Showing cs.CRShow all
2 papers · 1 filter
cs.CR2026
RAISED: Self-Distillation for Robustness to Prompt Injection in LLM Agents
Mohamed Dhouib, Clement Elliker, Alexi Canesse +6
Tool-using language-model agents are vulnerable to indirect prompt injection because they must act on untrusted external content. Existing training-time defenses can reduce attack…
cs.CR2026
Activation Surgery: Jailbreaking White-box LLMs without Touching the Prompt
Maël Jenny, Jérémie Dentan, Sonia Vanier +1
Most jailbreak techniques for Large Language Models (LLMs) primarily rely on prompt modifications, including paraphrasing, obfuscation, or conversational strategies. Meanwhile, abl…