Refusing Everything Looks Safe: Restoring the Benign Arm to Encoded-Prompt Evaluation

arXiv:2609.26176 · cs.CR, cs.AI · Submitted 2026-08-12 · Read on arXiv

cs.CR, cs.AI

Submitted: 2026-08-12

Updated: 2026-09-24

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Decode — 23× in this paper · explained in 2 episodes
• Benchmark — 18× in this paper · explained in 2 episodes
• Alignment — 6× in this paper · explained in 1 episode
• AUROC — 4× in this paper · explained in 2 episodes
• Accuracy — 3× in this paper · explained in 1 episode
• Robustness — 3× in this paper · explained in 5 episodes
• Core — 2× in this paper · explained in 2 episodes
• LLM judge — 2× in this paper · explained in 2 episodes
• Activation Steering — 1× in this paper · explained in 4 episodes
• Calibration — 1× in this paper · explained in 7 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Interpretability — 1× in this paper · explained in 15 episodes
• Steering — 1× in this paper · explained in 2 episodes
• Transformer — 1× in this paper · explained in 2 episodes

Sources

• The Llama 3 Herd of Models
• Mistral 7B
• Qwen2.5 Technical Report
• DUAL-Bench: Measuring Over-Refusal and Robustness in Vision-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
• Efficient Fuzzy PSI under One-Sided Assumptions
• Sealing the Audit-Runtime Gap for LLM Skills
• Token Composition: A Graph Based on EVM Logs