Generating Adversarial Samples in Mini-Batches May Be Detrimental To Adversarial Robustness

March 30, 2023 ยท Declared Dead ยท ๐Ÿ› 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

๐Ÿ‘ป CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors Timothy Redgrave, Colton Crum arXiv ID 2303.17720 Category cs.LG: Machine Learning Cross-listed cs.CR, cs.CV Citations 1 Venue 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) Last Checked 4 months ago
Abstract
Neural networks have been proven to be both highly effective within computer vision, and highly vulnerable to adversarial attacks. Consequently, as the use of neural networks increases due to their unrivaled performance, so too does the threat posed by adversarial attacks. In this work, we build towards addressing the challenge of adversarial robustness by exploring the relationship between the mini-batch size used during adversarial sample generation and the strength of the adversarial samples produced. We demonstrate that an increase in mini-batch size results in a decrease in the efficacy of the samples produced, and we draw connections between these observations and the phenomenon of vanishing gradients. Next, we formulate loss functions such that adversarial sample strength is not degraded by mini-batch size. Our findings highlight a potential risk for underestimating the true (practical) strength of adversarial attacks, and a risk of overestimating a model's robustness. We share our codes to let others replicate our experiments and to facilitate further exploration of the connections between batch size and adversarial sample strength.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

๐Ÿ“œ Similar Papers

In the same crypt โ€” Machine Learning

Died the same way โ€” ๐Ÿ‘ป Ghosted