Seeing Through the Mask: Rethinking Adversarial Examples for CAPTCHAs
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913494083829760 |
|---|---|
| author | Jabary, Yahya Plesner, Andreas Kuzhagaliyev, Turlan Wattenhofer, Roger |
| author_facet | Jabary, Yahya Plesner, Andreas Kuzhagaliyev, Turlan Wattenhofer, Roger |
| contents | Modern CAPTCHAs rely heavily on vision tasks that are supposedly hard for computers but easy for humans. However, advances in image recognition models pose a significant threat to such CAPTCHAs. These models can easily be fooled by generating some well-hidden "random" noise and adding it to the image, or hiding objects in the image. However, these methods are model-specific and thus can not aid CAPTCHAs in fooling all models. We show in this work that by allowing for more significant changes to the images while preserving the semantic information and keeping it solvable by humans, we can fool many state-of-the-art models. Specifically, we demonstrate that by adding masks of various intensities the Accuracy @ 1 (Acc@1) drops by more than 50%-points for all models, and supposedly robust models such as vision transformers see an Acc@1 drop of 80%-points.
These masks can therefore effectively fool modern image classifiers, thus showing that machines have not caught up with humans -- yet. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_05558 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Seeing Through the Mask: Rethinking Adversarial Examples for CAPTCHAs Jabary, Yahya Plesner, Andreas Kuzhagaliyev, Turlan Wattenhofer, Roger Computer Vision and Pattern Recognition Artificial Intelligence Modern CAPTCHAs rely heavily on vision tasks that are supposedly hard for computers but easy for humans. However, advances in image recognition models pose a significant threat to such CAPTCHAs. These models can easily be fooled by generating some well-hidden "random" noise and adding it to the image, or hiding objects in the image. However, these methods are model-specific and thus can not aid CAPTCHAs in fooling all models. We show in this work that by allowing for more significant changes to the images while preserving the semantic information and keeping it solvable by humans, we can fool many state-of-the-art models. Specifically, we demonstrate that by adding masks of various intensities the Accuracy @ 1 (Acc@1) drops by more than 50%-points for all models, and supposedly robust models such as vision transformers see an Acc@1 drop of 80%-points. These masks can therefore effectively fool modern image classifiers, thus showing that machines have not caught up with humans -- yet. |
| title | Seeing Through the Mask: Rethinking Adversarial Examples for CAPTCHAs |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2409.05558 |