1 citations · 2 across the 20 of their papers we have counts for
9 papers · 1 filter
What Your Posts Reveal: A Benchmark and Agentic Framework for User-Level Privacy Leakage on Social Media
Zifan Peng, Yini Huang, Aiwen Lu +7
Public social media posts can reveal private information through weak cues scattered across text, images, or metadata. Such leakage is often cumulative and cross-post: cues that ap…
"To Survive, I Must Defect": Jailbreaking LLMs via the Game-Theory Scenarios
Zhen Sun, Zongmin Zhang, Deqi Liang +8
As LLMs become more common, non-expert users can pose risks, prompting extensive research into jailbreak attacks. However, most existing black-box jailbreak attacks rely on hand-cr…
Auditing Data Membership in Reinforcement Learning With Verifiable Rewards
Yule Liu, Heyi Zhang, Jinyi Zheng +6
Reinforcement Learning with Verifiable Rewards (RLVR) has become a core training stage in recent large language models (LLMs). Its reliance on non-public, high-value prompt sets ra…
JALMBench: Benchmarking Jailbreak Vulnerabilities in Audio Language Models
Zifan Peng, Yule Liu, Zhen Sun +9
Large Audio Language Models (LALMs) have made significant progress. While increasingly deployed in real-world applications, LALMs face growing safety risks from jailbreak attacks t…
TH-Bench: Evaluating Evading Attacks via Humanizing AI Text on Machine-Generated Text Detectors
Jingyi Zheng, Junfeng Wang, Zhen Sun +3
As Large Language Models (LLMs) advance, Machine-Generated Texts (MGTs) have become increasingly fluent, high-quality, and informative. Existing wide-range MGT detectors are design…
SoK: Benchmarking Poisoning Attacks and Defenses in Federated Learning
Heyi Zhang, Yule Liu, Xinlei He +3
Federated learning (FL) enables collaborative model training while preserving data privacy, but its decentralized nature exposes it to client-side data poisoning attacks (DPAs) and…
Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search
Zeren Luo, Zifan Peng, Yule Liu +4
Recent advancements in Large Language Models (LLMs) have significantly enhanced the capabilities of AI-Powered Search Engines (AIPSEs), offering precise and efficient responses by…
Privacy-Preserving Federated Learning via Homomorphic Adversarial Networks
Wenhan Dong, Chao Lin, Xinlei He +2
Privacy-preserving federated learning (PPFL) aims to train a global model for multiple clients while maintaining their data privacy. However, current PPFL protocols exhibit one or…
Quantized Delta Weight Is Safety Keeper
Yule Liu, Zhen Sun, Xinlei He +1
Recent advancements in fine-tuning proprietary language models enable customized applications across various domains but also introduce two major challenges: high resource demands…