Expected Harm: Rethinking Safety Evaluation of (Mis)Aligned LLMs

arXiv:2602.01600 · cs.CR, cs.CL, cs.CY, cs.LG · Submitted 2026-02-02 · Read on arXiv

cs.CR, cs.CL, cs.CY, cs.LG

Submitted: 2026-02-02

Updated: 2026-10-30

Terminology

• Calibration — 1× in this paper · explained in 9 episodes
• Latent Space — 1× in this paper · explained in 7 episodes
• Linear Probing — 1× in this paper · explained in 3 episodes
• Trace — 1× in this paper · explained in 2 episodes

Related papers

• WADBERT: Dual-Channel Web Attack Detection via Permutation-Invariant Parameter Modeling
• Your Token Is Gone: A Token-Consumption Countermeasure for Disrupting LLM-Based Scam Systems
• Membership Inference Attack on Private Evolution
• Rank Ceiling for Twiddle-Perturbation Faults on the Forward NTT
• WebAgentGuard: A Reasoning-Driven Guard Model for Detecting Prompt Injection Attacks in Web Agents
• SoK: AI-Augmented Binary Reversing