arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2402.16430cs.CRcs.HC
收藏

利用XAI提升基于行为的身份认证对抗性攻击的能力

Improving behavior based authentication against adversarial attack using XAI

Dong Qin, George Amariucai, Daji Qiao, Yong Guan

AI总结:

针对基于行为的身份认证中攻击者复制对抗样本存在偏差的实际场景,提出基于XAI的特征选择过滤防御策略,经实验验证其防御效果优于对抗训练等现有方法。

摘要:

近年来,机器学习模型尤其是深度神经网络已被广泛应用于安全领域的分类任务。然而研究表明,这类模型易受对抗性操纵的影响:由对抗攻击模型习得的微小改动施加到输入上时,会导致输出出现显著变化。目前大多数关于对抗攻击及相应防御方法的研究,仅聚焦于攻击模型直接生成对抗样本的场景。本研究探讨了基于行为的身份认证中一个更具实际意义的场景:对抗样本由攻击者采集获取,攻击模型生成的对抗样本会被攻击者复制,且复制过程存在一定程度的偏差。我们提出了一种基于可解释人工智能(eXplainable AI, XAI)的防御策略,用于应对此类场景下的对抗攻击。通过我们的方法训练得到的特征选择器,可作为原始认证器前端的过滤器,它会过滤掉更易受对抗攻击影响或与身份认证无关的特征,同时保留鲁棒性更强的特征。通过综合实验我们证明,该基于XAI的防御策略能有效抵御对抗攻击,性能优于对抗训练、防御性蒸馏等其他防御策略。

英文摘要:

In recent years, machine learning models, especially deep neural networks, have been widely used for classification tasks in the security domain. However, these models have been shown to be vulnerable to adversarial manipulation: small changes learned by an adversarial attack model, when applied to the input, can cause significant changes in the output. Most research on adversarial attacks and corresponding defense methods focuses only on scenarios where adversarial samples are directly generated by the attack model. In this study, we explore a more practical scenario in behavior-based authentication, where adversarial samples are collected from the attacker. The generated adversarial samples from the model are replicated by attackers with a certain level of discrepancy. We propose an eXplainable AI (XAI) based defense strategy against adversarial attacks in such scenarios. A feature selector, trained with our method, can be used as a filter in front of the original authenticator. It filters out features that are more vulnerable to adversarial attacks or irrelevant to authentication, while retaining features that are more robust. Through comprehensive experiments, we demonstrate that our XAI based defense strategy is effective against adversarial attacks and outperforms other defense strategies, such as adversarial training and defensive distillation.

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。

↑