Unrestricted Adversarial Examples via Semantic Manipulation
| Autor: | Bhattad, Anand, Chong, Min Jin, Liang, Kaizhao, Li, Bo, Forsyth, D. A. |
|---|---|
| Rok vydání: | 2019 |
| Předmět: | |
| Druh dokumentu: | Working Paper |
| Popis: | Machine learning models, especially deep neural networks (DNNs), have been shown to be vulnerable against adversarial examples which are carefully crafted samples with a small magnitude of the perturbation. Such adversarial perturbations are usually restricted by bounding their $\mathcal{L}_p$ norm such that they are imperceptible, and thus many current defenses can exploit this property to reduce their adversarial impact. In this paper, we instead introduce "unrestricted" perturbations that manipulate semantically meaningful image-based visual descriptors - color and texture - in order to generate effective and photorealistic adversarial examples. We show that these semantically aware perturbations are effective against JPEG compression, feature squeezing and adversarially trained model. We also show that the proposed methods can effectively be applied to both image classification and image captioning tasks on complex datasets such as ImageNet and MSCOCO. In addition, we conduct comprehensive user studies to show that our generated semantic adversarial examples are photorealistic to humans despite large magnitude perturbations when compared to other attacks. Comment: Accepted to ICLR 2020. First two authors contributed equally. Code: https://github.com/aisecure/Big-but-Invisible-Adversarial-Attack and Openreview: https://openreview.net/forum?id=Sye_OgHFwH |
| Databáze: | arXiv |
| Externí odkaz: |
|