2 citations · 2 across the 14 of their papers we have counts for
16 papers
Memory Echo in Single-Agent Long-Term Memory: Lifecycle Evaluation and Provenance-Guided Mitigation
Yufeng Li, Sheng Yao, Peng Zeng +5
Long-term memory supports agents across sessions. Repeated retrieval and write-back can let one historical claim occupy multiple retrieval positions and influence current answers w…
TTS-Guard: Black-Box Ownership Verification of Text-to-Speech Models via Adaptive Adversarial Speaker-Pair Fingerprints
Xubin Yue, Zhenhua Xu, Zhebo Wang +5
The rapid maturation of zero-shot Text-to-Speech (TTS) models has turned high-quality voice cloning into a widely available capability, raising acute concerns over unauthorised rep…
Before Agents Speak: Pre-hoc Failure Risk Inference in Multi-Agent Systems
Shi Lin, Chenpei Wang, Peng Qian +4
LLM-based multi-agent systems (MAS) have exhibited remarkable capabilities in collaborative reasoning and decision-making, yet their interconnected communications introduce new sys…
Forecasting Trajectory-Level Safety Risks in Black-Box Multi-Turn Interactions
Shi Lin, Peng Qian, Dinghao Liu +5
As large language models (LLMs) evolve from standalone assistants into autonomous agents, ensuring their safety requires shifting beyond pointwise risk assessment to understand how…
AttnDiff: Attention-based Differential Fingerprinting for Large Language Models
Haobo Zhang, Zhenhua Xu, Junxian Li +3
Protecting the intellectual property of open-weight large language models (LLMs) requires verifying whether a suspect model is derived from a victim model despite common laundering…
DNF: Dual-Layer Nested Fingerprinting for Large Language Model Intellectual Property Protection
Zhenhua Xu, Yiran Zhao, Mengting Zhong +4
The rapid growth of large language models raises pressing concerns about intellectual property protection under black-box deployment. Existing backdoor-based fingerprints either re…
ICPO: Illocution-Calibrated Policy Optimization for Multi-Turn Conversation
Zhebo Wang, Xiaohu Mu, Zijie Zhou +4
Large Language Models (LLMs) in multi-turn conversations often suffer from a ``lost-in-conversation'' phenomenon, where they struggle to recover from early incorrect assumptions, p…
Policy of Thoughts: Scaling Test-Time Training for LLM Reasoning via Online Policy Evolution
Zhengbo Jiao, Hongyu Xian, Qinglong Wang +5
Large language models (LLMs) struggle with complex, long-horizon reasoning due to instability caused by their frozen policy assumption. Current test-time scaling methods treat exec…
MalURLBench: A Benchmark Evaluating Agents' Vulnerabilities When Processing Web URLs
Dezhang Kong, Zhuxi Wu, Shiqi Liu +8
LLM-based web agents have become increasingly popular for their utility in daily life and work. However, they exhibit critical vulnerabilities when processing malicious URLs: accep…
Scalpel-SAM: A Semi-Supervised Paradigm for Adapting SAM to Infrared Small Object Detection
Zihan Liu, Xiangning Ren, Dezhang Kong +2
Infrared small object detection urgently requires semi-supervised paradigms due to the high cost of annotation. However, existing methods like SAM face significant challenges of do…
Web Fraud Attacks Against LLM-Driven Multi-Agent Systems
Dezhang Kong, Hujin Peng, Yilun Zhang +5
With the proliferation of LLM-driven multi-agent systems (MAS), the security of Web links has become a critical concern. Once MAS is induced to trust a malicious link, attackers ca…
Copyright Protection for Large Language Models: A Survey of Methods, Challenges, and Trends
Zhenhua Xu, Xubin Yue, Zhebo Wang +9
Copyright protection for large language models is of critical importance, given their substantial development costs, proprietary value, and potential for misuse. Existing surveys h…
A Survey of LLM-Driven AI Agent Communication: Protocols, Security Risks, and Defense Countermeasures
Dezhang Kong, Shi Lin, Zhenhua Xu +16
In recent years, Large-Language-Model-driven AI agents have exhibited unprecedented intelligence and adaptability. Nowadays, agents are undergoing a new round of evolution. They no…
NeuRel-Attack: Neuron Relearning for Safety Disalignment in Large Language Models
Yi Zhou, Wenpeng Xing, Dezhang Kong +2
Safety alignment in large language models (LLMs) is achieved through fine-tuning mechanisms that regulate neuron activations to suppress harmful content. In this work, we propose a…
Fingerprint Vector: Enabling Scalable and Efficient Model Fingerprint Transfer via Vector Addition
Zhenhua Xu, Qichen Liu, Zhebo Wang +4
Backdoor-based fingerprinting has emerged as an effective technique for tracing the ownership of large language models. However, in real-world deployment scenarios, developers ofte…
Reasoning as a Weapon: Adaptive Dual-Path Jailbreak Attack on Large Language Models
Shi Lin, Peng Qian, Hongming Yang +3
Large language models (LLMs) have achieved remarkable progress across a wide range of applications. Despite advances in safety alignment, they remain vulnerable to jailbreak attack…