Enmo Safety: External, Non-invasive, Model-agnostic Oversight for Off-the-Shelf Language Models
cs.CR, cs.AI, cs.SE
Submitted: 2026-11-06
Updated: 2026-11-06
Code: https://github.com/rioryugen/enmo_safety
Terminology
Sources
- SafeEvolve: Harness-Policy Co-Evolution from Agent Experience for Safety Alignment
- On-Policy Self-Evolution via Failure Trajectories for Agentic Safety Alignment
- AgenticEval: Toward Agentic and Self-Evolving Safety Evaluation of Large Language Models
- Defending Against Indirect Prompt Injection Attacks With Spotlighting
- Enhancing Agent Safety Judgment: Controlled Benchmark Rewriting and Analogical Reasoning for Deceptive Out-of-Distribution Scenarios
- Think Twice Before You Act: Enhancing Agent Behavioral Safety with Thought Correction
- OpenSkillRisk: Benchmarking Agent Safety When Using Real-World Risky Third-Party Skills
- HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal
- Universal and Transferable Adversarial Attacks on Aligned Language Models
- JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models
- XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models
- AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents
- Jailbroken: How Does LLM Safety Training Fail?
Related papers
- From Strategy Search to Policy Learning: MCTS-Guided Adversarial Co-Evolution for LLM Safety Alignment
- Privacy Leakage from Recurrent State in LLM Inference
- Incrementally Verifiable Oracle Aided Computation
- Privilege and confidentiality in generative AI workflows
- BadMoE: Backdooring Mixture-of-Experts LLMs via Routing-Aware Triggers and Task-Underutilized Experts
- CoVault: Secure, Scalable Analytics of Personal Data