Poisoning the Pixels: Revisiting Backdoor Attacks on Semantic Segmentation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912970927243264 |
|---|---|
| author | Zhang, Guangsheng Tian, Huan Zhang, Leo Zhu, Tianqing Ding, Ming Zhou, Wanlei Liu, Bo |
| author_facet | Zhang, Guangsheng Tian, Huan Zhang, Leo Zhu, Tianqing Ding, Ming Zhou, Wanlei Liu, Bo |
| contents | Semantic segmentation models are widely deployed in safety-critical applications such as autonomous driving, yet their vulnerability to backdoor attacks remains largely underexplored. Prior segmentation backdoor studies transfer threat settings from existing image classification tasks, focusing primarily on object-to-background mis-segmentation. In this work, we revisit the threats by systematically examining backdoor attacks tailored to semantic segmentation. We identify four coarse-grained attack vectors (Object-to-Object, Object-to-Background, Background-to-Object, and Background-to-Background attacks), as well as two fine-grained vectors (Instance-Level and Conditional attacks). To formalize these attacks, we introduce BADSEG, a unified framework that optimizes trigger designs and applies label manipulation strategies to maximize attack performance while preserving victim model utility. Extensive experiments across diverse segmentation architectures on benchmark datasets demonstrate that BADSEG achieves high attack effectiveness with minimal impact on clean samples. We further evaluate six representative defenses and find that they fail to reliably mitigate our attacks, revealing critical gaps in current defenses. Finally, we demonstrate that these vulnerabilities persist in recent emerging architectures, including transformer-based networks and the Segment Anything Model (SAM), thereby compromising their security. Our work reveals previously overlooked security vulnerabilities in semantic segmentation, and motivates the development of defenses tailored to segmentation-specific threat models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_16405 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Poisoning the Pixels: Revisiting Backdoor Attacks on Semantic Segmentation Zhang, Guangsheng Tian, Huan Zhang, Leo Zhu, Tianqing Ding, Ming Zhou, Wanlei Liu, Bo Cryptography and Security Semantic segmentation models are widely deployed in safety-critical applications such as autonomous driving, yet their vulnerability to backdoor attacks remains largely underexplored. Prior segmentation backdoor studies transfer threat settings from existing image classification tasks, focusing primarily on object-to-background mis-segmentation. In this work, we revisit the threats by systematically examining backdoor attacks tailored to semantic segmentation. We identify four coarse-grained attack vectors (Object-to-Object, Object-to-Background, Background-to-Object, and Background-to-Background attacks), as well as two fine-grained vectors (Instance-Level and Conditional attacks). To formalize these attacks, we introduce BADSEG, a unified framework that optimizes trigger designs and applies label manipulation strategies to maximize attack performance while preserving victim model utility. Extensive experiments across diverse segmentation architectures on benchmark datasets demonstrate that BADSEG achieves high attack effectiveness with minimal impact on clean samples. We further evaluate six representative defenses and find that they fail to reliably mitigate our attacks, revealing critical gaps in current defenses. Finally, we demonstrate that these vulnerabilities persist in recent emerging architectures, including transformer-based networks and the Segment Anything Model (SAM), thereby compromising their security. Our work reveals previously overlooked security vulnerabilities in semantic segmentation, and motivates the development of defenses tailored to segmentation-specific threat models. |
| title | Poisoning the Pixels: Revisiting Backdoor Attacks on Semantic Segmentation |
| topic | Cryptography and Security |
| url | https://arxiv.org/abs/2603.16405 |