Data-Free Model-Related Attacks: Unleashing the Potential of Generative AI
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866918094401699840 |
|---|---|
| author | Ye, Dayong Zhu, Tianqing Wang, Shang Liu, Bo Zhang, Leo Yu Zhou, Wanlei Zhang, Yang |
| author_facet | Ye, Dayong Zhu, Tianqing Wang, Shang Liu, Bo Zhang, Leo Yu Zhou, Wanlei Zhang, Yang |
| contents | Generative AI technology has become increasingly integrated into our daily lives, offering powerful capabilities to enhance productivity. However, these same capabilities can be exploited by adversaries for malicious purposes. While existing research on adversarial applications of generative AI predominantly focuses on cyberattacks, less attention has been given to attacks targeting deep learning models. In this paper, we introduce the use of generative AI for facilitating model-related attacks, including model extraction, membership inference, and model inversion. Our study reveals that adversaries can launch a variety of model-related attacks against both image and text models in a data-free and black-box manner, achieving comparable performance to baseline methods that have access to the target models' training data and parameters in a white-box manner. This research serves as an important early warning to the community about the potential risks associated with generative AI-powered attacks on deep learning models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_16671 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Data-Free Model-Related Attacks: Unleashing the Potential of Generative AI Ye, Dayong Zhu, Tianqing Wang, Shang Liu, Bo Zhang, Leo Yu Zhou, Wanlei Zhang, Yang Cryptography and Security Artificial Intelligence Generative AI technology has become increasingly integrated into our daily lives, offering powerful capabilities to enhance productivity. However, these same capabilities can be exploited by adversaries for malicious purposes. While existing research on adversarial applications of generative AI predominantly focuses on cyberattacks, less attention has been given to attacks targeting deep learning models. In this paper, we introduce the use of generative AI for facilitating model-related attacks, including model extraction, membership inference, and model inversion. Our study reveals that adversaries can launch a variety of model-related attacks against both image and text models in a data-free and black-box manner, achieving comparable performance to baseline methods that have access to the target models' training data and parameters in a white-box manner. This research serves as an important early warning to the community about the potential risks associated with generative AI-powered attacks on deep learning models. |
| title | Data-Free Model-Related Attacks: Unleashing the Potential of Generative AI |
| topic | Cryptography and Security Artificial Intelligence |
| url | https://arxiv.org/abs/2501.16671 |