Boosting Decision-Based Black-Box Adversarial Attacks with Random Sign Flip

By Weilun Chen, Zhaoxiang Zhang, Xiaolin Hu, Baoyuan Wu. 2020

78 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Safety, Robustness & Interpretability

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Yujiu Yang
2. Zhifeng Li
3. Yanbo Fan
4. Yong Zhang
5. Baoyuan Wu
6. Bolei Zhou
7. Ming-Hsuan Yang
8. Jing-Hao Xue

In Safety, Robustness & Interpretability

1. Baoyuan Wu
2. Bolei Zhou
3. Ming-Hsuan Yang
4. Zhifeng Li
5. Yanbo Fan
6. Yong Zhang

Citations in the corpus

• GAN Inversion: A Survey (2021, methodology): “Adversarial attack methods [148], [149], [150], [151] aim at fooling a CNN classifier by adding a certain perturbation ∆x to a target image x.”
• A survey of algorithmic recourse: definitions, formulations, solutions, and prospects (2020, neutral): “[41, 86]).”
• Sparse Adversarial Attack via Perturbation Factorization (2020, methodology): “However, the 100% ASR values of C&W-(cid:96) 0 and our method tell that the above adversarial training is still not robust enough to defend the sparse attack.”