用51维特征检测对抗样本，兼具高精度与可解释性
FeatureLens: A Highly Generalizable and Interpretable Framework for Detecting Adversarial Examples Based on Image Features
- 通过提取图像特征并用轻量分类器分析异常
- 闭集测试准确率97.8%~99.75%，泛化能力达86.17%~99.6%
- 适合需要透明防御的工业场景，支持多种攻击类型
尽管深度神经网络在图像分类中表现卓越，其对对抗攻击的脆弱性仍是重大挑战。现有检测方法多依赖复杂且难解释的架构，影响可解释性与泛化能力。为此，我们提出FeatureLens，一种轻量级框架，如同镜头般审视图像特征中的异常。该框架由图像特征提取器（IFE）与浅层分类器（如SVM、MLP或XGBoost）组成，模型参数量仅1,000至30,000，仅使用51维特征，在闭集评估中实现97.8%至99.75%的检测准确率，在通用性评估中对FGSM、PGD、CW和DAmageNet攻击的准确率达86.17%至99.6%。凭借强检测性能、优秀泛化性、可解释性与计算高效性，FeatureLens为实现透明且有效的对抗防御提供了实用路径。
原文摘要 · Abstract (English)
Although the remarkable performance of deep neural networks (DNNs) in image classification, their vulnerability to adversarial attacks remains a critical challenge. Most existing detection methods rely on complex and poorly interpretable architectures, which compromise interpretability and generalization. To address this, we propose FeatureLens, a lightweight framework that acts as a lens to scrutinize anomalies in image features. Comprising an Image Feature Extractor (IFE) and shallow classifiers (e.g., SVM, MLP, or XGBoost) with model sizes ranging from 1,000 to 30,000 parameters, FeatureLens achieves high detection accuracy ranging from 97.8% to 99.75% in closed-set evaluation and 86.17% to 99.6% in generalization evaluation across FGSM, PGD, CW, and DAmageNet attacks, using only 51 dimensional features. By combining strong detection performance with excellent generalization, interpretability, and computational efficiency, FeatureLens offers a practical pathway toward transparent and effective adversarial defense.
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。