Summary of Peas: a Strategy For Crafting Transferable Adversarial Examples, by Bar Avraham and Yisroel Mirsky
PEAS: A Strategy for Crafting Transferable Adversarial Examples
by Bar Avraham, Yisroel Mirsky
First submitted to arxiv on: 20 Oct 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI); Cryptography and Security (cs.CR)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper proposes a novel strategy called PEAS (Perceptually Equivalent Augmentations for Selecting) that can boost the transferability of existing black box attacks. The approach generates a set of images from an initial sample via subtle augmentations and evaluates the transferability of adversarial perturbations on these images using substitute models. The most transferable adversarial example is then selected for the attack. PEAS leverages the insight that samples which are perceptually equivalent exhibit significant variability in their adversarial transferability. The proposed method is evaluated on ImageNet and CIFAR-10, achieving a 2.5x improvement in attack success rates on average over current ranking methods. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper helps keep machine learning systems safe from bad guys who try to trick them. They come up with a new way to make these attacks work better. It’s like trying different ways to make a joke funny, and then picking the one that works best. This new method can make attacks twice as successful, which is important because it helps keep our machines safe. |
Keywords
» Artificial intelligence » Machine learning » Transferability
