arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2604.17014cs.CR
收藏

良性大语言模型代码生成中的虚假安全信心

False Security Confidence in Benign LLM Code Generation

Macau University of Science and Technology(澳门科技大学)

Xiaolei Ren

AI总结:

本文研究在无攻击场景下,功能正确但存在安全漏洞的代码生成现象,提出FSC率作为衡量指标,并定义FSC-hard作为新的评估层次。

摘要:

先前研究显示,在威胁导向的环境中,功能正确但存在漏洞的输出系统性出现,通过对抗性或隐含渠道诱导安全失败。本文引入虚假安全信心(FSC)概念,从测量优先的角度研究普通非攻击框架下的生成任务。关注在无显性攻击压力下此类输出出现的频率和形式,以及传统功能评估是否能可靠检测。FSC率定义为功能正确输出中安全故障的普及率,区分了之前联合功能-安全指标如SAFE和基于结果的评估框架如CWEval。定义了三个生态系统任务视角研究FSC在通用编程、部署任务和安全显式编程中的表现,并将FSC-hard定义为一个实际重要的细化层次,其中静态分析器遗漏的漏洞仍可动态触发。本文技术报告有意限定为框架声明而非完整实证论文:其目的是建立术语、测量边界和研究设计承诺,为后续大规模评估奠定基础。

英文摘要:

Prior work has demonstrated that functionally correct yet vulnerable outputs arise systematically in threat-oriented settings, where adversarial or implicit channels are used to induce security failures in code agents and automated patching workflows. This note introduces a complementary but distinct framing: False Security Confidence (FSC), which studies the same surface phenomenon from a measurement-first perspective in ordinary, non-attack-framed generation tasks. Our interest is not in whether attacks can produce such outputs, but in how frequently and in what forms they appear absent explicit attack pressure, and whether conventional functional evaluation reliably detects them. We formalize FSC rate as the prevalence of security failure within the set of functionally correct outputs, distinguish it from prior joint functional-security metrics such as SAFE and outcome-driven evaluation frameworks such as CWEval, define a three-ecosystem task view for studying how FSC manifests across general-purpose programming, deployment-context tasks, and security-explicit programming, and identify FSC-hard as a practically important refinement layer in which static analyzers miss vulnerabilities that remain dynamically triggerable. This technical report is intentionally scoped as a framework statement rather than a full empirical paper: its purpose is to establish terminology, measurement boundaries, and study design commitments for subsequent large-scale evaluation.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑