Juan Zhai

Zhenting Wang, Juan Zhai, Shiqing Ma

Deep neural networks are vulnerable to Trojan attacks. Existing attacks use visible patterns (e.g., a patch or image transformations) as triggers, which are vulnerable to human inspection. In this paper, we propose stealthy and efficient Trojan attacks, BppAttack. Based on existing biology literature on human visual systems, we propose to use image quantization and dithering as the Trojan trigger, making imperceptible changes. It is a stealthy and efficient attack without training auxiliary models. Due to the small changes made to images, it is hard to inject such triggers during training. To alleviate this problem, we propose a contrastive learning based approach that leverages adversarial attacks to generate negative sample pairs so that the learned trigger is precise and accurate. The proposed method achieves high attack success rates on four benchmark datasets, including MNIST, CIFAR-10, GTSRB, and CelebA. It also effectively bypasses existing Trojan defenses and human inspection. Our code can be found in https://github.com/RU-System-Software-and-Security/BppAttack.

Zhenting Wang, Kai Mei, Juan Zhai et al.

The backdoor attack, where the adversary uses inputs stamped with triggers (e.g., a patch) to activate pre-planted malicious behaviors, is a severe threat to Deep Neural Network (DNN) models. Trigger inversion is an effective way of identifying backdoor models and understanding embedded adversarial behaviors. A challenge of trigger inversion is that there are many ways of constructing the trigger. Existing methods cannot generalize to various types of triggers by making certain assumptions or attack-specific constraints. The fundamental reason is that existing work does not consider the trigger's design space in their formulation of the inversion problem. This work formally defines and analyzes the triggers injected in different spaces and the inversion problem. Then, it proposes a unified framework to invert backdoor triggers based on the formalization of triggers and the identified inner behaviors of backdoor models from our analysis. Our prototype UNICORN is general and effective in inverting backdoor triggers in DNNs. The code can be found at https://github.com/RU-System-Software-and-Security/UNICORN.

Zhenting Wang, Kai Mei, Hailun Ding et al.

Deep Neural Networks are vulnerable to Trojan (or backdoor) attacks. Reverse-engineering methods can reconstruct the trigger and thus identify affected models. Existing reverse-engineering methods only consider input space constraints, e.g., trigger size in the input space. Expressly, they assume the triggers are static patterns in the input space and fail to detect models with feature space triggers such as image style transformations. We observe that both input-space and feature-space Trojans are associated with feature space hyperplanes. Based on this observation, we design a novel reverse-engineering method that exploits the feature space constraint to reverse-engineer Trojan triggers. Results on four datasets and seven different attacks demonstrate that our solution effectively defends both input-space and feature-space Trojans. It outperforms state-of-the-art reverse-engineering methods and other types of defenses in both Trojaned model detection and mitigation tasks. On average, the detection accuracy of our method is 93\%. For Trojan mitigation, our method can reduce the ASR (attack success rate) to only 0.26\% with the BA (benign accuracy) remaining nearly unchanged. Our code can be found at https://github.com/RU-System-Software-and-Security/FeatureRE.

Xuanqi Gao, Juan Zhai, Shiqing Ma et al.

With Deep Neural Network (DNN) being integrated into a growing number of critical systems with far-reaching impacts on society, there are increasing concerns on their ethical performance, such as fairness. Unfortunately, model fairness and accuracy in many cases are contradictory goals to optimize. To solve this issue, there has been a number of work trying to improve model fairness by using an adversarial game in model level. This approach introduces an adversary that evaluates the fairness of a model besides its prediction accuracy on the main task, and performs joint-optimization to achieve a balanced result. In this paper, we noticed that when performing backward propagation based training, such contradictory phenomenon has shown on individual neuron level. Based on this observation, we propose FairNeuron, a DNN model automatic repairing tool, to mitigate fairness concerns and balance the accuracy-fairness trade-off without introducing another model. It works on detecting neurons with contradictory optimization directions from accuracy and fairness training goals, and achieving a trade-off by selective dropout. Comparing with state-of-the-art methods, our approach is lightweight, making it scalable and more efficient. Our evaluation on 3 datasets shows that FairNeuron can effectively improve all models' fairness while maintaining a stable utility.

Weipeng Jiang, Zhenting Wang, Juan Zhai et al.

Despite prior safety alignment efforts, mainstream LLMs can still generate harmful and unethical content when subjected to jailbreaking attacks. Existing jailbreaking methods fall into two main categories: template-based and optimization-based methods. The former requires significant manual effort and domain knowledge, while the latter, exemplified by Greedy Coordinate Gradient (GCG), which seeks to maximize the likelihood of harmful LLM outputs through token-level optimization, also encounters several limitations: requiring white-box access, necessitating pre-constructed affirmative phrase, and suffering from low efficiency. In this paper, we present ECLIPSE, a novel and efficient black-box jailbreaking method utilizing optimizable suffixes. Drawing inspiration from LLMs' powerful generation and optimization capabilities, we employ task prompts to translate jailbreaking goals into natural language instructions. This guides the LLM to generate adversarial suffixes for malicious queries. In particular, a harmfulness scorer provides continuous feedback, enabling LLM self-reflection and iterative optimization to autonomously and efficiently produce effective suffixes. Experimental results demonstrate that ECLIPSE achieves an average attack success rate (ASR) of 0.92 across three open-source LLMs and GPT-3.5-Turbo, significantly surpassing GCG in 2.4 times. Moreover, ECLIPSE is on par with template-based methods in ASR while offering superior attack efficiency, reducing the average attack overhead by 83%.

Xuanqi Gao, Weipeng Jiang, Juan Zhai et al.

With the emergence of the Software 3.0 era, there is a growing trend of compressing and integrating large models into software systems, with significant societal implications. Regrettably, in numerous instances, model compression techniques impact the fairness performance of these models and thus the ethical behavior of DNN-powered software. One of the most notable example is the Lottery Ticket Hypothesis (LTH), a prevailing model pruning approach. This paper demonstrates that fairness issue of LTHbased pruning arises from both its subnetwork selection and training procedures, highlighting the inadequacy of existing remedies. To address this, we propose a novel pruning framework, Ballot, which employs a novel conflict-detection-based subnetwork selection to find accurate and fair subnetworks, coupled with a refined training process to attain a high-performance model, thereby improving the fairness of DNN-powered software. By means of this procedure, Ballot improves the fairness of pruning by 38.00%, 33.91%, 17.96%, and 35.82% compared to state-of-the-art baselines, namely Magnitude Pruning, Standard LTH, SafeCompress, and FairScratch respectively, based on our evaluation of five popular datasets and three widely used models. Our code is available at https://anonymous.4open.science/r/Ballot-506E.

Zhenting Wang, Zhizhi Wang, Mingyu Jin et al.

Backdoor attack is a severe threat to the trustworthiness of DNN-based language models. In this paper, we first extend the definition of memorization of language models from sample-wise to more fine-grained sentence element-wise (e.g., word, phrase, structure, and style), and then point out that language model backdoors are a type of element-wise memorization. Through further analysis, we find that the strength of such memorization is positively correlated to the frequency of duplicated elements in the training dataset. In conclusion, duplicated sentence elements are necessary for successful backdoor attacks. Based on this, we propose a data-centric defense. We first detect trigger candidates in training data by finding memorizable elements, i.e., duplicated elements, and then confirm real triggers by testing if the candidates can activate backdoor behaviors (i.e., malicious elements). Results show that our method outperforms state-of-the-art defenses in defending against different types of NLP backdoors.

Xuanqi Gao, Juan Zhai, Shiqing Ma et al.

Due to the model aging problem, Deep Neural Networks (DNNs) need updates to adjust them to new data distributions. The common practice leverages incremental learning (IL), e.g., Class-based Incremental Learning (CIL) that updates output labels, to update the model with new data and a limited number of old data. This avoids heavyweight training (from scratch) using conventional methods and saves storage space by reducing the number of old data to store. But it also leads to poor performance in fairness. In this paper, we show that CIL suffers both dataset and algorithm bias problems, and existing solutions can only partially solve the problem. We propose a novel framework, CILIATE, that fixes both dataset and algorithm bias in CIL. It features a novel differential analysis guided dataset and training refinement process that identifies unique and important samples overlooked by existing CIL and enforces the model to learn from them. Through this process, CILIATE improves the fairness of CIL by 17.03%, 22.46%, and 31.79% compared to state-of-the-art methods, iCaRL, BiC, and WA, respectively, based on our evaluation on three popular datasets and widely used ResNet models.

Mingzhe Li, Renhao Zhang, Zhiyang Wen et al.

Text-to-image (T2I) generative models such as Stable Diffusion and FLUX can synthesize realistic, high-quality images directly from textual prompts. The resulting image quality depends critically on well-crafted prompts that specify both subjects and stylistic modifiers, which have become valuable digital assets. However, the rising value and ubiquity of high-quality prompts expose them to security and intellectual-property risks. One key threat is the prompt stealing attack, i.e., the task of recovering the textual prompt that generated a given image. Prompt stealing enables unauthorized extraction and reuse of carefully engineered prompts, yet it can also support beneficial applications such as data attribution, model provenance analysis, and watermarking validation. Existing approaches often assume white-box gradient access, require large-scale labeled datasets for supervised training, or rely solely on captioning without explicit optimization, limiting their practicality and adaptability. To address these challenges, we propose PROMPTMINER, a black-box prompt stealing framework that decouples the task into two phases: (1) a reinforcement learning-based optimization phase to reconstruct the primary subject, and (2) a fuzzing-driven search phase to recover stylistic modifiers. Experiments across multiple datasets and diffusion backbones demonstrate that PROMPTMINER achieves superior results, with CLIP similarity up to 0.958 and textual alignment with SBERT up to 0.751, surpassing all baselines. Even when applied to in-the-wild images with unknown generators, it outperforms the strongest baseline by 7.5 percent in CLIP similarity, demonstrating better generalization. Finally, PROMPTMINER maintains strong performance under defensive perturbations, highlighting remarkable robustness. Code: https://github.com/aaFrostnova/PromptMiner

Gehao Zhang, Eugene Bagdasarian, Juan Zhai et al.

Distinguishing AI-generated code from human-written code is becoming crucial for tasks such as authorship attribution, content tracking, and misuse detection. Based on this, N-gram-based watermarking schemes have emerged as prominent, which inject secret watermarks to be detected during the generation. However, their robustness in code content remains insufficiently evaluated. Most claims rely solely on defenses against simple code transformations or code optimizations as a simulation of attack, creating a questionable sense of robustness. In contrast, more sophisticated schemes already exist in the software engineering world, e.g., code obfuscation, which significantly alters code while preserving functionality. Although obfuscation is commonly used to protect intellectual property or evade software scanners, the robustness of code watermarking techniques against such transformations remains largely unexplored. In this work, we formally model the code obfuscation and prove the impossibility of N-gram-based watermarking's robustness with only one intuitive and experimentally verified assumption, distribution consistency, satisfied. Given the original false positive rate of the watermarking detection, the ratio that the detector failed on the watermarked code after obfuscation will increase to 1 - fpr. The experiments have been performed on three SOTA watermarking schemes, two LLMs, two programming languages, four code benchmarks, and four obfuscators. Among them, all watermarking detectors show coin-flipping detection abilities on obfuscated codes (AUROC tightly surrounds 0.5). Among all models, watermarking schemes, and datasets, both programming languages own obfuscators that can achieve attack effects with no detection AUROC higher than 0.6 after the attack. Based on the theoretical and practical observations, we also proposed a potential path of robust code watermarking.

Yuan Xiao, Shiqing Ma, Juan Zhai et al.

The robustness of convolutional neural networks (CNNs) is vital to modern AI-driven systems. It can be quantified by formal verification by providing a certified lower bound, within which any perturbation does not alter the original input's classification result. It is challenging due to nonlinear components, such as MaxPool. At present, many verification methods are sound but risk losing some precision to enhance efficiency and scalability, and thus, a certified lower bound is a crucial criterion for evaluating the performance of verification tools. In this paper, we present MaxLin, a robustness verifier for MaxPool-based CNNs with tight linear approximation. By tightening the linear approximation of the MaxPool function, we can certify larger certified lower bounds of CNNs. We evaluate MaxLin with open-sourced benchmarks, including LeNet and networks trained on the MNIST, CIFAR-10, and Tiny ImageNet datasets. The results show that MaxLin outperforms state-of-the-art tools with up to 110.60% improvement regarding the certified lower bound and 5.13 $\times$ speedup for the same neural networks. Our code is available at https://github.com/xiaoyuanpigo/maxlin.

Zhenting Wang, Hailun Ding, Juan Zhai et al.

The backdoor or Trojan attack is a severe threat to deep neural networks (DNNs). Researchers find that DNNs trained on benign data and settings can also learn backdoor behaviors, which is known as the natural backdoor. Existing works on anti-backdoor learning are based on weak observations that the backdoor and benign behaviors can differentiate during training. An adaptive attack with slow poisoning can bypass such defenses. Moreover, these methods cannot defend natural backdoors. We found the fundamental differences between backdoor-related neurons and benign neurons: backdoor-related neurons form a hyperplane as the classification surface across input domains of all affected labels. By further analyzing the training process and model architectures, we found that piece-wise linear functions cause this hyperplane surface. In this paper, we design a novel training method that forces the training to avoid generating such hyperplanes and thus remove the injected backdoors. Our extensive experiments on five datasets against five state-of-the-art attacks and also benign training show that our method can outperform existing state-of-the-art defenses. On average, the ASR (attack success rate) of the models trained with NONE is 54.83 times lower than undefended models under standard poisoning backdoor attack and 1.75 times lower under the natural backdoor attack. Our code is available at https://github.com/RU-System-Software-and-Security/NONE.

Quanjun Zhang, Juan Zhai, Chunrong Fang et al.

Machine translation systems have been widely adopted in our daily life, making life easier and more convenient. Unfortunately, erroneous translations may result in severe consequences, such as financial losses. This requires to improve the accuracy and the reliability of machine translation systems. However, it is challenging to test machine translation systems because of the complexity and intractability of the underlying neural models. To tackle these challenges, we propose a novel metamorphic testing approach by syntactic tree pruning (STP) to validate machine translation systems. Our key insight is that a pruned sentence should have similar crucial semantics compared with the original sentence. Specifically, STP (1) proposes a core semantics-preserving pruning strategy by basic sentence structure and dependency relations on the level of syntactic tree representation; (2) generates source sentence pairs based on the metamorphic relation; (3) reports suspicious issues whose translations break the consistency property by a bag-of-words model. We further evaluate STP on two state-of-the-art machine translation systems (i.e., Google Translate and Bing Microsoft Translator) with 1,200 source sentences as inputs. The results show that STP can accurately find 5,073 unique erroneous translations in Google Translate and 5,100 unique erroneous translations in Bing Microsoft Translator (400% more than state-of-the-art techniques), with 64.5% and 65.4% precision, respectively. The reported erroneous translations vary in types and more than 90% of them cannot be found by state-of-the-art techniques. There are 9,393 erroneous translations unique to STP, which is 711.9% more than state-of-the-art techniques. Moreover, STP is quite effective to detect translation errors for the original sentences with a recall reaching 74.0%, improving state-of-the-art techniques by 55.1% on average.

Xiaoyu Zhang, Juan Zhai, Shiqing Ma et al.

Large Language Models (LLMs) have emerged as the new recommendation engines, surpassing traditional methods in both capability and scope, particularly in code generation. In this paper, we reveal a novel provider bias in LLMs: without explicit directives, these models show systematic preferences for services from specific providers in their recommendations (e.g., favoring Google Cloud over Microsoft Azure). To systematically investigate this bias, we develop an automated pipeline to construct the dataset, incorporating 6 distinct coding task categories and 30 real-world application scenarios. Leveraging this dataset, we conduct the first comprehensive empirical study of provider bias in LLM code generation across seven state-of-the-art LLMs, utilizing approximately 500 million tokens (equivalent to $5,000+ in computational costs). Our findings reveal that LLMs exhibit significant provider preferences, predominantly favoring services from Google and Amazon, and can autonomously modify input code to incorporate their preferred providers without users' requests. Such a bias holds far-reaching implications for market dynamics and societal equilibrium, potentially contributing to digital monopolies. It may also deceive users and violate their expectations, leading to various consequences. We call on the academic community to recognize this emerging issue and develop effective evaluation and mitigation methods to uphold AI security and fairness.

Xiaoyu Zhang, Juan Zhai, Shiqing Ma et al.

Deep Learning models have become an integrated component of modern software systems. In response to the challenge of model design, researchers proposed Automated Machine Learning (AutoML) systems, which automatically search for model architecture and hyperparameters for a given task. Like other software systems, existing AutoML systems suffer from bugs. We identify two common and severe bugs in AutoML, performance bug (i.e., searching for the desired model takes an unreasonably long time) and ineffective search bug (i.e., AutoML systems are not able to find an accurate enough model). After analyzing the workflow of AutoML, we observe that existing AutoML systems overlook potential opportunities in search space, search method, and search feedback, which results in performance and ineffective search bugs. Based on our analysis, we design and implement DREAM, an automatic debugging and repairing system for AutoML systems. It monitors the process of AutoML to collect detailed feedback and automatically repairs bugs by expanding search space and leveraging a feedback-driven search strategy. Our evaluation results show that DREAM can effectively and efficiently repair AutoML bugs.

Weipeng Jiang, Juan Zhai, Shiqing Ma et al.

In recent years, Large Language Models (LLMs) have faced increasing demands to selectively remove sensitive information, protect privacy, and comply with copyright regulations through unlearning, by Machine Unlearning. While evaluating unlearning effectiveness is crucial, existing benchmarks are limited in scale and comprehensiveness, typically containing only a few hundred test cases. We identify two critical challenges in generating holistic audit datasets: ensuring audit adequacy and handling knowledge redundancy between forget and retain dataset. To address these challenges, we propose HANKER, an automated framework for holistic audit dataset generation leveraging knowledge graphs to achieve fine-grained coverage and eliminate redundant knowledge. Applying HANKER to the popular MUSE benchmark, we successfully generated over 69,000 and 111,000 audit cases for the News and Books datasets respectively, identifying thousands of knowledge memorization instances that the previous benchmark failed to detect. Our empirical analysis uncovers how knowledge redundancy significantly skews unlearning effectiveness metrics, with redundant instances artificially inflating the observed memorization measurements ROUGE from 19.7% to 26.1% and Entailment Scores from 32.4% to 35.2%, highlighting the necessity of systematic deduplication for accurate assessment.

Xuanqi Gao, Weipeng Jiang, Juan Zhai et al.

The advent of neural machine translation (NMT) has revolutionized cross-lingual communication, yet preserving stylistic nuances remains a significant challenge. While existing approaches often require parallel corpora for style preservation, we introduce Babel, a novel framework that enhances stylistic fidelity in NMT using only monolingual corpora. Babel employs two key components: (1) a style detector based on contextual embeddings that identifies stylistic disparities between source and target texts, and (2) a diffusion-based style applicator that rectifies stylistic inconsistencies while maintaining semantic integrity. Our framework integrates with existing NMT systems as a post-processing module, enabling style-aware translation without requiring architectural modifications or parallel stylistic data. Extensive experiments on five diverse domains (law, literature, scientific writing, medicine, and educational content) demonstrate Babel's effectiveness: it identifies stylistic inconsistencies with 88.21% precision and improves stylistic preservation by 150% while maintaining a high semantic similarity score of 0.92. Human evaluation confirms that translations refined by Babel better preserve source text style while maintaining fluency and adequacy.

Mingzhe Li, Gehao Zhang, Zhenting Wang et al.

Text-to-image generation models~(e.g., Stable Diffusion) have achieved significant advancements, enabling the creation of high-quality and realistic images based on textual descriptions. Prompt inversion, the task of identifying the textual prompt used to generate a specific artifact, holds significant potential for applications including data attribution, model provenance, and watermarking validation. Recent studies introduced a delayed projection scheme to optimize for prompts representative of the vocabulary space, though challenges in semantic fluency and efficiency remain. Advanced image captioning models or visual large language models can generate highly interpretable prompts, but they often lack in image similarity. In this paper, we propose a prompt inversion technique called \sys for text-to-image diffusion models, which includes initializing embeddings using a pre-trained image captioning model, refining them through reverse-engineering in the latent space, and converting them to texts using an embedding-to-text model. Our experiments on the widely-used datasets, such as MS COCO, LAION, and Flickr, show that our method outperforms existing methods in terms of image similarity, textual alignment, prompt interpretability and generalizability. We further illustrate the application of our generated prompts in tasks such as cross-concept image synthesis, concept manipulation, evolutionary multi-concept generation and unsupervised segmentation.