arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2510.13992cs.SEcs.LG
收藏

代码后门检测中的签名方法:我们进展如何?

Optimizing Spectral Signature in Code Backdoor Detection

North Carolina State University(北卡罗来纳州立大学);The University of Melbourne(墨尔本大学)

Quoc Hung Le, Thanh Le-Cong, Bach Le, Bowen Xu

AI总结:

本文重新评估谱签名防御在代码模型后门检测中的有效性,发现常用设置并非最优,并提出一种无需重训即可准确估计其性能的新代理指标。

摘要:

随着大型语言模型(LLMs)日益融入软件开发工作流程,它们也成为对抗性攻击的主要目标。其中,后门攻击是一种重大威胁,攻击者通过嵌入训练数据中的隐藏触发器来操纵模型输出。检测此类后门仍然是一项挑战,一种有前景的方法是使用谱签名防御方法,该方法通过特征向量分析特征表示来识别中毒数据。虽然先前的一些工作已探索了将谱签名用于神经网络中的后门检测,但近期研究表明,这些方法可能对代码模型并非最优。在本文中,我们重新审视了基于谱签名的防御在代码模型后门攻击场景中的适用性。我们系统评估了其在各种攻击场景和防御配置下的有效性,分析了其优势与局限性。我们发现,谱签名在代码后门检测中的广泛使用设置往往不是最优的。因此,我们探索了关键因素不同设置的影响。我们发现了一个新的代理指标,该指标可以在防御后无需重新训练模型的情况下,更准确地估计谱签名的实际性能。

英文摘要:

As Large Language Models (LLMs) are increasingly integrated into software development workflows, they also become prime targets for adversarial attacks. Among these, backdoor attacks are a significant threat, allowing attackers to manipulate model outputs through hidden triggers embedded in training data. Detecting such backdoors remains a challenge, and one promising approach is the use of Spectral Signature defense methods that identify poisoned data by analyzing feature representations through eigenvectors. While some prior works have explored Spectral Signatures for backdoor detection in neural networks, recent studies suggest that these methods may not be optimally effective for code models. In this paper, we revisit the applicability of Spectral Signature-based defenses in the context of backdoor attacks on code models. We systematically evaluate their effectiveness under various attack scenarios and defense configurations, analyzing their strengths and limitations. We found that the widely used setting of Spectral Signature in code backdoor detection is often suboptimal. Hence, we explored the impact of different settings of the key factors. We discovered a new proxy metric that can more accurately estimate the actual performance of Spectral Signature without model retraining after the defense. Our findings contribute to a deeper understanding of the configurations of Spectral Signature defenses in securing code models and offer insights into potential improvements for future research.

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。

↑