提出HALO方法，提升模型在对抗攻击下的异常检测鲁棒性。
HALO: Robust Out-of-Distribution Detection via Joint Optimisation
- 基于TRADES框架改进，引入新损失函数增强抗干扰能力。
- 干净数据下平均AUROC提升3.15，对抗攻击下提升7.07。
- 兼容现有框架，可调参数且对迁移攻击有抵抗性。
有效的分布外（OOD）检测对机器学习模型在真实场景中的安全部署至关重要。然而，近期研究发现现有方法易受对抗攻击影响，可能导致高风险应用中的严重故障。为此，本文提出一种基于辅助信息的对抗鲁棒OOD检测方法HALO，通过扩展已有鲁棒分类框架TRADES，设计新的目标函数。考虑到干净与鲁棒性能之间的平衡至关重要，引入额外损失项以同时提升分类与检测表现。实验表明，相比当前最优方法，HALO在多个数据集和攻击设置下均达到最新水平：干净环境下平均AUROC提升3.15，对抗攻击下提升7.07。此外，HALO具备对迁移攻击的抵抗力，可通过超参数调节性能，并可无缝集成至现有OOD检测框架中，为未来性能提升留出空间。代码已开源。
原文摘要 · Abstract (English)
Effective out-of-distribution (OOD) detection is crucial for the safe deployment of machine learning models in real-world scenarios. However, recent work has shown that OOD detection methods are vulnerable to adversarial attacks, potentially leading to critical failures in high-stakes applications. This discovery has motivated work on robust OOD detection methods that are capable of maintaining performance under various attack settings. Prior approaches have made progress on this problem but face a number of limitations: often only exhibiting robustness to attacks on OOD data or failing to maintain strong clean performance. In this work, we adapt an existing robust classification framework, TRADES, extending it to the problem of robust OOD detection and discovering a novel objective function. Recognising the critical importance of a strong clean/robust trade-off for OOD detection, we introduce an additional loss term which boosts classification and detection performance. Our approach, called HALO (Helper-based AdversariaL OOD detection), surpasses existing methods and achieves state-of-the-art performance across a number of datasets and attack settings. Extensive experiments demonstrate an average AUROC improvement of 3.15 in clean settings and 7.07 under adversarial attacks when compared to the next best method. Furthermore, HALO exhibits resistance to transferred attacks, offers tuneable performance through hyperparameter selection, and is compatible with existing OOD detection frameworks out-of-the-box, leaving open the possibility of future performance gains. Code is available at: https://github.com/hugo0076/HALO
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。