activity
20242026
collaborators

6 papers

cs.CL2026

DiscourseFlip: An Oblique Discourse-Level Opinion Manipulation Attack against Black-box Retrieval-Augmented Generation

Yuyang Gong, Miaokun Chen, Jiawei Liu +5

Retrieval-Augmented Generation (RAG) systems are widely deployed and increasingly influential, but their reliance on external corpora exposes new security risks from poisoned retri…

cs.AI2026

Can We Trust a Black-box LLM? LLM Untrustworthy Boundary Detection via Bias-Diffusion and Multi-Agent Reinforcement Learning

Xiaotian Zhou, Di Tang, Xiaofeng Wang +1

Large Language Models (LLMs) have shown a high capability in answering questions on a diverse range of topics. However, these models sometimes produce biased, ideologized or incorr…

cs.AI2026

LLM-as-Judge for Semantic Judging of Powerline Segmentation in UAV Inspection

Akram Hossain, Rabab Abdelfattah, Xiaofeng Wang +1

The deployment of lightweight segmentation models on drones for autonomous power line inspection presents a critical challenge: maintaining reliable performance under real-world co…

cs.CL2025

Topic-FlipRAG: Topic-Orientated Adversarial Opinion Manipulation Attacks to Retrieval-Augmented Generation Models

Yuyang Gong, Zhuo Chen, Jiawei Liu +5

Retrieval-Augmented Generation (RAG) systems based on Large Language Models (LLMs) have become essential for tasks such as question answering and content generation. However, their…

cs.CR2025

RAG-WM: An Efficient Black-Box Watermarking Approach for Retrieval-Augmented Generation of Large Language Models

Peizhuo Lv, Mengjie Sun, Hao Wang +5

In recent years, tremendous success has been witnessed in Retrieval-Augmented Generation (RAG), widely used to enhance Large Language Models (LLMs) in domain-specific, knowledge-in…

cs.CR2024

PersonaMark: Personalized LLM watermarking for model protection and user attribution

Yuehan Zhang, Peizhuo Lv, Yinpeng Liu +5

The rapid advancement of customized Large Language Models (LLMs) offers considerable convenience. However, it also intensifies concerns regarding the protection of copyright/confid…