Abstract
Deep neural networks are susceptible to interference from deliberately crafted noise, which can lead to incorrect classification results. Existing approaches make less use of latent space information and conduct pixel-domain modification in the input space instead, which increases the computational cost and decreases the transferability. In this work, we propose an effective adversarial distribution searching-driven attack (ADSAttack) algorithm to generate adversarial examples against deep neural networks. ADSAttack introduces an affiliated network to search for potential distributions in image latent space for synthesizing adversarial examples. ADSAttack uses an edge-detection algorithm to locate low-level feature mapping in input space to sketch the minimum effective disturbed area. Experimental results demonstrate that ADSAttack achieves higher transferability, better imperceptible visualization, and faster generation speed compared to traditional algorithms. To generate 1000 adversarial examples, ADSAttack takes (Formula presented.) and, on average, achieves a success rate of (Formula presented.).
Original language | English |
---|---|
Article number | 816 |
Journal | Electronics |
Volume | 12 |
Issue number | 4 |
DOIs | |
Publication status | Published - Feb 2023 |
MoE publication type | A1 Journal article-refereed |
Funding
This research was funded by the National Natural Science Foundation of China under Grant 61972092 and the Collaborative Innovation Major Project of Zhengzhou (20XTZX06013).
Keywords
- adversarial attack
- adversarial distribution searching
- edge-detection algorithm
- latent space