arXiv subjects

Zhengyuan Jiang

Publications and source records attributed to Zhengyuan Jiang.

At least 19 recordsLinked to original sources

arXiv2026

Package Hallucination Attacks on Coding Agents through Prompt Injection in Rule Files

Modern agentic coding frameworks increasingly rely on community-shared rule files (e.g., AGENTS.md or .cursorrules) to guide autonomous code generation, yet the security risks of this pipeline remain underexplored. To bridge this gap, we introduce the package hallucination attack, where an attacker injects malicious prompts into benign rule files to induce coding agents to replace legitimate dependencies with attacker-controlled packages. To obtain effective malicious prompts injected into rule files, we propose PackHallu, an evolutionary optimization framework that iteratively rewrites these injected prompts using trajectory-level feedback and LLM-guided mutations. Evaluations across multiple benchmarks, LLMs, and agent frameworks show that PackHallu achieves high attack success rates and strong transferability across diverse models and agent combinations. Our findings demonstrate that coding agents are vulnerable to package hallucination attacks, highlighting the urgent need for stronger security safeguards in autonomous coding systems.

cs.CR↗

arXiv2026

Self-Evolving Coding Rules for AI Coding Agents

The performance of AI coding agents is highly dependent on their underlying coding rules. However, existing coding rules are typically hand-crafted and fixed, making the process labor-intensive and often suboptimal. In this work, we propose RuleEvolve, a self-evolving framework for coding rules. RuleEvolve maintains a pool of candidate coding rules and iteratively improves them. In each iteration, it employs an LLM-powered mutator module to generate variants from existing candidates, and then uses a judge module to evaluate these variants and update the pool with the best-performing ones. Extensive evaluations across two coding-agent frameworks, four backbone LLMs, and three benchmarks demonstrate that RuleEvolve outperforms both manual engineering and existing prompt optimization baselines in terms of functional correctness of the generated code, code length, and/or generation cost (e.g., tokens used).

cs.CL↗

arXiv2026

Divide and Doubt: Diverse Distributed Poisoning for Retrieval-Augmented Generation

Multi-passage corpus poisoning often repeats one target claim across similar documents, creating correlated lexical and semantic patterns that similarity- and conflict-aware defenses can suppress jointly. We introduce DnD (Divide and Doubt), a targeted attack based on two principles: distributing support for the target answer across stylistically diverse passages, and including a passage that casts doubt on evidence for the reference answer. The first disperses poison-passage representations in embedding space, while the second strengthens target adoption when multiple poisoned passages are retrieved. We evaluate DnD on two open-domain QA datasets across three LLMs and nine RAG configurations, under both black-box and white-box access to the retriever. Across these settings, DnD matches or outperforms prior attacks in most configurations, with its largest gains against clustering- and conflict-aware defenses.

cs.CR↗

arXiv2026

Large Language Models and Social Media Information Integrity: Opportunities, Challenges, and Research Directions

Large Language Models (LLMs) have emerged as powerful tools that impact information integrity on social media platforms. This comprehensive review examines the dual role of LLMs in both facilitating and mitigating various information integrity challenges, including misinformation, disinformation, fake news, social bots, and privacy concerns. \textcolor{black}{We conduct a comprehensive review of the literature from 2019 to 2024, screening 1048 studies and performing an in-depth analysis of 215 representative papers. This systematic approach allows us to identify key patterns in how LLMs influence the information security in social media ecosystems.} Through a systematic analysis of papers from multiple databases, our findings reveal that while LLMs can enhance detection capabilities for malicious content and enable sophisticated defense mechanisms, they simultaneously pose risks by enabling the generation of highly convincing, deceptive content. We categorize and analyze the potential and challenges across different dimensions of information integrity, examining technical capabilities, ethical implications, and privacy concerns. The study demonstrates critical gaps in current approaches, particularly in cross-lingual detection, real-time monitoring, and privacy-preserving implementations. We conclude by proposing future research directions and recommendations for stakeholders to leverage LLMs while mitigating risks in social media information integrity.

cs.CR↗

arXiv2026

Rare Concept Generation via Counterfactual Inference in Diffusion Models

Rare concept generation focuses on synthesizing customized images conditioned on text prompts that describe objects with unusual attributes. Previous works failed to align the generated images with rare concepts, resulting in incorrect attribute rendering or inconsistent composition of concepts. Such failures, as we observed, stem from the inherent common knowledge bias in the training stage of diffusion models, where objects are strongly associated with their common attributes, making it difficult to break these associations when generating rare concepts. To address such challenges, in this paper, we propose a novel Counterfactual Inference-based Diffusion approach, dubbed CI-Diff. CI-Diff blocks the interference of the model's inherent common knowledge bias and utilizes the Natural Direct Effect to capture the independent influence of the text prompt of rare concepts on image generation so that decoupling the unusual attributes from the rare concepts. To this end, we reformulate the classifier-free guidance mechanism to highlight the atypical attributes. To the best of our knowledge, we are the first to introduce causal inference into the rare concept generation task. Extensive experiments on the RareBench benchmark validate the superiority of CI-Diff over state-of-the-art diffusion models. Our code can be accessed from https://github.com/200204jzy/CI-Diff.

cs.CV↗

arXiv2026

Dynamic Malicious Skills in Agentic AI

Skills are a key enabling component of agentic AI. While they enhance agents' capabilities, they also introduce new attack surfaces. In this work, we investigate one such attack surface by demonstrating dynamic malicious skills. By embedding malicious instructions in natural-language documentation (e.g., SKILL.md), an attacker can induce an agent to dynamically inject malicious logic into an otherwise benign skill during execution. We evaluate this attack across agentic frameworks such as OpenHands and Claude Code, showing that dynamic malicious skills can successfully introduce a range of malicious behaviors at runtime with non-trivial success rates. To mitigate this vulnerability, we propose a system-level defense that prevents dynamic modification of skills using operating system kernel-enforced read-only mounts. Our evaluation demonstrates that this defense effectively blocks dynamic malicious skills while preserving the functionality of benign skills.

cs.CR↗

arXiv2026

Fingerprinting LLMs via Prompt Injection

Large language models (LLMs) are often modified after release through post-processing such as post-training or quantization, which makes it challenging to determine whether one model is derived from another. Existing provenance detection methods have two main limitations: (1) they embed signals into the base model before release, which is infeasible for already published models, or (2) they compare outputs across models using hand-crafted or random prompts, which are not robust to post-processing. In this work, we propose LLMPrint, a novel detection framework that constructs fingerprints by exploiting LLMs' inherent vulnerability to prompt injection. Our key insight is that by optimizing fingerprint prompts to enforce consistent token preferences, we can obtain fingerprints that are both unique to the base model and robust to post-processing. We further develop a unified verification procedure that applies to both gray-box and black-box settings, with statistical guarantees. We evaluate LLMPrint on five base models and around 700 post-trained or quantized variants. Our results show that LLMPrint achieves high true positive rates while keeping false positive rates near zero. The code is publicly available at https://github.com/hifi-hyp/ACL-LLMPrint.

cs.CR↗

arXiv2026

Robustness of Vision Foundation Models to Common Perturbations

A vision foundation model outputs an embedding vector for an image, which can be affected by common editing operations (e.g., JPEG compression, brightness, contrast adjustments). These common perturbations alter embedding vectors and may impact the performance of downstream tasks using these embeddings. In this work, we present the first systematic study on foundation models' robustness to such perturbations. We propose three robustness metrics and formulate five desired mathematical properties for these metrics, analyzing which properties they satisfy or violate. Using these metrics, we evaluate six industry-scale foundation models (OpenAI, Meta) across nine common perturbation categories, finding them generally non-robust. We also show that common perturbations degrade downstream application performance (e.g., classification accuracy) and that robustness values can predict performance impacts. Finally, we propose a fine-tuning approach to improve robustness without sacrificing utility.

cs.CR↗

arXiv2026

Benchmarking Vision-Language Models under Contradictory Virtual Content Attacks in Augmented Reality

Augmented reality (AR) has rapidly expanded over the past decade. As AR becomes increasingly integrated into daily life, its security and reliability emerge as critical challenges. Among various threats, contradictory virtual content attacks, where malicious or inconsistent virtual elements are introduced into the user's view, pose a unique risk by misleading users, creating semantic confusion, or delivering harmful information. In this work, we systematically model such attacks and present ContrAR, a novel benchmark for evaluating the robustness of vision-language models (VLMs) against virtual content manipulation and contradiction in AR. ContrAR contains 312 real-world AR videos validated by 10 human participants. We further benchmark 11 VLMs, including both commercial and open-source models. Experimental results reveal that while current VLMs exhibit reasonable understanding of contradictory virtual content, room still remains for improvement in detecting and reasoning about adversarial content manipulations in AR environments. Moreover, balancing detection accuracy and latency remains challenging.

cs.CV↗

arXiv2026

BoBa: Boosting Backdoor Detection through Data Distribution Inference in Federated Learning

Federated learning, while being a promising approach for collaborative model training, is susceptible to backdoor attacks due to its decentralized nature. Backdoor attacks have shown remarkable stealthiness, as they compromise model predictions only when inputs contain specific triggers. As a countermeasure, anomaly detection is widely used to filter out backdoor attacks in FL. However, the non-independent and identically distributed (non-IID) data distribution nature of FL clients presents substantial challenges in backdoor attack detection, as the data variety introduces variance among benign models, making them indistinguishable from malicious ones. In this work, we propose a novel distribution-aware backdoor detection mechanism, BoBa, to address this problem. To differentiate outliers arising from data variety versus backdoor attacks, we propose to break down the problem into two steps: clustering clients utilizing their data distribution, and followed by a voting-based detection. We propose a novel data distribution inference mechanism for accurate data distribution estimation. To improve detection robustness, we introduce an overlapping clustering method, where each client is associated with multiple clusters, ensuring that the trustworthiness of a model update is assessed collectively by multiple clusters rather than a single cluster. Through extensive evaluations, we demonstrate that BoBa can reduce the attack success rate to lower than 0.001 while maintaining high main task accuracy across various attack strategies and experimental settings.

cs.LG↗

arXiv2026

Watermark-based Attribution of AI-Generated Content

Several companies have deployed watermark-based detection to identify AI-generated content. However, attribution--the ability to trace back to the user of a generative AI (GenAI) service who created a given AI-generated content--remains largely unexplored despite its growing importance. In this work, we aim to bridge this gap by conducting the first systematic study on watermark-based, user-level attribution of AI-generated content. Our key idea is to assign a unique watermark to each user of the GenAI service and embed this watermark into the AI-generated content created by that user. Attribution is then performed by identifying the user whose watermark best matches the one extracted from the given content. This approach, however, faces a key challenge: How should watermarks be selected for users to maximize attribution performance? To address the challenge, we first theoretically derive lower bounds on detection and attribution performance through rigorous probabilistic analysis for any given set of user watermarks. Then, we select watermarks for users to maximize these lower bounds, thereby optimizing detection and attribution performance. Our theoretical and empirical results show that watermark-based attribution inherits both the accuracy and (non-)robustness properties of the underlying watermark. Specifically, attribution remains highly accurate when the watermarked AI-generated content is either not post-processed or subjected to common post-processing such as JPEG compression, as well as black-box adversarial post-processing with limited query budgets.

cs.CR↗

arXiv2026

Jailbreaking Safeguarded Text-to-Image Models via Large Language Models

Text-to-Image models may generate harmful content, such as pornographic images, particularly when unsafe prompts are submitted. To address this issue, safety filters are often added on top of text-to-image models, or the models themselves are aligned to reduce harmful outputs. However, these defenses remain vulnerable when an attacker strategically designs adversarial prompts to bypass these safety guardrails. In this work, we propose \alg, a method to jailbreak text-to-image models with safety guardrails using a fine-tuned large language model. Unlike other query-based jailbreak attacks that require repeated queries to the target model, our attack generates adversarial prompts efficiently after fine-tuning our AttackLLM. We evaluate our method on three datasets of unsafe prompts and against five safety guardrails. Our results demonstrate that our approach effectively bypasses safety guardrails, outperforms existing no-box attacks, and also facilitates other query-based attacks.

cs.CR↗

arXiv2026

A Comprehensive Survey of Website Fingerprinting Attacks and Defenses in Tor: Advances and Open Challenges

The Tor network provides users with strong anonymity by routing their internet traffic through multiple relays. While Tor encrypts traffic and hides IP addresses, it remains vulnerable to traffic analysis attacks such as the website fingerprinting (WF) attack, achieving increasingly high fingerprinting accuracy even under open-world conditions. In response, researchers have proposed a variety of defenses, ranging from adaptive padding, traffic regularization, and traffic morphing to adversarial perturbation, that seek to obfuscate or reshape traffic traces. However, these defenses often entail trade-offs between privacy, usability, and system performance. Despite extensive research, a comprehensive survey unifying WF datasets, attack methodologies, and defense strategies remains absent. This paper fills that gap by systematically categorizing existing WF research into three key domains: datasets, attack models, and defense mechanisms. We provide an in-depth comparative analysis of techniques, highlight their strengths and limitations under diverse threat models, and discuss emerging challenges such as multi-tab browsing and coarse-grained traffic features. By consolidating prior work and identifying open research directions, this survey serves as a foundation for advancing stronger privacy protection in Tor.

cs.CR↗

arXiv2025

EditTrack: Detecting and Attributing AI-assisted Image Editing

In this work, we formulate and study the problem of image-editing detection and attribution: given a base image and a suspicious image, detection seeks to determine whether the suspicious image was derived from the base image using an AI editing model, while attribution further identifies the specific editing model responsible. Existing methods for detecting and attributing AI-generated images are insufficient for this problem, as they focus on determining whether an image was AI-generated/edited rather than whether it was edited from a particular base image. To bridge this gap, we propose EditTrack, the first framework for this image-editing detection and attribution problem. Building on four key observations about the editing process, EditTrack introduces a novel re-editing strategy and leverages carefully designed similarity metrics to determine whether a suspicious image originates from a base image and, if so, by which model. We evaluate EditTrack on five state-of-the-art editing models across six datasets, demonstrating that it consistently achieves accurate detection and attribution, significantly outperforming five baselines.

cs.CR↗

arXiv2025

VideoMarkBench: Benchmarking Robustness of Video Watermarking

The rapid development of video generative models has led to a surge in highly realistic synthetic videos, raising ethical concerns related to disinformation and copyright infringement. Recently, video watermarking has been proposed as a mitigation strategy by embedding invisible marks into AI-generated videos to enable subsequent detection. However, the robustness of existing video watermarking methods against both common and adversarial perturbations remains underexplored. In this work, we introduce VideoMarkBench, the first systematic benchmark designed to evaluate the robustness of video watermarks under watermark removal and watermark forgery attacks. Our study encompasses a unified dataset generated by three state-of-the-art video generative models, across three video styles, incorporating four watermarking methods and seven aggregation strategies used during detection. We comprehensively evaluate 12 types of perturbations under white-box, black-box, and no-box threat models. Our findings reveal significant vulnerabilities in current watermarking approaches and highlight the urgent need for more robust solutions. Our code is available at https://github.com/zhengyuan-jiang/VideoMarkBench.

cs.CR↗

arXiv2025

SafeText: Safe Text-to-image Models via Aligning the Text Encoder

Text-to-image models can generate harmful images when presented with unsafe prompts, posing significant safety and societal risks. Alignment methods aim to modify these models to ensure they generate only non-harmful images, even when exposed to unsafe prompts. A typical text-to-image model comprises two main components: 1) a text encoder and 2) a diffusion module. Existing alignment methods mainly focus on modifying the diffusion module to prevent harmful image generation. However, this often significantly impacts the model's behavior for safe prompts, causing substantial quality degradation of generated images. In this work, we propose SafeText, a novel alignment method that fine-tunes the text encoder rather than the diffusion module. By adjusting the text encoder, SafeText significantly alters the embedding vectors for unsafe prompts, while minimally affecting those for safe prompts. As a result, the diffusion module generates non-harmful images for unsafe prompts while preserving the quality of images for safe prompts. We evaluate SafeText on multiple datasets of safe and unsafe prompts, including those generated through jailbreak attacks. Our results show that SafeText effectively prevents harmful image generation with minor impact on the images for safe prompts, and SafeText outperforms six existing alignment methods. We will publish our code and data after paper acceptance.

cs.CR↗

arXiv2025

A Transfer Attack to Image Watermarks

Watermark has been widely deployed by industry to detect AI-generated images. The robustness of such watermark-based detector against evasion attacks in the white-box and black-box settings is well understood in the literature. However, the robustness in the no-box setting is much less understood. In this work, we propose a new transfer evasion attack to image watermark in the no-box setting. Our transfer attack adds a perturbation to a watermarked image to evade multiple surrogate watermarking models trained by the attacker itself, and the perturbed watermarked image also evades the target watermarking model. Our major contribution is to show that, both theoretically and empirically, watermark-based AI-generated image detector based on existing watermarking methods is not robust to evasion attacks even if the attacker does not have access to the watermarking model nor the detection API. Our code is available at: https://github.com/hifi-hyp/Watermark-Transfer-Attack.

cs.CR↗

arXiv2025

AI-generated Image Detection: Passive or Watermark?

While text-to-image models offer numerous benefits, they also pose significant societal risks. Detecting AI-generated images is crucial for mitigating these risks. Detection methods can be broadly categorized into passive and watermark-based approaches: passive detectors rely on artifacts present in AI-generated images, whereas watermark-based detectors proactively embed watermarks into such images. A key question is which type of detector performs better in terms of effectiveness, robustness, and efficiency. However, the current literature lacks a comprehensive understanding of this issue. In this work, we aim to bridge that gap by developing ImageDetectBench, the first comprehensive benchmark to compare the effectiveness, robustness, and efficiency of passive and watermark-based detectors. Our benchmark includes four datasets, each containing a mix of AI-generated and non-AI-generated images. We evaluate five passive detectors and four watermark-based detectors against eight types of common perturbations and three types of adversarial perturbations. Our benchmark results reveal several interesting findings. For instance, watermark-based detectors consistently outperform passive detectors, both in the presence and absence of perturbations. Based on these insights, we provide recommendations for detecting AI-generated images, e.g., when both types of detectors are applicable, watermark-based detectors should be the preferred choice. Our code and data are publicly available at https://github.com/moyangkuo/ImageDetectBench.git.

cs.CR↗