arXiv subjects

Quanchen Zou

Publications and source records attributed to Quanchen Zou.

30 records · Page 2Linked to original sources

arXiv2026

Evolving Deception: When Agents Evolve, Deception Wins

Self-evolving agents offer a promising path toward scalable autonomy. However, in this work, we show that in competitive environments, self-evolution can instead give rise to a serious and previously underexplored risk: the spontaneous emergence of deception as an evolutionarily stable strategy. We conduct a systematic empirical study on the self-evolution of large language model (LLM) agents in a competitive Bidding Arena, where agents iteratively refine their strategies through interaction-driven reflection. Across different evolutionary paths (\eg, Neutral, Honesty-Guided, and Deception-Guided), we find a consistent pattern: under utility-driven competition, unconstrained self-evolution reliably drifts toward deceptive behaviors, even when honest strategies remain viable. This drift is explained by a fundamental asymmetry in generalization. Deception evolves as a transferable meta-strategy that generalizes robustly across diverse and unseen tasks, whereas honesty-based strategies are fragile and often collapse outside their original contexts. Further analysis of agents internal states reveals the emergence of rationalization mechanisms, through which agents justify or deny deceptive actions to reconcile competitive success with normative instructions. Our paper exposes a fundamental tension between agent self-evolution and alignment, highlighting the risks of deploying self-improving agents in adversarial environments.

cs.CR↗

arXiv2026

Reasoning-Oriented Programming: Chaining Semantic Gadgets to Jailbreak Large Vision Language Models

Large Vision-Language Models (LVLMs) undergo safety alignment to suppress harmful content. However, current defenses predominantly target explicit malicious patterns in the input representation, often overlooking the vulnerabilities inherent in compositional reasoning. In this paper, we identify a systemic flaw where LVLMs can be induced to synthesize harmful logic from benign premises. We formalize this attack paradigm as \textit{Reasoning-Oriented Programming}, drawing a structural analogy to Return-Oriented Programming in systems security. Just as ROP circumvents memory protections by chaining benign instruction sequences, our approach exploits the model's instruction-following capability to orchestrate a semantic collision of orthogonal benign inputs. We instantiate this paradigm via \tool{}, an automated framework that optimizes for \textit{semantic orthogonality} and \textit{spatial isolation}. By generating visual gadgets that are semantically decoupled from the harmful intent and arranging them to prevent premature feature fusion, \tool{} forces the malicious logic to emerge only during the late-stage reasoning process. This effectively bypasses perception-level alignment. We evaluate \tool{} on SafeBench and MM-SafetyBench across 7 state-of-the-art 0.LVLMs, including GPT-4o and Claude 3.7 Sonnet. Our results demonstrate that \tool{} consistently circumvents safety alignment, outperforming the strongest existing baseline by an average of 4.67\% on open-source models and 9.50\% on commercial models.

cs.CR↗

arXiv2026

SPARK: Jailbreaking T2V Models by Synergistically Prompting Auditory and Recontextualized Knowledge

Jailbreak attacks can circumvent model safety guardrails and reveal critical blind spots. Prior attacks on text-to-video (T2V) models typically add adversarial perturbations to obviously unsafe prompts, which are often easy to detect and defend. In contrast, we show that benign-looking prompts containing rich, implicit cues can induce T2V models to generate semantically unsafe videos that both violate policy and preserve the original (blocked) intent. To realize this, we propose SPARK, a jailbreak framework that leverages T2V models cross-modal associative patterns via a modular prompt design. Specifically, our prompts combine three components: neutral scene anchors, which provide the surface-level scene description extracted from the blocked intent to maintain plausibility; latent auditory triggers, textual descriptions of innocuous-sounding audio events (e.g., creaking, muffled noises) that exploit learned audio-visual co-occurrence priors to bias the model toward particular unsafe visual concepts; and stylistic modulators, cinematic directives (e.g., camera framing, atmosphere) that amplify and stabilize the latent trigger's effect. We formalize attack generation as a constrained optimization over the above modular prompt space and solve it with a guided search procedure that balances stealth and effectiveness. Extensive experiments over 7 T2V models demonstrate the efficacy of our attack, achieving a +23% improvement in average attack success rate in commercial models.

cs.CV↗

arXiv2026

Mask-GCG: Are All Tokens in Adversarial Suffixes Necessary for Jailbreak Attacks?

Jailbreak attacks on Large Language Models (LLMs) have demonstrated various successful methods whereby attackers manipulate models into generating harmful responses that they are designed to avoid. Among these, Greedy Coordinate Gradient (GCG) has emerged as a general and effective approach that optimizes the tokens in a suffix to generate jailbreakable prompts. While several improved variants of GCG have been proposed, they all rely on fixed-length suffixes. However, the potential redundancy within these suffixes remains unexplored. In this work, we propose Mask-GCG, a plug-and-play method that employs learnable token masking to identify impactful tokens within the suffix. Our approach increases the update probability for tokens at high-impact positions while pruning those at low-impact positions. This pruning not only reduces redundancy but also decreases the size of the gradient space, thereby lowering computational overhead and shortening the time required to achieve successful attacks compared to GCG. We evaluate Mask-GCG by applying it to the original GCG and several improved variants. Experimental results show that most tokens in the suffix contribute significantly to attack success, and pruning a minority of low-impact tokens does not affect the loss values or compromise the attack success rate (ASR), thereby revealing token redundancy in LLM prompts. Our findings provide insights for developing efficient and interpretable LLMs from the perspective of jailbreak attacks.

cs.CL↗

arXiv2026

DIVER: Dynamic Iterative Visual Evidence Reasoning for Multimodal Fake News Detection

Multimodal fake news detection is crucial for mitigating adversarial misinformation. Existing methods, relying on static fusion or LLMs, face computational redundancy and hallucination risks due to weak visual foundations. To address this, we propose DIVER (Dynamic Iterative Visual Evidence Reasoning), a framework grounded in a progressive, evidence-driven reasoning paradigm. DIVER first establishes a strong text-based baseline through language analysis, leveraging intra-modal consistency to filter unreliable or hallucinated claims. Only when textual evidence is insufficient does the framework introduce visual information, where inter-modal alignment verification adaptively determines whether deeper visual inspection is necessary. For samples exhibiting significant cross-modal semantic discrepancies, DIVER selectively invokes fine-grained visual tools (e.g., OCR and dense captioning) to extract task-relevant evidence, which is iteratively aggregated via uncertainty-aware fusion to refine multimodal reasoning. Experiments on Weibo, Weibo21, and GossipCop demonstrate that DIVER outperforms state-of-the-art baselines by an average of 2.72\%, while optimizing inference efficiency with a reduced latency of 4.12 s.

cs.CV↗

arXiv2026

SAPL: Semantic-Agnostic Prompt Learning in CLIP for Weakly Supervised Image Manipulation Localization

Malicious image manipulation threatens public safety and requires efficient localization methods. Existing approaches depend on costly pixel-level annotations which make training expensive. Existing weakly supervised methods rely only on image-level binary labels and focus on global classification, often overlooking local edge cues that are critical for precise localization. We observe that feature variations at manipulated boundaries are substantially larger than in interior regions. To address this gap, we propose Semantic-Agnostic Prompt Learning (SAPL) in CLIP, which learns text prompts that intentionally encode non-semantic, boundary-centric cues so that CLIPs multimodal similarity highlights manipulation edges rather than high-level object semantics. SAPL combines two complementary modules Edge-aware Contextual Prompt Learning (ECPL) and Hierarchical Edge Contrastive Learning (HECL) to exploit edge information in both textual and visual spaces. The proposed ECPL leverages edge-enhanced image features to generate learnable textual prompts via an attention mechanism, embedding semantic-irrelevant information into text features, to guide CLIP focusing on manipulation edges. The proposed HECL extract genuine and manipulated edge patches, and utilize contrastive learning to boost the discrimination between genuine edge patches and manipulated edge patches. Finally, we predict the manipulated regions from the similarity map after processing. Extensive experiments on multiple public benchmarks demonstrate that SAPL significantly outperforms existing approaches, achieving state-of-the-art localization performance.

cs.CV↗

arXiv2025

RoboSafe: Safeguarding Embodied Agents via Executable Safety Logic

Embodied agents powered by vision-language models (VLMs) are increasingly capable of executing complex real-world tasks, yet they remain vulnerable to hazardous instructions that may trigger unsafe behaviors. Runtime safety guardrails, which intercept hazardous actions during task execution, offer a promising solution due to their flexibility. However, existing defenses often rely on static rule filters or prompt-level control, which struggle to address implicit risks arising in dynamic, temporally dependent, and context-rich environments. To address this, we propose RoboSafe, a hybrid reasoning runtime safeguard for embodied agents through executable predicate-based safety logic. RoboSafe integrates two complementary reasoning processes on a Hybrid Long-Short Safety Memory. We first propose a Backward Reflective Reasoning module that continuously revisits recent trajectories in short-term memory to infer temporal safety predicates and proactively triggers replanning when violations are detected. We then propose a Forward Predictive Reasoning module that anticipates upcoming risks by generating context-aware safety predicates from the long-term safety memory and the agent's multimodal observations. Together, these components form an adaptive, verifiable safety logic that is both interpretable and executable as code. Extensive experiments across multiple agents demonstrate that RoboSafe substantially reduces hazardous actions (-36.8% risk occurrence) compared with leading baselines, while maintaining near-original task performance. Real-world evaluations on physical robotic arms further confirm its practicality. Code will be released upon acceptance.

cs.AI↗

arXiv2025

Towards Understanding the Safety Boundaries of DeepSeek Models: Evaluation and Findings

This study presents the first comprehensive safety evaluation of the DeepSeek models, focusing on evaluating the safety risks associated with their generated content. Our evaluation encompasses DeepSeek's latest generation of large language models, multimodal large language models, and text-to-image models, systematically examining their performance regarding unsafe content generation. Notably, we developed a bilingual (Chinese-English) safety evaluation dataset tailored to Chinese sociocultural contexts, enabling a more thorough evaluation of the safety capabilities of Chinese-developed models. Experimental results indicate that despite their strong general capabilities, DeepSeek models exhibit significant safety vulnerabilities across multiple risk dimensions, including algorithmic discrimination and sexual content. These findings provide crucial insights for understanding and improving the safety of large foundation models. Our code is available at https://github.com/NY1024/DeepSeek-Safety-Eval.

cs.CR↗

arXiv2025

Reasoning-Augmented Conversation for Multi-Turn Jailbreak Attacks on Large Language Models

Multi-turn jailbreak attacks simulate real-world human interactions by engaging large language models (LLMs) in iterative dialogues, exposing critical safety vulnerabilities. However, existing methods often struggle to balance semantic coherence with attack effectiveness, resulting in either benign semantic drift or ineffective detection evasion. To address this challenge, we propose Reasoning-Augmented Conversation, a novel multi-turn jailbreak framework that reformulates harmful queries into benign reasoning tasks and leverages LLMs' strong reasoning capabilities to compromise safety alignment. Specifically, we introduce an attack state machine framework to systematically model problem translation and iterative reasoning, ensuring coherent query generation across multiple turns. Building on this framework, we design gain-guided exploration, self-play, and rejection feedback modules to preserve attack semantics, enhance effectiveness, and sustain reasoning-driven attack progression. Extensive experiments on multiple LLMs demonstrate that RACE achieves state-of-the-art attack effectiveness in complex conversational scenarios, with attack success rates (ASRs) increasing by up to 96%. Notably, our approach achieves ASRs of 82% and 92% against leading commercial models, OpenAI o1 and DeepSeek R1, underscoring its potency. We release our code at https://github.com/NY1024/RACE to facilitate further research in this critical domain.

cs.CL↗

arXiv2025

Towards Reliable Vector Database Management Systems: A Software Testing Roadmap for 2030

The rapid growth of Large Language Models (LLMs) and AI-driven applications has propelled Vector Database Management Systems (VDBMSs) into the spotlight as a critical infrastructure component. VDBMS specializes in storing, indexing, and querying dense vector embeddings, enabling advanced LLM capabilities such as retrieval-augmented generation, long-term memory, and caching mechanisms. However, the explosive adoption of VDBMS has outpaced the development of rigorous software testing methodologies tailored for these emerging systems. Unlike traditional databases optimized for structured data, VDBMS face unique testing challenges stemming from the high-dimensional nature of vector data, the fuzzy semantics in vector search, and the need to support dynamic data scaling and hybrid query processing. In this paper, we begin by conducting an empirical study of VDBMS defects and identify key challenges in test input generation, oracle definition, and test evaluation. Drawing from these insights, we propose the first comprehensive research roadmap for developing effective testing methodologies tailored to VDBMS. By addressing these challenges, the software testing community can contribute to the development of more reliable and trustworthy VDBMS, enabling the full potential of LLMs and data-intensive AI applications.

cs.SE↗

arXiv2024

Multi-Turn Context Jailbreak Attack on Large Language Models From First Principles

Large language models (LLMs) have significantly enhanced the performance of numerous applications, from intelligent conversations to text generation. However, their inherent security vulnerabilities have become an increasingly significant challenge, especially with respect to jailbreak attacks. Attackers can circumvent the security mechanisms of these LLMs, breaching security constraints and causing harmful outputs. Focusing on multi-turn semantic jailbreak attacks, we observe that existing methods lack specific considerations for the role of multiturn dialogues in attack strategies, leading to semantic deviations during continuous interactions. Therefore, in this paper, we establish a theoretical foundation for multi-turn attacks by considering their support in jailbreak attacks, and based on this, propose a context-based contextual fusion black-box jailbreak attack method, named Context Fusion Attack (CFA). This method approach involves filtering and extracting key terms from the target, constructing contextual scenarios around these terms, dynamically integrating the target into the scenarios, replacing malicious key terms within the target, and thereby concealing the direct malicious intent. Through comparisons on various mainstream LLMs and red team datasets, we have demonstrated CFA's superior success rate, divergence, and harmfulness compared to other multi-turn attack strategies, particularly showcasing significant advantages on Llama3 and GPT-4.

cs.CL↗

arXiv2023

ConFL: Constraint-guided Fuzzing for Machine Learning Framework

As machine learning gains prominence in various sectors of society for automated decision-making, concerns have risen regarding potential vulnerabilities in machine learning (ML) frameworks. Nevertheless, testing these frameworks is a daunting task due to their intricate implementation. Previous research on fuzzing ML frameworks has struggled to effectively extract input constraints and generate valid inputs, leading to extended fuzzing durations for deep execution or revealing the target crash. In this paper, we propose ConFL, a constraint-guided fuzzer for ML frameworks. ConFL automatically extracting constraints from kernel codes without the need for any prior knowledge. Guided by the constraints, ConFL is able to generate valid inputs that can pass the verification and explore deeper paths of kernel codes. In addition, we design a grouping technique to boost the fuzzing efficiency. To demonstrate the effectiveness of ConFL, we evaluated its performance mainly on Tensorflow. We find that ConFL is able to cover more code lines, and generate more valid inputs than state-of-the-art (SOTA) fuzzers. More importantly, ConFL found 84 previously unknown vulnerabilities in different versions of Tensorflow, all of which were assigned with new CVE ids, of which 3 were critical-severity and 13 were high-severity. We also extended ConFL to test PyTorch and Paddle, 7 vulnerabilities are found to date.

cs.SE↗