Superclass Adversarial Attack
Adversarial attacks have only focused on changing the predictions of the classifier, but their danger greatly depends on how the class is mistaken. For example, when an automatic driving system mistakes a Persian cat for a Siamese cat, it is hardly a problem. However, if it mistakes a cat for a 120km/h minimum speed sign, serious problems can arise. As a stepping stone to more threatening adversarial attacks, we consider the superclass adversarial attack, which causes misclassification of not only fine classes, but also superclasses. We conducted the first comprehensive analysis of superclass adversarial attacks (an existing and 19 new methods) in terms of accuracy, speed, and stability, and identified several strategies to achieve better performance. Although this study is aimed at superclass misclassification, the findings can be applied to other problem settings involving multiple classes, such as top-k and multi-label classification attacks.
Code (0)
등록된 구현이 없습니다.
Tasks
Adversarial AttackMulti-Label ClassificationMUlTI-LABEL-ClASSIFICATIONMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Hierarchically Robust Zero-shot Vision-language Models
Vision-Language Models (VLMs) can perform zero-shot classification but are susceptible to adversarial attacks. While robust fine-tuning improves their robustness, existing approaches align fixed text embeddings with an i…
Adversarial RobustnessSample Complexity Bounds for Robustly Learning Decision Lists against Evasion Attacks
A fundamental problem in adversarial machine learning is to quantify how much training data is needed in the presence of evasion attacks. In this paper we address this issue within the framework of PAC learning, focusing…
PAC learningSuperclass Learning With Representation Enhancement
In many real scenarios, data are often divided into a handful of artificial super categories in terms of expert knowledge rather than the representations of images. Concretely, a superclass may contain massive and va…
Classification Done Right for Vision-Language Pre-Training
We introduce SuperClass, a super simple classification method for vision-language pre-training on image-text data. Unlike its contrastive counterpart CLIP who contrast with a text encoder, SuperClass directly utilizes to…
ClassificationWhat can we learn from misclassified ImageNet images?
Understanding the patterns of misclassified ImageNet images is particularly important, as it could guide us to design deep neural networks (DNN) that generalize better. However, the richness of ImageNet imposes difficult…
GPUQuantization