Ellipsoid Control: A White-List Jailbreak Defense via Benign Latent Modeling

Summary

Ellipsoid Control is a test-time jailbreak defense for large language models that takes a white-list approach instead of relying on collected harmful samples. It runs projected gradient descent to elicit refusal on arbitrary inputs, while an anisotropic ellipsoid fitted from abundant benign data constrains the update to limit distortion of the benign latent geometry. The authors report that across multiple LLMs, jailbreak attacks, benign tasks and safety-boundary evaluations, it improves safety while better preserving utility.

Topics

• Prompt injection and jailbreaks

Related items

• InfoImproving Fuzzy Robustness in LLM Safety with Automated Red TeamingSimilar attack · OpenAI Alignment Research Blog
• InfoBait: Mitigating Harmful Agentic Reinforcement Learning via Probing Reward FunctionSimilar attack · Arxiv (cs.CR + cs.CL + cs.LG)
• MediumAI SAST Finding: Path Traversal in OpenClaw via LLM Guardrail Bypass | Endor LabsSimilar attack · Endor Labs Blog
• InfoPOEM: Output-Relative Block-Sparse Attention for Long-Context PrefillingSimilar attack · Arxiv (cs.CR + cs.CL + cs.LG)
• InfoTERM: Target-Free Jailbreak Defense via Entropy-Guided Residual ModulationSimilar attack · Arxiv (cs.CR + cs.CL + cs.LG)