Protecting Your LLMs with Information Bottleneck

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

1. 1RIB-Guard: A Risk-Aware Information Bottleneck Defense for Black-Box Large Language Models2026
2. 2Defensive Prompt Patch: A Robust and Interpretable Defense of LLMs against Jailbreak Attacks2024 · 3 citations
3. 3Defending Large Language Models Against Jailbreak Attacks via Layer-specific Editing2024
4. 4Defending LLMs against Jailbreaking Attacks via Backtranslation2024
5. 5LLM Jailbreak Attack versus Defense Techniques -- A Comprehensive Study2024 · 12 citations