Unrestricted Adversarial Attacks on ImageNet Competition
arXiv:2110.09903
Abstract
Many works have investigated the adversarial attacks or defenses under the settings where a bounded and imperceptible perturbation can be added to the input. However in the real-world, the attacker does not need to comply with this restriction. In fact, more threats to the deep model come from unrestricted adversarial examples, that is, the attacker makes large and visible modifications on the image, which causes the model classifying mistakenly, but does not affect the normal observation in human perspective. Unrestricted adversarial attack is a popular and practical direction but has not been studied thoroughly. We organize this competition with the purpose of exploring more effective unrestricted adversarial attack algorithm, so as to accelerate the academical research on the model robustness under stronger unbounded attacks. The competition is held on the TianChi platform (\url{https://tianchi.aliyun.com/competition/entrance/531853/introduction}) as one of the series of AI Security Challengers Program.
arXiv commentCVPR-2021 AIC Phase VI Track2: Unrestricted Adversarial Attacks on ImageNet
References in corpus (11)
- Towards Deep Learning Models Resistant to Adversarial Attacks
- Learning Robust Global Representations by Penalizing Local Predictive Power
- Natural Adversarial Examples
- Improving Black-box Adversarial Attacks with a Transfer-based Prior
- Understanding and Enhancing the Transferability of Adversarial Examples
- APE-GAN: Adversarial Perturbation Elimination with GAN
- Unrestricted Adversarial Examples via Semantic Manipulation
- Watch out! Motion is Blurring the Vision of Your Deep Neural Networks
- RepVGG: Making VGG-style ConvNets Great Again
- Should Adversarial Attacks Use Pixel p-Norm?
- Improving Adversarial Transferability with Gradient Refining