5 citations · 7 across the 20 of their papers we have counts for
23 papers
CoRedSkill: Stealthy Skill Composition Attacks via AST-Guided Injection
Qichen Zhao, Shengfang Zhai, Qingni Shen +2
Agents extend their capabilities through reusable skills that package instructions, executable code, and resources. Composing these skills enables complex task workflows, but their…
Don't Solve, Just Compare: Tiny Advisors for Runtime Intervention in LLM Agents
Yanze Jiang, Mingxuan Li, Yuhao Wang +2
LLM agents are emerging as an important paradigm for real-world tasks that require reasoning, tool use, and sequential decision-making. As these agents operate over longer horizons…
AliMark: Enhancing Robustness of Sentence-Level Watermarking Against Text Paraphrasing
Yuexin Li, Wenjie Qu, Linyu Wu +5
Existing sentence-level watermarking methods enhance robustness to paraphrasing by anchoring watermarks in sentence semantics. However, their prefix-based designs remain vulnerable…
Echoes within the Reasoning: Stealthy and Effective Watermarking via Chain of Thought
Jiacheng Lu, Yiming Li, Tao Song +4
Large Language Models with Chain-of-Thought reasoning capabilities represent valuable intellectual property, yet existing black-box watermarking methods often trade robustness for…
AutoResearchClaw: Self-Reinforcing Autonomous Research with Human-AI Collaboration
Jiaqi Liu, Shi Qiu, Mairui Li +33
Automating scientific discovery requires more than generating papers from ideas. Real research is iterative: hypotheses are challenged from multiple perspectives, experiments fail…
Securing LLM Agents Need Intent-to-Execution Integrity
Wenjie Qu, Ming Xu, Peiran Wang +3
This position paper argues that securing LLM agents requires first defining an end-to-end correctness property that specifies when an agent's execution faithfully reflects the user…
SAMark: A Self-Anchored Text Watermarking with Paragraph-Level Paraphrase Robustness
Jiahao Huo, Wenjie Qu, Yibo Yan +5
Semantic-level watermarking (SWM) improves robustness against text modifications by treating sentences as the basic unit. However, robustness to paragraph-level paraphrasing remain…
STEP: Detecting Audio Backdoor Attacks via Stability-based Trigger Exposure Profiling
Kun Wang, Meng Chen, Junhao Wang +6
With the widespread deployment of deep-learning-based speech models in security-critical applications, backdoor attacks have emerged as a serious threat: an adversary who poisons a…
V3DB: Audit-on-Demand Zero-Knowledge Proofs for Verifiable Vector Search over Committed Snapshots
Zipeng Qiu, Wenjie Qu, Jiaheng Zhang +1
Dense retrieval services increasingly underpin semantic search, recommendation, and retrieval-augmented generation, yet clients typically receive only a top- list with no audita…
Self-Sovereign Agent
Wenjie Qu, Xuandong Zhao, Jiaheng Zhang +1
We investigate the emerging prospect of self-sovereign agents -- AI systems that can economically sustain and extend their own operation without human involvement. Recent advances…
Efficient Self-Evaluation for Diffusion Language Models via Sequence Regeneration
Linhao Zhong, Linyu Wu, Wen Wang +5
Diffusion large language models (dLLMs) have recently attracted significant attention for their ability to enhance diversity, controllability, and parallelism. However, their non-s…
IMMACULATE: A Practical LLM Auditing Framework via Verifiable Computation
Yanpei Guo, Wenjie Qu, Linyu Wu +7
Commercial large language models are typically deployed as black-box API services, requiring users to trust providers to execute inference correctly and report token usage honestly…
On Representation Redundancy in Large-Scale Instruction Tuning Data Selection
Youwei Shu, Shaomian Zheng, Dingnan Jin +5
Data quality is a crucial factor in large language models training. While prior work has shown that models trained on smaller, high-quality datasets can outperform those trained on…
GuardReasoner-Omni: A Reasoning-based Multi-modal Guardrail for Text, Image, Video, and Audio
Zhenhao Zhu, Yue Liu, Yanpei Guo +9
We present GuardReasoner-Omni, a reasoning-based guardrail model designed to moderate text, image, video, and audio data. First, we construct a comprehensive training corpus compri…
DMark: Order-Agnostic Watermarking for Diffusion Large Language Models
Linyu Wu, Linhao Zhong, Wenjie Qu +5
Diffusion large language models (dLLMs) offer faster generation than autoregressive models while maintaining comparable quality, but existing watermarking methods fail on them due…
RepoMark: A Data-Usage Auditing Framework for Code Large Language Models
Wenjie Qu, Yuguang Zhou, Bo Wang +4
The rapid development of Large Language Models (LLMs) for code generation has transformed software development by automating coding tasks with unprecedented efficiency. However, th…
Prompt Inversion Attack against Collaborative Inference of Large Language Models
Wenjie Qu, Yuguang Zhou, Yongji Wu +4
Large language models (LLMs) have been widely applied for their remarkable capability of content generation. However, the practical use of open-source LLMs is hindered by high reso…
Silent Leaks: Implicit Knowledge Extraction Attack on RAG Systems through Benign Queries
Yuhao Wang, Wenjie Qu, Shengfang Zhai +5
Retrieval-Augmented Generation (RAG) systems enhance large language models (LLMs) by incorporating external knowledge bases, but this may expose them to extraction attacks, leading…
Sparse Autoencoder as a Zero-Shot Classifier for Concept Erasing in Text-to-Image Diffusion Models
Zhihua Tian, Sirun Nan, Ming Xu +5
Text-to-image (T2I) diffusion models have achieved remarkable progress in generating high-quality images but also raise people's concerns about generating harmful or misleading con…
Efficient Input-level Backdoor Defense on Text-to-Image Synthesis via Neuron Activation Variation
Shengfang Zhai, Jiajun Li, Yue Liu +7
In recent years, text-to-image (T2I) diffusion models have gained significant attention for their ability to generate high quality images reflecting text prompts. However, their gr…
FlipAttack: Jailbreak LLMs via Flipping
Yue Liu, Xiaoxin He, Miao Xiong +5
This paper proposes a simple yet effective jailbreak attack named FlipAttack against black-box LLMs. First, from the autoregressive nature, we reveal that LLMs tend to understand t…
Lazarus: Resilient and Elastic Training of Mixture-of-Experts Models
Yongji Wu, Wenjie Qu, Xueshen Liu +10
Sparsely-activated Mixture-of-Experts (MoE) architecture has increasingly been adopted to further scale large language models (LLMs). However, frequent failures still pose signific…
Provably Robust Multi-bit Watermarking for AI-generated Text
Wenjie Qu, Wengrui Zheng, Tianyang Tao +6
Large Language Models (LLMs) have demonstrated remarkable capabilities of generating texts resembling human language. However, they can be misused by criminals to create deceptive…