通过差异嵌入提升安卓恶意软件检测抗攻击能力
DeepTrust: Multi-Step Classification through Dissimilar Adversarial Representations for Robust Android Malware Detection
- 多阶段分类器级联，各模型学习不同数据表示
- 对抗攻击下准确率领先第二名266%，误报率低于1%
- 适合需要高鲁棒性的安卓安全检测场景
过去十年中，机器学习被广泛用于识别恶意安卓应用。然而，这些方法对对抗样本仍显脆弱，即经过细微扰动的输入可能诱使模型做出错误判断。本文提出DeepTrust，一种新型元启发式方法，将深度神经网络等灵活分类器按序排列，最终决策由单个内部模型基于级联触发条件作出。在2025年IEEE SaTML会议的鲁棒安卓恶意软件检测竞赛中，DeepTrust荣获第一名，于特征空间逃避攻击下表现超越次优方案达266%。同时，在非对抗样本上保持最高检出率，误报率低于1%。该方法有效性源于最大化内部模型间学习表征的差异性。通过使分类器生成根本不同的数据嵌入，决策空间对攻击者变得不可预测，阻碍了逃避攻击中迭代扰动过程，从而在不牺牲干净样本准确率的前提下显著增强系统鲁棒性。
原文摘要 · Abstract (English)
Over the last decade, machine learning has been extensively applied to identify malicious Android applications. However, such approaches remain vulnerable against adversarial examples, i.e., examples that are subtly manipulated to fool a machine learning model into making incorrect predictions. This research presents DeepTrust, a novel metaheuristic that arranges flexible classifiers, like deep neural networks, into an ordered sequence where the final decision is made by a single internal model based on conditions activated in cascade. In the Robust Android Malware Detection competition at the 2025 IEEE Conference SaTML, DeepTrust secured the first place and achieved state-of-the-art results, outperforming the next-best competitor by up to 266% under feature-space evasion attacks. This is accomplished while maintaining the highest detection rate on non-adversarial malware and a false positive rate below 1%. The method's efficacy stems from maximizing the divergence of the learned representations among the internal models. By using classifiers inducing fundamentally dissimilar embeddings of the data, the decision space becomes unpredictable for an attacker. This frustrates the iterative perturbation process inherent to evasion attacks, enhancing system robustness without compromising accuracy on clean examples.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。