arXiv AI By Jithin VG, Ditto PS

Compute-Bounded Security Assurance - Coverage, Verification, and Response under Resource Constraints

Read the original on arXiv AI →

The paper introduces a resource‑constrained framework that distinguishes between repeated success, unique coverage, accepted evidence, and operational protection in security assurance tasks. It derives formulas for coverage under repeated, conditionally independent attempts, shows that pairwise outcome correlation does not necessarily limit coverage, and links coverage to evidence checking, scoring, resource accounting, and response modeling. The authors propose a defensive architecture separating evidence analysis, adjudication, and operational authority, and outline an evaluation protocol with held‑out tasks and uncertainty reporting.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv Machine Learning
Nov 2

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

The paper critiques current LLM safety evaluations that rely solely on severity taxonomies, arguing they ignore the probability that a threat will actually be executed. It introduces Expected Harm, a metric that multiplies severity by execution likelihood—modeled via execution cost—to better gauge real-world risk. Empirical studies show that models over‑refuse low‑likelihood, high‑cost threats while remaining vulnerable to high‑likelihood, low‑cost ones, a miscalibration traced to the distribution of safety examples in supervised fine‑tuning. This misalignment can be exploited to double the success rate of jailbreak attacks.

By Yen-Shan Chen, Zhi Rui Tam, Cheng-Kuang Wu, Yun-Nung Chen