Beyond AUROC: Deployment-Aware Evaluation of Model-Internal Jailbreak Detectors
cs.CR, cs.CL
Submitted: 2026-11-08
Updated: 2026-11-08
Code: https://github.com/Mtehabsim/internal-detector-sensititvity
Terminology
Sources
- Is DPO Superior to PPO for LLM Alignment? A Comprehensive Study
- Universal and Transferable Adversarial Attacks on Aligned Language Models
- Detecting Language Model Attacks with Perplexity
- Baseline Defenses for Adversarial Attacks Against Aligned Language Models
- Llama 2: Open Foundation and Fine-Tuned Chat Models
- The Llama 3 Herd of Models
- Mistral 7B
- Low-Resource Languages Jailbreak GPT-4
- JAILJUDGE: A Comprehensive Jailbreak Judge Benchmark with Multi-Agent Enhanced Explanation Evaluation Framework
- Constitutional Classifiers++: Efficient Production-Grade Defenses against Universal Jailbreaks
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