Scholarlink

Adversarial attacks present a significant challenge in artificial intelligence (AI) and deep learning by subtly altering input data to cause misclassification or incorrect outputs. These attacks manipulate input data in ways imperceptible to humans, tricking even the state-of-the-art models into making errors. This vulnerability affects many AI applications, including image recognition, natural language processing, and autonomous driving. To counter these threats, researchers are developing methods to improve the robustness and reliability of AI systems. This study proposes AYO-GAN, an adversarial attack method utilizing a Generative Adversarial Network to generate perturbations designed to deceive object detection models. The goal is to evaluate the model’s robustness against such attacks. Experimental results on the COCO dataset show average Structural Similarity Index (SSIM) of 0.936 and average Attack Success Rate (ASR) of \(22.25\%\) , surpassing Xiao et al.’s the best SSIM of 0.842 and average ASR of \(12.67\%\) .

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

AYO-GAN: A Novel GAN-Based Adversarial Attack on YOLO Object Detection Models

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Phi Ho Truong,
  • Ngoc Minh Pham,
  • Duy Trung Pham,
  • Nhat Hai Nguyen

摘要

Adversarial attacks present a significant challenge in artificial intelligence (AI) and deep learning by subtly altering input data to cause misclassification or incorrect outputs. These attacks manipulate input data in ways imperceptible to humans, tricking even the state-of-the-art models into making errors. This vulnerability affects many AI applications, including image recognition, natural language processing, and autonomous driving. To counter these threats, researchers are developing methods to improve the robustness and reliability of AI systems. This study proposes AYO-GAN, an adversarial attack method utilizing a Generative Adversarial Network to generate perturbations designed to deceive object detection models. The goal is to evaluate the model’s robustness against such attacks. Experimental results on the COCO dataset show average Structural Similarity Index (SSIM) of 0.936 and average Attack Success Rate (ASR) of \(22.25\%\) , surpassing Xiao et al.’s the best SSIM of 0.842 and average ASR of \(12.67\%\) .