评估对抗鲁棒性：FGSM、Carlini-Wagner攻击的比较以及蒸馏作为防御机制的作用
Evaluating Adversarial Robustness: A Comparison Of FGSM, Carlini-Wagner Attacks, And The Role of Distillation as Defense Mechanism
- Praxis Tech School（普拉西斯科技学院）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本文针对图像分类DNN比较FGSM与CW攻击，并在CIFAR-10上评估以resnet101为教师、Resnext50_32x4d为学生的防御性蒸馏，证明其可抵御FGSM但仍难防CW。
AI中文摘要：
本技术报告深入探讨了专门针对用于图像分类的深度神经网络（DNN）的对抗性攻击。研究还调查了旨在增强机器学习模型鲁棒性的防御机制。研究重点是理解两种著名攻击方法的后果：快速梯度符号法（FGSM）和Carlini-Wagner（CW）方法。利用Tiny-ImageNet数据集，针对三个预训练图像分类器Resnext50_32x4d、DenseNet-201和VGG-19检验了这些攻击。此外，研究提出了防御性蒸馏作为抵御FGSM和CW攻击的防御机制的鲁棒性。该防御机制使用CIFAR-10数据集进行评估，其中CNN模型（具体为resnet101和Resnext50_32x4d）分别充当教师模型和学生模型。所提出的防御性蒸馏模型在挫败FGSM等攻击方面表现出有效性。然而，值得注意的是，它仍然容易受到CW攻击等更复杂技术的影响。本文对所提出的方案进行了细致验证，提供了详细全面的结果，阐明了所采用防御机制的功效和局限性。通过严格的实验和分析，研究深入洞察了针对DNN的对抗性攻击的动态变化，以及防御策略在减轻其影响方面的有效性。
英文摘要：
This technical report delves into an in-depth exploration of adversarial attacks specifically targeted at Deep Neural Networks (DNNs) utilized for image classification. The study also investigates defense mechanisms aimed at bolstering the robustness of machine learning models. The research focuses on comprehending the ramifications of two prominent attack methodologies: the Fast Gradient Sign Method (FGSM) and the Carlini-Wagner (CW) approach. These attacks are examined concerning three pre-trained image classifiers: Resnext50_32x4d, DenseNet-201, and VGG-19, utilizing the Tiny-ImageNet dataset. Furthermore, the study proposes the robustness of defensive distillation as a defense mechanism to counter FGSM and CW attacks. This defense mechanism is evaluated using the CIFAR-10 dataset, where CNN models, specifically resnet101 and Resnext50_32x4d, serve as the teacher and student models, respectively. The proposed defensive distillation model exhibits effectiveness in thwarting attacks such as FGSM. However, it is noted to remain susceptible to more sophisticated techniques like the CW attack. The document presents a meticulous validation of the proposed scheme. It provides detailed and comprehensive results, elucidating the efficacy and limitations of the defense mechanisms employed. Through rigorous experimentation and analysis, the study offers insights into the dynamics of adversarial attacks on DNNs, as well as the effectiveness of defensive strategies in mitigating their impact.
