Exploiting Alpha Transparency In Language And Vision-Based AI Systems
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_ | 1866910332416425984 |
|---|---|
| author | Noever, David McKee, Forrest |
| author_facet | Noever, David McKee, Forrest |
| contents | This investigation reveals a novel exploit derived from PNG image file formats, specifically their alpha transparency layer, and its potential to fool multiple AI vision systems. Our method uses this alpha layer as a clandestine channel invisible to human observers but fully actionable by AI image processors. The scope tested for the vulnerability spans representative vision systems from Apple, Microsoft, Google, Salesforce, Nvidia, and Facebook, highlighting the attack's potential breadth. This vulnerability challenges the security protocols of existing and fielded vision systems, from medical imaging to autonomous driving technologies. Our experiments demonstrate that the affected systems, which rely on convolutional neural networks or the latest multimodal language models, cannot quickly mitigate these vulnerabilities through simple patches or updates. Instead, they require retraining and architectural changes, indicating a persistent hole in multimodal technologies without some future adversarial hardening against such vision-language exploits. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_09671 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Exploiting Alpha Transparency In Language And Vision-Based AI Systems Noever, David McKee, Forrest Computer Vision and Pattern Recognition Machine Learning This investigation reveals a novel exploit derived from PNG image file formats, specifically their alpha transparency layer, and its potential to fool multiple AI vision systems. Our method uses this alpha layer as a clandestine channel invisible to human observers but fully actionable by AI image processors. The scope tested for the vulnerability spans representative vision systems from Apple, Microsoft, Google, Salesforce, Nvidia, and Facebook, highlighting the attack's potential breadth. This vulnerability challenges the security protocols of existing and fielded vision systems, from medical imaging to autonomous driving technologies. Our experiments demonstrate that the affected systems, which rely on convolutional neural networks or the latest multimodal language models, cannot quickly mitigate these vulnerabilities through simple patches or updates. Instead, they require retraining and architectural changes, indicating a persistent hole in multimodal technologies without some future adversarial hardening against such vision-language exploits. |
| title | Exploiting Alpha Transparency In Language And Vision-Based AI Systems |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2402.09671 |