通过渐进自回归机制提升对抗样本生成能力与速度
PAR-AdvGAN: Improving Adversarial Attack Capability with Progressive Auto-Regression AdvGAN
- 采用渐进式自回归网络，分步生成更强对抗扰动
- 在Inception-v3上达335.5帧/秒，速度远超梯度类方法
- 适合需要高效高转移性攻击的防御测试场景
深度神经网络在多个领域表现优异，但易受对抗样本影响导致错误预测。生成对抗网络（GAN）可通过生成器与判别器的协同训练快速生成高质量对抗样本，相比传统方法具有更好迁移性。然而，现有方法通常仅单次迭代生成扰动，难以充分发挥潜力。为此，本文提出渐进自回归AdvGAN（PAR-AdvGAN），在渐进生成网络中引入自回归迭代机制，显著提升对抗样本的攻击能力。大规模实验表明，PAR-AdvGAN在多种主流黑盒攻击方法及原始AdvGAN上均表现更优。此外，其生成速度高达Inception-v3模型下335.5帧/秒，优于基于梯度的可迁移攻击算法。代码已开源。
原文摘要 · Abstract (English)
Deep neural networks have demonstrated remarkable performance across various domains. However, they are vulnerable to adversarial examples, which can lead to erroneous predictions. Generative Adversarial Networks (GANs) can leverage the generators and discriminators model to quickly produce high-quality adversarial examples. Since both modules train in a competitive and simultaneous manner, GAN-based algorithms like AdvGAN can generate adversarial examples with better transferability compared to traditional methods. However, the generation of perturbations is usually limited to a single iteration, preventing these examples from fully exploiting the potential of the methods. To tackle this issue, we introduce a novel approach named Progressive Auto-Regression AdvGAN (PAR-AdvGAN). It incorporates an auto-regressive iteration mechanism within a progressive generation network to craft adversarial examples with enhanced attack capability. We thoroughly evaluate our PAR-AdvGAN method with a large-scale experiment, demonstrating its superior performance over various state-of-the-art black-box adversarial attacks, as well as the original AdvGAN.Moreover, PAR-AdvGAN significantly accelerates the adversarial example generation, i.e., achieving the speeds of up to 335.5 frames per second on Inception-v3 model, outperforming the gradient-based transferable attack algorithms. Our code is available at: https://github.com/LMBTough/PAR
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。