Unrestricted Adversarial Attacks on ImageNet Competition
This work tackles the problem of improving model robustness against stronger unbounded attacks for AI security researchers, but it is incremental as it focuses on organizing a competition rather than proposing a new method.
The paper addresses the lack of thorough study on unrestricted adversarial attacks, where large visible modifications cause model misclassification without affecting human observation, by organizing a competition to explore more effective algorithms for such attacks on ImageNet.
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.