Mind the Gap: Detecting Black-box Adversarial Attacks in the Making through Query Update Analysis
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915199656656896 |
|---|---|
| author | Park, Jeonghwan McLaughlin, Niall Alouani, Ihsen |
| author_facet | Park, Jeonghwan McLaughlin, Niall Alouani, Ihsen |
| contents | Adversarial attacks remain a significant threat that can jeopardize the integrity of Machine Learning (ML) models. In particular, query-based black-box attacks can generate malicious noise without having access to the victim model's architecture, making them practical in real-world contexts. The community has proposed several defenses against adversarial attacks, only to be broken by more advanced and adaptive attack strategies. In this paper, we propose a framework that detects if an adversarial noise instance is being generated. Unlike existing stateful defenses that detect adversarial noise generation by monitoring the input space, our approach learns adversarial patterns in the input update similarity space. In fact, we propose to observe a new metric called Delta Similarity (DS), which we show it captures more efficiently the adversarial behavior. We evaluate our approach against 8 state-of-the-art attacks, including adaptive attacks, where the adversary is aware of the defense and tries to evade detection. We find that our approach is significantly more robust than existing defenses both in terms of specificity and sensitivity. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_02986 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Mind the Gap: Detecting Black-box Adversarial Attacks in the Making through Query Update Analysis Park, Jeonghwan McLaughlin, Niall Alouani, Ihsen Cryptography and Security Adversarial attacks remain a significant threat that can jeopardize the integrity of Machine Learning (ML) models. In particular, query-based black-box attacks can generate malicious noise without having access to the victim model's architecture, making them practical in real-world contexts. The community has proposed several defenses against adversarial attacks, only to be broken by more advanced and adaptive attack strategies. In this paper, we propose a framework that detects if an adversarial noise instance is being generated. Unlike existing stateful defenses that detect adversarial noise generation by monitoring the input space, our approach learns adversarial patterns in the input update similarity space. In fact, we propose to observe a new metric called Delta Similarity (DS), which we show it captures more efficiently the adversarial behavior. We evaluate our approach against 8 state-of-the-art attacks, including adaptive attacks, where the adversary is aware of the defense and tries to evade detection. We find that our approach is significantly more robust than existing defenses both in terms of specificity and sensitivity. |
| title | Mind the Gap: Detecting Black-box Adversarial Attacks in the Making through Query Update Analysis |
| topic | Cryptography and Security |
| url | https://arxiv.org/abs/2503.02986 |