用预训练特征增强k-NN，实现抗对抗攻击的新型检测
Killing it with Zero-Shot: Adversarially Robust Novelty Detection
- 结合ImageNet预训练特征与k-NN算法提升鲁棒性
- 在多个基准上显著优于现有方法，对抗条件下表现更优
- 适合关注模型安全与未知样本检测的研究者
新颖性检测（ND）在机器学习中至关重要，能识别推理阶段的未知数据，对自动化系统安全运行意义重大。尽管该领域已有进展，但现有方法在面对对抗攻击时性能往往下降。本文通过融合最近邻算法与ImageNet预训练模型获得的鲁棒特征，提升ND算法的鲁棒性与性能。实验表明，该方法在多个基准上显著超越当前最优技术，尤其在对抗环境下表现突出。通过将鲁棒预训练特征引入k-NN，本研究确立了鲁棒新颖性检测的新标准。代码已公开于https://github.com/rohban-lab/ZARND。
原文摘要 · Abstract (English)
Novelty Detection (ND) plays a crucial role in machine learning by identifying new or unseen data during model inference. This capability is especially important for the safe and reliable operation of automated systems. Despite advances in this field, existing techniques often fail to maintain their performance when subject to adversarial attacks. Our research addresses this gap by marrying the merits of nearest-neighbor algorithms with robust features obtained from models pretrained on ImageNet. We focus on enhancing the robustness and performance of ND algorithms. Experimental results demonstrate that our approach significantly outperforms current state-of-the-art methods across various benchmarks, particularly under adversarial conditions. By incorporating robust pretrained features into the k-NN algorithm, we establish a new standard for performance and robustness in the field of robust ND. This work opens up new avenues for research aimed at fortifying machine learning systems against adversarial vulnerabilities. Our implementation is publicly available at https://github.com/rohban-lab/ZARND.
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。