8 citations · 30 across the 14 of their papers we have counts for
14 papers
InjecMEM: Memory Injection Attack on LLM Agent Memory Systems
Hanling Tian, Gengyu Zhang, Zeyang Sha +5
Memory is becoming a default subsystem in deployed LLM agents to provide persistent personalization and continuity. This naturally prompts a question: will memory system introduce…
The Reasoning Trap: How Enhancing LLM Reasoning Amplifies Tool Hallucination
Chenlong Yin, Zeyang Sha, Shiwen Cui +2
Enhancing the reasoning capabilities of Large Language Models (LLMs) is a key strategy for building Agents that "think then act." However, recent observations, like OpenAI's o3, su…
Agent Safety Alignment via Reinforcement Learning
Zeyang Sha, Hanling Tian, Zhuoer Xu +3
The emergence of autonomous Large Language Model (LLM) agents capable of tool usage has introduced new safety risks that go beyond traditional conversational misuse. These agents,…
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…
SEM: Reinforcement Learning for Search-Efficient Large Language Models
Zeyang Sha, Shiwen Cui, Weiqiang Wang
Recent advancements in Large Language Models(LLMs) have demonstrated their capabilities not only in reasoning but also in invoking external tools, particularly search engines. Howe…
Can VLMs Detect and Localize Fine-Grained AI-Edited Images?
Zhen Sun, Ziyi Zhang, Zeren Luo +10
Fine-grained detection and localization of localized image edits is crucial for assessing content authenticity, especially as modern diffusion models and image editors can produce…
Thought Manipulation: External Thought Can Be Efficient for Large Reasoning Models
Yule Liu, Jingyi Zheng, Zhen Sun +6
Recent advancements in large reasoning models (LRMs) have demonstrated the effectiveness of scaling test-time computation to enhance reasoning capabilities on various tasks. Howeve…
Prompt Stealing Attacks Against Large Language Models
Zeyang Sha, Yang Zhang
The increasing reliance on large language models (LLMs) such as ChatGPT in various fields emphasizes the importance of ``prompt engineering,'' a technology to improve the quality o…
Reconstruct Your Previous Conversations! Comprehensively Investigating Privacy Leakage Risks in Conversations with GPT Models
Junjie Chu, Zeyang Sha, Michael Backes +1
Significant advancements have recently been made in large language models represented by GPT models. Users frequently have multi-round private conversations with cloud-hosted GPT m…
Comprehensive Assessment of Toxicity in ChatGPT
Boyang Zhang, Xinyue Shen, Wai Man Si +6
Moderating offensive, hateful, and toxic language has always been an important but challenging topic in the domain of safe use in NLP. The emerging large language models (LLMs), su…
From Visual Prompt Learning to Zero-Shot Transfer: Mapping Is All You Need
Ziqing Yang, Zeyang Sha, Michael Backes +1
Visual prompt learning, as a newly emerged technique, leverages the knowledge learned by a large-scale pre-trained model and adapts it to downstream tasks through the usage of prom…
Fine-Tuning Is All You Need to Mitigate Backdoor Attacks
Zeyang Sha, Xinlei He, Pascal Berrang +2
Backdoor attacks represent one of the major threats to machine learning models. Various efforts have been made to mitigate backdoors. However, existing defenses have become increas…
DE-FAKE: Detection and Attribution of Fake Images Generated by Text-to-Image Generation Models
Zeyang Sha, Zheng Li, Ning Yu +1
Text-to-image generation models that generate images based on prompt descriptions have attracted an increasing amount of attention during the past few months. Despite their encoura…
Can't Steal? Cont-Steal! Contrastive Stealing Attacks Against Image Encoders
Zeyang Sha, Xinlei He, Ning Yu +2
Self-supervised representation learning techniques have been developing rapidly to make full use of unlabeled images. They encode images into rich features that are oblivious to do…