Showing cs.CLShow all
2 papers · 1 filter
cs.CL2025
Semantic-Preserving Prompt Hijacking: A Black-Box Adversarial Attack on Auto-Prompt Optimization
Chong Zhang, Xiang Li, Jia Wang +3
LLMs increasingly integrate auto-suggestion optimization modules, enabling them to rewrite and display user input before generating the final response. While this design aims to en…
cs.CL2025
Efficient and Stealthy Jailbreak Attacks via Adversarial Prompt Distillation from LLMs to SLMs
Xiang Li, Chong Zhang, Jia Wang +3
Current jailbreak attacks on large language models (LLMs) predominantly rely on LLMs themselves to generate adversarial prompts, creating a critical efficiency bottleneck: each att…