy efficiency enhancement of the inference phase of DNNs. The first one is model compression techniques while the second is efficient hardware implementation. Recent works on extremely-low-bit CNNs such as the binary neural network (BNN) and XNOR-Net replace the traditional floating-point operations with binary bit operations which significantly reduces the memory bandwidth and storage requirement. However, it suffers from non-negligible accuracy loss and underutilized digital signal processing (DSP) blocks of FPGAs. To overcome these limitations, this paper proposes REQ-YOLO, a resource-aware, systematic weight quantization framework for object detection, considering both algorithm and hardware resource aspects in object detection. We adopt the block-circulant matrix method and propose a heterogeneous weight quantization using the Alternating Direction Method of Multipliers (ADMM), an effective optimization technique for general, non-convex optimization problems. To achieve real-time, highly-efficient implementations on FPGA, we present the detailed hardware implementation of block circulant matrices on CONV layers and develop an efficient processing element (PE) structure supporting the heterogeneous weight quantization, CONV dataflow and pipelining techniques, design optimization, and a template-based automatic synthesis framework to optimally exploit hardware resource. Experimental results show that our proposed REQ-YOLO framework can significantly compress the YOLO model while introducing very small accuracy degradation.

Pu Zhao, Sijia Liu, Pin-Yu Chen et al.

Robust machine learning is currently one of the most prominent topics which could potentially help shaping a future of advanced AI platforms that not only perform well in average cases but also in worst cases or adverse situations. Despite the long-term vision, however, existing studies on black-box adversarial attacks are still restricted to very specific settings of threat models (e.g., single distortion metric and restrictive assumption on target model's feedback to queries) and/or suffer from prohibitively high query complexity. To push for further advances in this field, we introduce a general framework based on an operator splitting method, the alternating direction method of multipliers (ADMM) to devise efficient, robust black-box attacks that work with various distortion metrics and feedback settings without incurring high query complexity. Due to the black-box nature of the threat model, the proposed ADMM solution framework is integrated with zeroth-order (ZO) optimization and Bayesian optimization (BO), and thus is applicable to the gradient-free regime. This results in two new black-box adversarial attack generation methods, ZO-ADMM and BO-ADMM. Our empirical evaluations on image classification datasets show that our proposed approaches have much lower function query complexities compared to state-of-the-art attack methods, but achieve very competitive attack success rates.