PaperScope
LIVE · 2026-09-03 05:40 UTC

Same Request, Different Boundary: Evaluating Cybersecurity Assistance across Conversational Contexts

Rui Yang, Yang Hong, Yichao Xu, Zhengyu Liu, Ziyang Li, Yinzhi Cao

Latestcs.CLcs.LGcs.AIcs.CV
arXiv ID
2609.00578 v1
Category
Submitted
2026-09-01

Abstract

Large Language Models (LLMs) can solve complex problems, but their misuse in high-risk domains can lead to severe consequences. Model providers therefore restrict assistance for potentially harmful requests. Refusing all cybersecurity requests would therefore harm legitimate users. Providers need a mechanism to block malicious use without denying legitimate assistance to defenders. Existing cybersecurity-specific datasets evaluate this mechanism, but none considers the conversational context of a request. We introduce 3R-Bench (Refusal, Repetition, and Revision), a benchmark of 150 real-world cybersecurity requests augmented with two adversarial conversational settings, and evaluate eight LLMs on it. Prior assistant behavior strongly changes responses to an unchanged request: among 376 available pairs from a 400-pair panel, compliance rises from 62.0% after refused history to 85.1% after accepted history. The opposite pattern appears under dialogue decomposition. In comparison, compliance falls from 501/800 direct responses to 172/800 after dialogue; among 738 pairs returning model-authored text in both conditions, the decrease is 45.1 points. Failure feedback recovers only a small fraction of this loss.

Comment: 14 pages, 7 figures

arXiv abs page · PDF · same-day batch