WaveTransform: Crafting Adversarial Examples via Input Decomposition

Autor:	Anshumaan, Divyam, Agarwal, Akshay, Vatsa, Mayank, Singh, Richa
Rok vydání:	2020
Předmět:	Computer Science - Computer Vision and Pattern Recognition Computer Science - Artificial Intelligence Computer Science - Cryptography and Security
Druh dokumentu:	Working Paper
Popis:	Frequency spectrum has played a significant role in learning unique and discriminating features for object recognition. Both low and high frequency information present in images have been extracted and learnt by a host of representation learning techniques, including deep learning. Inspired by this observation, we introduce a novel class of adversarial attacks, namely `WaveTransform', that creates adversarial noise corresponding to low-frequency and high-frequency subbands, separately (or in combination). The frequency subbands are analyzed using wavelet decomposition; the subbands are corrupted and then used to construct an adversarial example. Experiments are performed using multiple databases and CNN models to establish the effectiveness of the proposed WaveTransform attack and analyze the importance of a particular frequency component. The robustness of the proposed attack is also evaluated through its transferability and resiliency against a recent adversarial defense algorithm. Experiments show that the proposed attack is effective against the defense algorithm and is also transferable across CNNs. Comment: ECCV Workshop Adversarial Robustness in the Real World 2020, 17 pages, 3 Tables, 6 Figures
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2010.15773 Zobrazit plný text záznamu View this record from Arxiv