Haixu Tang

Chen Xiong, Zihao Wang, Rui Zhu et al.

Large Language Models (LLMs) rely on massive training datasets, often including proprietary data, which raises concerns about unauthorized usage and copyright infringement. Existing dataset inference methods typically require access to log probabilities or other internal signals, but many modern LLMs restrict such access, motivating token-only inference approaches. We propose CatShift, a token-only dataset inference framework based on catastrophic forgetting, where models overwrite prior knowledge when trained on new data. Fine-tuning an LLM on a subset of its training data induces larger output shifts than fine-tuning on unseen data. CatShift compares these shifts against those from a known non-member validation set to infer whether a dataset was included in training. Experiments on both open-source and API-based LLMs show that CatShift remains effective without logit access, enabling practical protection of proprietary datasets.

Xiaoyi Chen, Siyuan Tang, Rui Zhu et al.

The rapid advancements of large language models (LLMs) have raised public concerns about the privacy leakage of personally identifiable information (PII) within their extensive training datasets. Recent studies have demonstrated that an adversary could extract highly sensitive privacy data from the training data of LLMs with carefully designed prompts. However, these attacks suffer from the model's tendency to hallucinate and catastrophic forgetting (CF) in the pre-training stage, rendering the veracity of divulged PIIs negligible. In our research, we propose a novel attack, Janus, which exploits the fine-tuning interface to recover forgotten PIIs from the pre-training data in LLMs. We formalize the privacy leakage problem in LLMs and explain why forgotten PIIs can be recovered through empirical analysis on open-source language models. Based upon these insights, we evaluate the performance of Janus on both open-source language models and two latest LLMs, i.e., GPT-3.5-Turbo and LLaMA-2-7b. Our experiment results show that Janus amplifies the privacy risks by over 10 times in comparison with the baseline and significantly outperforms the state-of-the-art privacy extraction attacks including prefix attacks and in-context learning (ICL). Furthermore, our analysis validates that existing fine-tuning APIs provided by OpenAI and Azure AI Studio are susceptible to our Janus attack, allowing an adversary to conduct such an attack at a low cost.

Rui Zhu, Di Tang, Siyuan Tang et al.

Most existing methods to detect backdoored machine learning (ML) models take one of the two approaches: trigger inversion (aka. reverse engineer) and weight analysis (aka. model diagnosis). In particular, the gradient-based trigger inversion is considered to be among the most effective backdoor detection techniques, as evidenced by the TrojAI competition, Trojan Detection Challenge and backdoorBench. However, little has been done to understand why this technique works so well and, more importantly, whether it raises the bar to the backdoor attack. In this paper, we report the first attempt to answer this question by analyzing the change rate of the backdoored model around its trigger-carrying inputs. Our study shows that existing attacks tend to inject the backdoor characterized by a low change rate around trigger-carrying inputs, which are easy to capture by gradient-based trigger inversion. In the meantime, we found that the low change rate is not necessary for a backdoor attack to succeed: we design a new attack enhancement called \textit{Gradient Shaping} (GRASP), which follows the opposite direction of adversarial training to reduce the change rate of a backdoored model with regard to the trigger, without undermining its backdoor effect. Also, we provide a theoretic analysis to explain the effectiveness of this new technique and the fundamental weakness of gradient-based trigger inversion. Finally, we perform both theoretical and experimental analysis, showing that the GRASP enhancement does not reduce the effectiveness of the stealthy attacks against the backdoor detection methods based on weight analysis, as well as other backdoor mitigation methods without using detection.

Yuchu Liu, Rui Zhu, Jingwei Xiong et al.

Can large language models predict physical and mechanical polymer properties simply by reading unstructured scientific prose? Polymer performance is rarely determined by chemical structure alone; identical nominal polymers can exhibit drastically different behaviors depending on their synthesis route, processing history, morphology, and testing conditions. Yet, state-of-the-art polymer property models typically rely on structure-only representations -- such as SMILES or molecular graphs -- which strip away this vital experimental context. In this work, we introduce \textbf{PolyLM}, a natural-language-only, process- and condition-aware framework that predicts materials performance directly from full-text literature. By circumventing structural inputs entirely, PolyLM preserves the nuanced, unstructured descriptions of synthesis and processing reported by domain scientists. To train this framework, we curated an unprecedented, literature-scale dataset encompassing 185,000 scientific papers and over 276,400 unique polymer samples across 22 physical, mechanical, and thermal properties. We fine-tuned a massive 9-billion-parameter language model (Qwen3.5-9B) using Low-Rank Adaptation (LoRA) and task-level uncertainty weighting. Evaluated on 68,283 held-out observations, the model achieves remarkably high predictive accuracy, establishing new state-of-the-art benchmarks for complex properties. Across the 22 diverse targets, the model achieves a median $R^2$ of 0.74, with predictions for key thermal, mechanical, and physicochemical properties frequently surpassing an $R^2$ of 0.80. These results unequivocally demonstrate that natural language is a powerful, highly scalable interface for realistic materials performance prediction.

Tianhao Mao, Dongfang Zhao, Haixu Tang et al.

Large language models (LLMs) are rapidly transforming software engineering by enabling developers to generate code ranging from small snippets to entire projects. As AI-generated code becomes increasingly integrated into real-world systems, understanding its characteristics and impact is critical. However, prior work primarily focuses on small-scale, controlled evaluations and lacks comprehensive analysis in real-world settings. In this paper, we present a large-scale empirical study of AI-generated code in real-world repositories. We analyze both code-level metrics (\eg complexity, structure, and defect-related indicators) and commit-level characteristics (\eg commit size, frequency, and post-commit stability). To enable this study, we develop heuristic filter with LLM classification to identify AI-generated code and construct a large dataset. Our results provide new insights into how AI-generated code differs from human-written code and how AI assistance influences development practices. These findings contribute to a deeper understanding of the practical implications of AI-assisted programming.

Xiaoyi Chen, Haoyuan Wang, Siyuan Tang et al.

Large language models (LLMs) often memorize private information during training, raising serious privacy concerns. While machine unlearning has emerged as a promising solution, its true effectiveness against privacy attacks remains unclear. To address this, we propose PrivUn, a new evaluation framework that systematically assesses unlearning robustness through three-tier attack scenarios: direct retrieval, in-context learning recovery, and fine-tuning restoration; combined with quantitative analysis using forgetting scores, association metrics, and forgetting depth assessment. Our study exposes significant weaknesses in current unlearning methods, revealing two key findings: 1) unlearning exhibits gradient-driven ripple effects: unlike traditional forgetting which follows semantic relations (e.g., knowledge graphs), privacy unlearning propagates across latent gradient-based associations; and 2) most methods suffer from shallow forgetting, failing to remove private information distributed across multiple deep model layers. To validate these insights, we explore two strategies: association-aware core-set selection that leverages gradient similarity, and multi-layer deep intervention through representational constraints. These strategies represent a paradigm shift from shallow forgetting to deep forgetting.

Rui Zhu, Di Tang, Siyuan Tang et al.

In this paper, we present a simple yet surprisingly effective technique to induce "selective amnesia" on a backdoored model. Our approach, called SEAM, has been inspired by the problem of catastrophic forgetting (CF), a long standing issue in continual learning. Our idea is to retrain a given DNN model on randomly labeled clean data, to induce a CF on the model, leading to a sudden forget on both primary and backdoor tasks; then we recover the primary task by retraining the randomized model on correctly labeled clean data. We analyzed SEAM by modeling the unlearning process as continual learning and further approximating a DNN using Neural Tangent Kernel for measuring CF. Our analysis shows that our random-labeling approach actually maximizes the CF on an unknown backdoor in the absence of triggered inputs, and also preserves some feature extraction in the network to enable a fast revival of the primary task. We further evaluated SEAM on both image processing and Natural Language Processing tasks, under both data contamination and training manipulation attacks, over thousands of models either trained on popular image datasets or provided by the TrojAI competition. Our experiments show that SEAM vastly outperforms the state-of-the-art unlearning techniques, achieving a high Fidelity (measuring the gap between the accuracy of the primary task and that of the backdoor) within a few minutes (about 30 times faster than training a model from scratch using the MNIST dataset), with only a small amount of clean data (0.1% of training data for TrojAI models).

Di Tang, Rui Zhu, XiaoFeng Wang et al.

With extensive studies on backdoor attack and detection, still fundamental questions are left unanswered regarding the limits in the adversary's capability to attack and the defender's capability to detect. We believe that answers to these questions can be found through an in-depth understanding of the relations between the primary task that a benign model is supposed to accomplish and the backdoor task that a backdoored model actually performs. For this purpose, we leverage similarity metrics in multi-task learning to formally define the backdoor distance (similarity) between the primary task and the backdoor task, and analyze existing stealthy backdoor attacks, revealing that most of them fail to effectively reduce the backdoor distance and even for those that do, still much room is left to further improve their stealthiness. So we further design a new method, called TSA attack, to automatically generate a backdoor model under a given distance constraint, and demonstrate that our new attack indeed outperforms existing attacks, making a step closer to understanding the attacker's limits. Most importantly, we provide both theoretic results and experimental evidence on various datasets for the positive correlation between the backdoor distance and backdoor detectability, demonstrating that indeed our task similarity analysis help us better understand backdoor risks and has the potential to identify more effective mitigations.

Xiaotian Zhou, Qian Wang, Xiaofeng Wang et al.

Large language models (LLMs) have demonstrated human-level performance on a vast spectrum of natural language tasks. However, few studies have addressed the LLM threat and vulnerability from an ideology perspective, especially when they are increasingly being deployed in sensitive domains, e.g., elections and education. In this study, we explore the implications of GPT soft ideologization through the use of AI-self-consciousness. By utilizing GPT self-conversations, AI can be granted a vision to "comprehend" the intended ideology, and subsequently generate finetuning data for LLM ideology injection. When compared to traditional government ideology manipulation techniques, such as information censorship, LLM ideologization proves advantageous; it is easy to implement, cost-effective, and powerful, thus brimming with risks.

Chathura Widanage, Weijie Liu, Jiayu Li et al.

Trusted execution environments (TEE) such as Intel's Software Guard Extension (SGX) have been widely studied to boost security and privacy protection for the computation of sensitive data such as human genomics. However, a performance hurdle is often generated by SGX, especially from the small enclave memory. In this paper, we propose a new Hybrid Secured Flow framework (called "HySec-Flow") for large-scale genomic data analysis using SGX platforms. Here, the data-intensive computing tasks can be partitioned into independent subtasks to be deployed into distinct secured and non-secured containers, therefore allowing for parallel execution while alleviating the limited size of Page Cache (EPC) memory in each enclave. We illustrate our contributions using a workflow supporting indexing, alignment, dispatching, and merging the execution of SGX- enabled containers. We provide details regarding the architecture of the trusted and untrusted components and the underlying Scorn and Graphene support as generic shielding execution frameworks to port legacy code. We thoroughly evaluate the performance of our privacy-preserving reads mapping algorithm using real human genome sequencing data. The results demonstrate that the performance is enhanced by partitioning the time-consuming genomic computation into subtasks compared to the conventional execution of the data-intensive reads mapping algorithm in an enclave. The proposed HySec-Flow framework is made available as an open-source and adapted to the data-parallel computation of other large-scale genomic tasks requiring security and scalable computational resources.

Zihao Wang, Rui Zhu, Dongruo Zhou et al.

Recent developments have underscored the critical role of \textit{differential privacy} (DP) in safeguarding individual data for training machine learning models. However, integrating DP oftentimes incurs significant model performance degradation due to the perturbation introduced into the training process, presenting a formidable challenge in the {differentially private machine learning} (DPML) field. To this end, several mitigative efforts have been proposed, typically revolving around formulating new DPML algorithms or relaxing DP definitions to harmonize with distinct contexts. In spite of these initiatives, the diminishment induced by DP on models, particularly large-scale models, remains substantial and thus, necessitates an innovative solution that adeptly circumnavigates the consequential impairment of model utility. In response, we introduce DPAdapter, a pioneering technique designed to amplify the model performance of DPML algorithms by enhancing parameter robustness. The fundamental intuition behind this strategy is that models with robust parameters are inherently more resistant to the noise introduced by DP, thereby retaining better performance despite the perturbations. DPAdapter modifies and enhances the sharpness-aware minimization (SAM) technique, utilizing a two-batch strategy to provide a more accurate perturbation estimate and an efficient gradient descent, thereby improving parameter robustness against noise. Notably, DPAdapter can act as a plug-and-play component and be combined with existing DPML algorithms to further improve their performance. Our experiments show that DPAdapter vastly enhances state-of-the-art DPML algorithms, increasing average accuracy from 72.92\% to 77.09\% with a privacy budget of $ε=4$.

Weijie Liu, Hongbo Chen, XiaoFeng Wang et al.

As an emerging technique for confidential computing, trusted execution environment (TEE) receives a lot of attention. To better develop, deploy, and run secure applications on a TEE platform such as Intel's SGX, both academic and industrial teams have devoted much effort to developing reliable and convenient TEE containers. In this paper, we studied the isolation strategies of 15 existing TEE containers to protect secure applications from potentially malicious operating systems (OS) or untrusted applications, using a semi-automatic approach combining a feedback-guided analyzer with manual code review. Our analysis reveals the isolation protection each of these TEE containers enforces, and their security weaknesses. We observe that none of the existing TEE containers can fulfill the goal they set, due to various pitfalls in their design and implementation. We report the lessons learnt from our study for guiding the development of more secure containers, and further discuss the trend of TEE container designs. We also release our analyzer that helps evaluate the container middleware both from the enclave and from the kernel.

Weijie Liu, Wenhao Wang, Xiaofeng Wang et al.

A trusted execution environment (TEE) such as Intel Software Guard Extension (SGX) runs a remote attestation to prove to a data owner the integrity of the initial state of an enclave, including the program to operate on her data. For this purpose, the data-processing program is supposed to be open to the owner, so its functionality can be evaluated before trust can be established. However, increasingly there are application scenarios in which the program itself needs to be protected. So its compliance with privacy policies as expected by the data owner should be verified without exposing its code. To this end, this paper presents CAT, a new model for TEE-based confidential attestation. Our model is inspired by Proof-Carrying Code, where a code generator produces proof together with the code and a code consumer verifies the proof against the code on its compliance with security policies. Given that the conventional solutions do not work well under the resource-limited and TCB-frugal TEE, we propose a new design that allows an untrusted out-enclave generator to analyze the source code of a program when compiling it into binary and a trusted in-enclave consumer efficiently verifies the correctness of the instrumentation and the presence of other protection before running the binary. Our design strategically moves most of the workload to the code generator, which is responsible for producing well-formatted and easy-to-check code, while keeping the consumer simple. Also, the whole consumer can be made public and verified through a conventional attestation. We implemented this model on Intel SGX and demonstrate that it introduces a very small part of TCB. We also thoroughly evaluated its performance on micro- and macro- benchmarks and real-world applications, showing that the new design only incurs a small overhead when enforcing several categories of security policies.

Rui Zhu, Bo Lin, Haixu Tang

The number of linear regions is one of the distinct properties of the neural networks using piecewise linear activation functions such as ReLU, comparing with those conventional ones using other activation functions. Previous studies showed this property reflected the expressivity of a neural network family ([14]); as a result, it can be used to characterize how the structural complexity of a neural network model affects the function it aims to compute. Nonetheless, it is challenging to directly compute the number of linear regions; therefore, many researchers focus on estimating the bounds (in particular the upper bound) of the number of linear regions for deep neural networks using ReLU. These methods, however, attempted to estimate the upper bound in the entire input space. The theoretical methods are still lacking to estimate the number of linear regions within a specific area of the input space, e.g., a sphere centered at a training data point such as an adversarial example or a backdoor trigger. In this paper, we present the first method to estimate the upper bound of the number of linear regions in any sphere in the input space of a given ReLU neural network. We implemented the method, and computed the bounds in deep neural networks using the piece-wise linear active function. Our experiments showed that, while training a neural network, the boundaries of the linear regions tend to move away from the training data points. In addition, we observe that the spheres centered at the training data points tend to contain more linear regions than any arbitrary points in the input space. To the best of our knowledge, this is the first study of bounding linear regions around a specific data point. We consider our work as a first step toward the investigation of the structural complexity of deep neural networks in a specific input area.

Tongxin Wang, Zhengming Ding, Wei Shao et al.

Domain Adaptation (DA) targets at adapting a model trained over the well-labeled source domain to the unlabeled target domain lying in different distributions. Existing DA normally assumes the well-labeled source domain is class-wise balanced, which means the size per source class is relatively similar. However, in real-world applications, labeled samples for some categories in the source domain could be extremely few due to the difficulty of data collection and annotation, which leads to decreasing performance over target domain on those few-shot categories. To perform fair cross-domain adaptation and boost the performance on these minority categories, we develop a novel Generative Few-shot Cross-domain Adaptation (GFCA) algorithm for fair cross-domain classification. Specifically, generative feature augmentation is explored to synthesize effective training data for few-shot source classes, while effective cross-domain alignment aims to adapt knowledge from source to facilitate the target learning. Experimental results on two large cross-domain visual datasets demonstrate the effectiveness of our proposed method on improving both few-shot and overall classification accuracy comparing with the state-of-the-art DA approaches.

Di Tang, XiaoFeng Wang, Haixu Tang et al.

A security threat to deep neural networks (DNN) is backdoor contamination, in which an adversary poisons the training data of a target model to inject a Trojan so that images carrying a specific trigger will always be classified into a specific label. Prior research on this problem assumes the dominance of the trigger in an image's representation, which causes any image with the trigger to be recognized as a member in the target class. Such a trigger also exhibits unique features in the representation space and can therefore be easily separated from legitimate images. Our research, however, shows that simple target contamination can cause the representation of an attack image to be less distinguishable from that of legitimate ones, thereby evading existing defenses against the backdoor infection. In our research, we show that such a contamination attack actually subtly changes the representation distribution for the target class, which can be captured by a statistic analysis. More specifically, we leverage an EM algorithm to decompose an image into its identity part (e.g., person, traffic sign) and variation part within a class (e.g., lighting, poses). Then we analyze the distribution in each class, identifying those more likely to be characterized by a mixture model resulted from adding attack samples to the legitimate image pool. Our research shows that this new technique effectively detects data contamination attacks, including the new one we propose, and is also robust against the evasion attempts made by a knowledgeable adversary.

Wenhao Wang, Yichen Jiang, Qintao Shen et al.

It has been a long standing problem to securely outsource computation tasks to an untrusted party with integrity and confidentiality guarantees. While fully homomorphic encryption (FHE) is a promising technique that allows computations performed on the encrypted data, it suffers from a significant slow down to the computation. In this paper we propose a hybrid solution that uses the latest hardware Trusted Execution Environments (TEEs) to assist FHE by moving the bootstrapping step, which is one of the major obstacles in designing practical FHE schemes, to a secured SGX enclave. TEEFHE, the hybrid system we designed, makes it possible for homomorphic computations to be performed on smaller ciphertext and secret key, providing better performance and lower memory consumption. We make an effort to mitigate side channel leakages within SGX by making the memory access patterns totally independent from the secret information. The evaluation shows that TEEFHE effectively improves the software only FHE schemes in terms of both time and space.

Yunhui Long, Vincent Bindschaedler, Lei Wang et al.

Membership Inference Attack (MIA) determines the presence of a record in a machine learning model's training data by querying the model. Prior work has shown that the attack is feasible when the model is overfitted to its training data or when the adversary controls the training algorithm. However, when the model is not overfitted and the adversary does not control the training algorithm, the threat is not well understood. In this paper, we report a study that discovers overfitting to be a sufficient but not a necessary condition for an MIA to succeed. More specifically, we demonstrate that even a well-generalized model contains vulnerable instances subject to a new generalized MIA (GMIA). In GMIA, we use novel techniques for selecting vulnerable instances and detecting their subtle influences ignored by overfitting metrics. Specifically, we successfully identify individual records with high precision in real-world datasets by querying black-box machine learning models. Further we show that a vulnerable record can even be indirectly attacked by querying other related records and existing generalization techniques are found to be less effective in protecting the vulnerable instances. Our findings sharpen the understanding of the fundamental cause of the problem: the unique influences the training instance may have on the model.

Wenhao Wang, Guoxing Chen, Xiaorui Pan et al.

Side-channel risks of Intel's SGX have recently attracted great attention. Under the spotlight is the newly discovered page-fault attack, in which an OS-level adversary induces page faults to observe the page-level access patterns of a protected process running in an SGX enclave. With almost all proposed defense focusing on this attack, little is known about whether such efforts indeed raise the bar for the adversary, whether a simple variation of the attack renders all protection ineffective, not to mention an in-depth understanding of other attack surfaces in the SGX system. In the paper, we report the first step toward systematic analyses of side-channel threats that SGX faces, focusing on the risks associated with its memory management. Our research identifies 8 potential attack vectors, ranging from TLB to DRAM modules. More importantly, we highlight the common misunderstandings about SGX memory side channels, demonstrating that high frequent AEXs can be avoided when recovering EdDSA secret key through a new page channel and fine-grained monitoring of enclave programs (at the level of 64B) can be done through combining both cache and cross-enclave DRAM channels. Our findings reveal the gap between the ongoing security research on SGX and its side-channel weaknesses, redefine the side-channel threat model for secure enclaves, and can provoke a discussion on when to use such a system and how to use it securely.