PAR-AdvGAN: Improving Adversarial Attack Capability with Progressive Auto-Regression AdvGAN

2025-02-16 · Jiayu Zhang, Zhiyu Zhu, Xinyi Wang, Silin Liao, Zhibo Jin, Flora D. Salim, Huaming Chen

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://anonymous.4open.science/r/PAR-01BF/

📄 PDF Abstract BibTeX arXiv:2502.12207

Code (0)

등록된 구현이 없습니다.

Tasks

Adversarial Attack regression

Methods 이 논문이 사용한 방법론

Average Pooling 설명 없음

Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…

Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…

Max Pooling Max Pooling is a pooling operation that calculates the maximum value for patches of a feature map, and uses it to create a downsampled (pooled) feature map. It is usually…

Auxiliary Classifier Auxiliary Classifiers are type of architectural component that seek to improve the convergence of very deep networks. They are classifier heads we attach to layers before the…

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…

Enhancing Transferability of Adversarial Attacks with GE-AdvGAN+: A Comprehensive Framework for Gradient Editing

2024-08-22 · Zhibo Jin, Jiayu Zhang, Zhiyu Zhu, Yuchen Zhang 외

Transferable adversarial attacks pose significant threats to deep neural networks, particularly in black-box scenarios where internal model information is inaccessible. Studying adversarial attack methods helps advance t…

Adversarial Attack Computational Efficiency Edge-computing

NODE-AdvGAN: Improving the transferability and perceptual similarity of adversarial examples by dynamic-system-driven adversarial generative model

2024-12-04 · Xinheng Xie, Yue Wu, Cuiyu He

Understanding adversarial examples is crucial for improving the model's robustness, as they introduce imperceptible perturbations that deceive models. Effective adversarial examples, therefore, offer the potential to tra…

GE-AdvGAN: Improving the transferability of adversarial samples by gradient editing-based adversarial generative model

2024-01-11 · Zhiyu Zhu, Huaming Chen, Xinyi Wang, Jiayu Zhang 외

Adversarial generative models, such as Generative Adversarial Networks (GANs), are widely applied for generating various types of data, i.e., images, text, and audio. Accordingly, its promising performance has led to the…

Adversarial Attack

AdvGAN++ : Harnessing latent layers for adversary generation

2019-08-02 · Puneet Mangla, Surgan Jandial, Sakshi Varshney, Vineeth N. Balasubramanian

Adversarial examples are fabricated examples, indistinguishable from the original image that mislead neural networks and drastically lower their performance. Recently proposed AdvGAN, a GAN based approach, takes input im…

Cycle-Consistent Adversarial GAN: the integration of adversarial attack and defense

2019-04-12 · Lingyun Jiang, Kai Qiao, Ruoxi Qin, Linyuan Wang 외

In image classification of deep learning, adversarial examples where inputs intended to add small magnitude perturbations may mislead deep neural networks (DNNs) to incorrect results, which means DNNs are vulnerable to t…

Adversarial Attack image-classification Image Classification