paper-with-me

Papers

Generative Dynamic Patch Attack

2021-11-08 · Xiang Li, Shihao Ji

Adversarial patch attack is a family of attack algorithms that perturb a part of image to fool a deep neural network model. Existing patch attacks mostly consider injecting adversarial patches at input-agnostic locations: either a predefined location or a random location. This attack setup may be sufficient for attack but has considerable limitations when using it for adversarial training. Thus, robust models trained with existing patch attacks cannot effectively defend other adversarial attacks. In this paper, we first propose an end-to-end patch attack algorithm, Generative Dynamic Patch Attack (GDPA), which generates both patch pattern and patch location adversarially for each input image. We show that GDPA is a generic attack framework that can produce dynamic/static and visible/invisible patches with a few configuration changes. Secondly, GDPA can be readily integrated for adversarial training to improve model robustness to various adversarial attacks. Extensive experiments on VGGFace, Traffic Sign and ImageNet show that GDPA achieves higher attack success rates than state-of-the-art patch attacks, while adversarially trained model with GDPA demonstrates superior robustness to adversarial patch attacks than competing methods. Our source code can be found at https://github.com/lxuniverse/gdpa.

📄 PDF Abstract BibTeX arXiv:2111.04266

Code (1)

lxuniverse/gdpa 공식 구현 pytorch

Similar Papers 제목 키워드 기반

Rethinking Model Inversion Attacks With Patch-Wise Reconstruction

2023-12-12 · Jonggyu Jang, Hyeonsu Lyu, Hyun Jong Yang

Model inversion (MI) attacks aim to infer or reconstruct the training dataset through reverse-engineering from the target model's weights. Recently, significant advancements in generative models have enabled MI attacks t…

Generative Adversarial Network

Leveraging Local Patch Differences in Multi-Object Scenes for Generative Adversarial Attacks

2022-09-20 · Abhishek Aich, Shasha Li, Chengyu Song, M. Salman Asif 외

State-of-the-art generative model-based attacks against image classifiers overwhelmingly focus on single-object (i.e., single dominant object) images. Different from such settings, we tackle a more practical problem of g…

Object

DisPatch: Disarming Adversarial Patches in Object Detection with Diffusion Models

2025-09-04 · Jin Ma, Mohammed Aldeen, Christopher Salas, Feng Luo 외 arxiv

Object detection is fundamental to various real-world applications, such as security monitoring and surveillance video analysis. Despite their advancements, state-of-the-art object detectors are still vulnerable to adver…

Object Detection

DAP: A Dynamic Adversarial Patch for Evading Person Detectors

2023-05-19 · CVPR 2024 1 · Amira Guesmi, Ruitian Ding, Muhammad Abdullah Hanif, Ihsen Alouani 외

Patch-based adversarial attacks were proven to compromise the robustness and reliability of computer vision systems. However, their conspicuous and easily detectable nature challenge their practicality in real-world sett…

Dynamic Adversarial Patch for Evading Object Detection Models

2020-10-25 · Shahar Hoory, Tzvika Shapira, Asaf Shabtai, Yuval Elovici

Recent research shows that neural networks models used for computer vision (e.g., YOLO and Fast R-CNN) are vulnerable to adversarial evasion attacks. Most of the existing real-world adversarial attacks against object det…

Objectobject-detectionObject DetectionPosition