Defending Object Detectors against Patch Attacks with Out-of-Distribution Smoothing
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2022
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917858482585600 |
|---|---|
| author | Feng, Ryan Mangaokar, Neal Choi, Jihye Jha, Somesh Prakash, Atul |
| author_facet | Feng, Ryan Mangaokar, Neal Choi, Jihye Jha, Somesh Prakash, Atul |
| contents | Patch attacks against object detectors have been of recent interest due to their being physically realizable and more closely aligned with practical systems. In response to this threat, many new defenses have been proposed that train a patch segmenter model to detect and remove the patch before the image is passed to the downstream model. We unify these approaches with a flexible framework, OODSmoother, which characterizes the properties of approaches that aim to remove adversarial patches. This framework naturally guides us to design 1) a novel adaptive attack that breaks existing patch attack defenses on object detectors, and 2) a novel defense approach SemPrior that takes advantage of semantic priors. Our key insight behind SemPrior is that the existing machine learning-based patch detectors struggle to learn semantic priors and that explicitly incorporating them can improve performance. We find that SemPrior alone provides up to a 40% gain, or up to a 60% gain when combined with existing defenses. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2205_08989 |
| institution | arXiv |
| publishDate | 2022 |
| record_format | arxiv |
| spellingShingle | Defending Object Detectors against Patch Attacks with Out-of-Distribution Smoothing Feng, Ryan Mangaokar, Neal Choi, Jihye Jha, Somesh Prakash, Atul Machine Learning Cryptography and Security Computer Vision and Pattern Recognition Patch attacks against object detectors have been of recent interest due to their being physically realizable and more closely aligned with practical systems. In response to this threat, many new defenses have been proposed that train a patch segmenter model to detect and remove the patch before the image is passed to the downstream model. We unify these approaches with a flexible framework, OODSmoother, which characterizes the properties of approaches that aim to remove adversarial patches. This framework naturally guides us to design 1) a novel adaptive attack that breaks existing patch attack defenses on object detectors, and 2) a novel defense approach SemPrior that takes advantage of semantic priors. Our key insight behind SemPrior is that the existing machine learning-based patch detectors struggle to learn semantic priors and that explicitly incorporating them can improve performance. We find that SemPrior alone provides up to a 40% gain, or up to a 60% gain when combined with existing defenses. |
| title | Defending Object Detectors against Patch Attacks with Out-of-Distribution Smoothing |
| topic | Machine Learning Cryptography and Security Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2205.08989 |