3 citations · 5 across the 28 of their papers we have counts for
15 papers · 1 filter
SINGED: Correct Outputs Do Not Certify Safe Execution in LLM Agents
Xiaoyu Xu, Zi Liang, Minxin Du +4
Tool-using language-model agents select and execute third-party artifacts. Different implementations can return the requested output while producing hidden execution effects that t…
CAITLYN: Can LLM Agents Autonomously Synthesize Defenses against Emerging Injection Attacks?
Zi Liang, Xiaoyu Xu, Yanyun Wang +3
Prompt injection attacks on Large Language Model (LLM) agents seek to introduce malicious instructions or content into external text sources retrieved by agents, forcing the underl…
Is Imagination Derived from Hallucination? A Cross-Taxonomy Evaluation of Imagination and Hallucination in Large Language Models
Zixuan Tang, Hongzong Li, Shuxin Zhuang +2
Imagination performs as a high-level function of large language models (LLMs) which determines the potential of how an LLM creates unseen or creative content. While existing works…
Where World Models Break: Natural-Input Failure Discovery
Zhanpeng Shi, Zi Liang, Rong Feng +3
World models predict action-conditioned futures and serve as critical internal simulators for downstream planning and control. However, catastrophic prediction failures of world mo…
Adversarial Attacks on Deep OCR Systems
Wenbo Sun, Hongzong LI, Yanyun Wang +5
Deep-OCR (DeepSeek-OCR) advances document recognition by treating the visual modality as an optical compression medium, enabling long-context OCR at low token cost. However, its in…
Controlled Memory Interference in Continual LLM Agents
Ao Ding, Hongzong LI, Shiqin Tang +4
Long-term memory enables AI agents to maintain continuity across sessions, personalize behavior, and evolve through accumulated experience. Yet memory evolution is not simply a pro…
Beyond Prompt Engineering: A Systematic Analysis of Prompt Lexical Sensitivity and Its Impacts on Quality
Qipeng Xie, Zi Liang, Jiafei Wu +6
Large Language Models (LLMs) exhibit extreme sensitivity to surface-level prompt variations, in which minor lexical changes can trigger disproportionate performance fluctuations. M…
Acoustic Interference: A New Paradigm Weaponizing Acoustic Latent Semantic for Universal Jailbreak against Large Audio Language Models
Yanyun Wang, Yu Huang, Zi Liang +2
The integration of audio modality into Large Audio Language Models (LALMs) significantly expands their attack surface. Existing jailbreak paradigms predominantly treat audio as a c…
Mobius Injection: From One-Shot Prompt Injection to Sustained Resource Exhaustion in AI Agent Infrastructure
Zi Liang, Ronghua Li, Yanyun Wang +2
Large Language Model (LLM) agents have emerged as key intermediaries, orchestrating complex interactions between human users and a wide range of digital services and LLM infrastruc…
Robust Alignment: Harmonizing Clean Accuracy and Adversarial Robustness in Adversarial Training
Yanyun Wang, Qingqing Ye, Li Liu +2
Adversarial Training (AT) is one of the most effective methods for developing robust deep neural networks (DNNs). However, AT faces a trade-off problem between clean accuracy and a…
Argus: Reorchestrating Static Analysis via a Multi-Agent Ensemble for Full-Chain Security Vulnerability Detection
Zi Liang, Qipeng Xie, Jun He +7
Recent advancements in Large Language Models (LLMs) have sparked interest in their application to Static Application Security Testing (SAST), primarily due to their superior contex…
How Vulnerable Are Edge LLMs?
Ao Ding, Hongzong Li, Zi Liang +5
Large language models (LLMs) are increasingly deployed on edge devices under strict computation and quantization constraints, yet their security implications remain unclear. We stu…
How Much Information Can a Vision Token Hold? A Scaling Law for Recognition Limits in VLMs
Shuxin Zhuang, Zi Liang, Runsheng Yu +4
Recent vision-centric approaches have made significant strides in long-context modeling. Represented by DeepSeek-OCR, these models encode rendered text into continuous vision token…
FIT to Forget: Robust Continual Unlearning for Large Language Models
Xiaoyu Xu, Minxin Du, Kun Fang +5
While large language models (LLMs) exhibit remarkable capabilities, they increasingly face demands to unlearn memorized privacy-sensitive, copyrighted, or harmful content. Existing…
From Domains to Instances: Dual-Granularity Data Synthesis for LLM Unlearning
Xiaoyu Xu, Minxin Du, Zitong Li +6
Although machine unlearning is essential for removing private, harmful, or copyrighted content from LLMs, current benchmarks often fail to faithfully represent the true ``forgettin…