Skip to content

GRAPHITE: Generating Automatic Physical Examples for Machine-Learning Attacks on Computer Vision Systems

GRAPHITE: Generating Automatic Physical Examples for Machine-Learning Attacks on Computer Vision Systems

arXiv· arXiv:2002.07088· EuroS&P 2022· Ryan Feng, Neal Mangaokar, Jiefeng Chen, Earlence Fernandes, Somesh Jha, Atul PrakashUniversity of Michigan, Ann Arbor; University of Wisconsin, MadisonIndexed by this site · 23 days ago· Originally publishedAttacks

Translation in progress — untranslated text is omitted.

Quick read

Attacks

Based on the paper PDF (AI-generated); refer to the original

AI summaryThe researchers propose the GRAPHITE framework, which can automatically generate physical adversarial examples that can be made into stickers and attack computer vision models in black-box hard-label settings. The method is based on a transform-robustness metric that takes the expectation over transformations, automatically generates small-size masks and solves them with gradient-free optimization, and can trade off among transform robustness, perturbation size and number of queries. In the hard-label black-box setting on the GTSRB model, the authors claim to have found attacks for all 1,806 victim-target class pairs, with an average transform robustness of 77.8%, perturbations accounting for 16.63% of the victim image, and about 126K queries per pair. With digital attacks only, 92.2% of class pairs can be attacked with small-size patches using an average of 566 queries. The paper also claims that perturbations modifying a small region of the image can break the PatchGuard defense against patch attacks.

Questions
Real-world adversarial attacks must simultaneously satisfy three points: automatically restricting the perturbation region so it can be made into a sticker, robustness to physical transformations such as viewpoint and lighting, and working under a hard-label black-box setting where only the top-1 label is available; the authors state that existing methods cannot satisfy all three simultaneously.
Methods
The authors propose GRAPHITE: it formulates mask size and transform-robustness (EoT) as a joint optimization; the white-box version extends C&W l0 with EoT PGD; the black-box version splits into two steps: mask generation (heatmap estimation + coarse/fine-grained reduction) and RGF perturbation boosting.
Experiments and results
Average 77.8% transform-robustness, mask 16.63%, and 126K queries over all 1,806 victim-target pairs in GTSRB; physical sticker and drive-by test success rate up to 97.5%; average 68% TR for attacks on the PatchGuard-defended CIFAR-10 model.
Limitations and future work
The authors point out that gamma correction struggles to simulate sunlight glare and printing errors (especially blue), and that the Turn Left Ahead physical attack has only 0% outdoor success rate; in-depth evaluation of defenses, adversarial training, and the feasibility of query detection defenses are all left for future work.

Related papers

Show 3 more papers
Read originalEuroS&P 2022