1 citations · 1 across the 13 of their papers we have counts for
15 papers
JudgeStealer: Extracting LLM Judging Capabilities across Evaluation Protocols
Chen Chen, Yaolin Chen, Xuehan Sun +5
Large language model (LLM) judges are increasingly used across various evaluation scenarios, making their judgment capabilities valuable intellectual property. However, black-box a…
The Art of Mixology: Mixup-based Obfuscation for Privacy-Preserving Split Learning in Large Language Models
Chen Chen, Xiang Gao, Xianshun Wang +6
Split learning provides a practical paradigm for resource-constrained users to train Large Language Models (LLMs) by offloading computation-intensive layers to a server while keepi…
SoK: Security and Privacy of Foundation-Model-Powered Robots
Xueluan Gong, Chen Chen, Jinxin Liu +2
Foundation models are reshaping robotics by enabling robots to interpret open-ended instructions, reason over multimodal contexts, and operate in complex, open-world environments.…
Plato's Form: Toward Backdoor Defense-as-a-Service for LLMs with Prototype Representations
Chen Chen, Yuchen Sun, Jiaxin Gao +4
Large language models (LLMs) are increasingly deployed in security-sensitive applications, yet remain vulnerable to backdoor attacks. However, existing backdoor defenses are diffic…
The Shadow Self: Intrinsic Value Misalignment in Large Language Model Agents
Chen Chen, Kim Young Il, Yuan Yang +7
Large language model (LLM) agents with extended autonomy unlock new capabilities, but also introduce heightened challenges for LLM safety. In particular, an LLM agent may pursue ob…
Beyond Max Tokens: Stealthy Resource Amplification via Tool Calling Chains in LLM Agents
Kaiyu Zhou, Yongsen Zheng, Yicheng He +5
The agent--tool interaction loop is a critical attack surface for modern Large Language Model (LLM) agents. Existing denial-of-service (DoS) attacks typically function at the user-…
Evaluating and Mitigating LLM-as-a-judge Bias in Communication Systems
Jiaxin Gao, Chen Chen, Yanwen Jia +3
Large Language Models (LLMs) are increasingly being used to autonomously evaluate the quality of content in communication systems, e.g., to assess responses in telecom customer sup…
Lethe: Purifying Backdoored Large Language Models with Knowledge Dilution
Chen Chen, Yuchen Sun, Jiaxin Gao +5
Large language models (LLMs) have seen significant advancements, achieving superior performance in various Natural Language Processing (NLP) tasks. However, they remain vulnerable…
LLMs Cannot Reliably Judge (Yet?): A Comprehensive Assessment on the Robustness of LLM-as-a-Judge
Songze Li, Chuokun Xu, Jiaying Wang +6
Large Language Models (LLMs) have demonstrated exceptional capabilities across diverse tasks, driving the development and widespread adoption of LLM-as-a-Judge systems for automate…
TrojanDam: Detection-Free Backdoor Defense in Federated Learning through Proactive Model Robustification utilizing OOD Data
Yanbo Dai, Songze Li, Zihan Gan +1
Federated learning (FL) systems allow decentralized data-owning clients to jointly train a global model through uploading their locally trained updates to a centralized server. The…
Megatron: Evasive Clean-Label Backdoor Attacks against Vision Transformer
Xueluan Gong, Bowei Tian, Meng Xue +3
Vision transformers have achieved impressive performance in various vision-related tasks, but their vulnerability to backdoor attacks is under-explored. A handful of existing works…
Neutralizing Backdoors through Information Conflicts for Large Language Models
Chen Chen, Yuchen Sun, Xueluan Gong +2
Large language models (LLMs) have seen significant advancements, achieving superior performance in various Natural Language Processing (NLP) tasks, from understanding to reasoning.…
Hidden Data Privacy Breaches in Federated Learning
Xueluan Gong, Yuji Wang, Shuaike Li +5
Federated Learning (FL) emerged as a paradigm for conducting machine learning across broad and decentralized datasets, promising enhanced privacy by obviating the need for direct d…
AI Safety Landscape for Large Language Models: Taxonomy, State-of-the-art, and Future Directions
Chen Chen, Xueluan Gong, Ziyao Liu +3
AI Safety is an emerging area of critical importance to the safe adoption and deployment of AI systems. With the rapid proliferation of AI and especially with the recent advancemen…
URVFL: Undetectable Data Reconstruction Attack on Vertical Federated Learning
Duanyi Yao, Songze Li, Xueluan Gong +2
Launching effective malicious attacks in VFL presents unique challenges: 1) Firstly, given the distributed nature of clients' data features and models, each client rigorously guard…