Diagnose Before You Refine: Multi-Dimensional Judge Feedback for Query-Efficient Jailbreak Attacks
cs.CR
Submitted: 2026-10-14
Updated: 2026-10-14
Comments: Under Review
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- Detecting Language Model Attacks with Perplexity
- Constitutional AI: Harmlessness from AI Feedback
- Just Ask Jev: Reinforcement Learning for Calibrated Decisions as a Zero-Shot Detector of AI Alignment Failures
- Mixtral of Experts
- JEV-as-a-Judge: Accept When Confident, Escalate When Unsure
- JAILJUDGE: A Comprehensive Jailbreak Judge Benchmark with Multi-Agent Enhanced Explanation Evaluation Framework
- Instruction Tuning with GPT-4
- JailbreakEval: An Integrated Toolkit for Evaluating Jailbreak Attempts Against Large Language Models
- A Coin Flip for Safety: LLM Judges Fail to Reliably Measure Adversarial Robustness
- One Leak Away: How Pretrained Model Exposure Amplifies Jailbreak Risks in Finetuned LLMs
- Gemma 2: Improving Open Language Models at a Practical Size
- The Llama 3 Herd of Models
- Llama 2: Open Foundation and Fine-Tuned Chat Models
- Baichuan 2: Open Large-scale Language Models
- Qwen2.5 Technical Report
- ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools
- Universal and Transferable Adversarial Attacks on Aligned Language Models
Related papers
- SoK: AI-Augmented Binary Reversing
- Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
- Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
- Estimating the Social Cost of Corporate Data Breaches
- Efficient Fuzzy PSI under One-Sided Assumptions
- Sealing the Audit-Runtime Gap for LLM Skills