5 papers
Why Are LLM Backdoor Defenses Fragmented? A Feature-Level Explanation with Sparse Autoencoders
Yizhe Zeng, Chenxu Niu, Wei Zhang +7
Backdoor attacks pose a serious threat to large language models (LLMs), but existing defenses remain fragmented, failing to pro?vide unified defense against both dirty-label and cl…
LARFT: Closing the Cognition-Action Gap for Length Instruction Following in Large Language Models
Wei Zhang, Lintong Du, Yuanhe Zhang +4
Despite the strong performance of Large Language Models (LLMs) on complex instruction-following tasks, precise control of output length remains a persistent challenge. Existing met…
Crabs: Consuming Resource via Auto-generation for LLM-DoS Attack under Black-box Settings
Yuanhe Zhang, Zhenhong Zhou, Wei Zhang +4
Large Language Models (LLMs) have demonstrated remarkable performance across diverse tasks yet still are vulnerable to external threats, particularly LLM Denial-of-Service (LLM-DoS…
Faster-GCG: Efficient Discrete Optimization Jailbreak Attacks against Aligned Large Language Models
Xiao Li, Wei Zhang, Zhuhong Li +6
Aligned Large Language Models (LLMs) have attracted significant attention for their safety, particularly in the context of jailbreak attacks that attempt to bypass guardrails via a…
Alignment-Enhanced Decoding:Defending via Token-Level Adaptive Refining of Probability Distributions
Quan Liu, Zhenhong Zhou, Longzhu He +3
Large language models are susceptible to jailbreak attacks, which can result in the generation of harmful content. While prior defenses mitigate these risks by perturbing or inspec…