DATABench: Evaluating Dataset Auditing in Deep Learning from an Adversarial Perspective
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_ | 1866915672013930496 |
|---|---|
| author | Shao, Shuo Li, Yiming Zheng, Mengren Hu, Zhiyang Chen, Yukun Li, Boheng He, Yu Guo, Junfeng Tao, Dacheng Qin, Zhan |
| author_facet | Shao, Shuo Li, Yiming Zheng, Mengren Hu, Zhiyang Chen, Yukun Li, Boheng He, Yu Guo, Junfeng Tao, Dacheng Qin, Zhan |
| contents | The widespread application of Deep Learning across diverse domains hinges critically on the quality and composition of training datasets. However, the common lack of disclosure regarding their usage raises significant privacy and copyright concerns. Dataset auditing techniques, which aim to determine if a specific dataset was used to train a given suspicious model, provide promising solutions to addressing these transparency gaps. While prior work has developed various auditing methods, their resilience against dedicated adversarial attacks remains largely unexplored. To bridge the gap, this paper initiates a comprehensive study evaluating dataset auditing from an adversarial perspective. We start with introducing a novel taxonomy, classifying existing methods based on their reliance on internal features (IF) (inherent to the data) versus external features (EF) (artificially introduced for auditing). Subsequently, we formulate two primary attack types: evasion attacks, designed to conceal the use of a dataset, and forgery attacks, intending to falsely implicate an unused dataset. Building on the understanding of existing methods and attack objectives, we further propose systematic attack strategies: decoupling, removal, and detection for evasion; adversarial example-based methods for forgery. These formulations and strategies lead to our new benchmark, DATABench, comprising 17 evasion attacks, 5 forgery attacks, and 9 representative auditing methods. Extensive evaluations using DATABench reveal that none of the evaluated auditing methods are sufficiently robust or distinctive under adversarial settings. These findings underscore the urgent need for developing a more secure and reliable dataset auditing method capable of withstanding sophisticated adversarial manipulation. Code is available in https://github.com/shaoshuo-ss/DATABench. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_05622 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | DATABench: Evaluating Dataset Auditing in Deep Learning from an Adversarial Perspective Shao, Shuo Li, Yiming Zheng, Mengren Hu, Zhiyang Chen, Yukun Li, Boheng He, Yu Guo, Junfeng Tao, Dacheng Qin, Zhan Cryptography and Security Artificial Intelligence Machine Learning The widespread application of Deep Learning across diverse domains hinges critically on the quality and composition of training datasets. However, the common lack of disclosure regarding their usage raises significant privacy and copyright concerns. Dataset auditing techniques, which aim to determine if a specific dataset was used to train a given suspicious model, provide promising solutions to addressing these transparency gaps. While prior work has developed various auditing methods, their resilience against dedicated adversarial attacks remains largely unexplored. To bridge the gap, this paper initiates a comprehensive study evaluating dataset auditing from an adversarial perspective. We start with introducing a novel taxonomy, classifying existing methods based on their reliance on internal features (IF) (inherent to the data) versus external features (EF) (artificially introduced for auditing). Subsequently, we formulate two primary attack types: evasion attacks, designed to conceal the use of a dataset, and forgery attacks, intending to falsely implicate an unused dataset. Building on the understanding of existing methods and attack objectives, we further propose systematic attack strategies: decoupling, removal, and detection for evasion; adversarial example-based methods for forgery. These formulations and strategies lead to our new benchmark, DATABench, comprising 17 evasion attacks, 5 forgery attacks, and 9 representative auditing methods. Extensive evaluations using DATABench reveal that none of the evaluated auditing methods are sufficiently robust or distinctive under adversarial settings. These findings underscore the urgent need for developing a more secure and reliable dataset auditing method capable of withstanding sophisticated adversarial manipulation. Code is available in https://github.com/shaoshuo-ss/DATABench. |
| title | DATABench: Evaluating Dataset Auditing in Deep Learning from an Adversarial Perspective |
| topic | Cryptography and Security Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2507.05622 |