Deep Learning Model Security: Threats and Defenses
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_ | 1866917869838663680 |
|---|---|
| author | Wang, Tianyang Bi, Ziqian Zhang, Yichao Liu, Ming Hsieh, Weiche Feng, Pohsun Yan, Lawrence K. Q. Wen, Yizhu Peng, Benji Liu, Junyu Chen, Keyu Zhang, Sen Li, Ming Jiang, Chuanqi Song, Xinyuan Yang, Junjie Jing, Bowen Ren, Jintao Song, Junhao Tseng, Hong-Ming Chen, Silin Wang, Yunze Liang, Chia Xin Xu, Jiawei Pan, Xuanhe Wang, Jinlang Niu, Qian |
| author_facet | Wang, Tianyang Bi, Ziqian Zhang, Yichao Liu, Ming Hsieh, Weiche Feng, Pohsun Yan, Lawrence K. Q. Wen, Yizhu Peng, Benji Liu, Junyu Chen, Keyu Zhang, Sen Li, Ming Jiang, Chuanqi Song, Xinyuan Yang, Junjie Jing, Bowen Ren, Jintao Song, Junhao Tseng, Hong-Ming Chen, Silin Wang, Yunze Liang, Chia Xin Xu, Jiawei Pan, Xuanhe Wang, Jinlang Niu, Qian |
| contents | Deep learning has transformed AI applications but faces critical security challenges, including adversarial attacks, data poisoning, model theft, and privacy leakage. This survey examines these vulnerabilities, detailing their mechanisms and impact on model integrity and confidentiality. Practical implementations, including adversarial examples, label flipping, and backdoor attacks, are explored alongside defenses such as adversarial training, differential privacy, and federated learning, highlighting their strengths and limitations.
Advanced methods like contrastive and self-supervised learning are presented for enhancing robustness. The survey concludes with future directions, emphasizing automated defenses, zero-trust architectures, and the security challenges of large AI models. A balanced approach to performance and security is essential for developing reliable deep learning systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_08969 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Deep Learning Model Security: Threats and Defenses Wang, Tianyang Bi, Ziqian Zhang, Yichao Liu, Ming Hsieh, Weiche Feng, Pohsun Yan, Lawrence K. Q. Wen, Yizhu Peng, Benji Liu, Junyu Chen, Keyu Zhang, Sen Li, Ming Jiang, Chuanqi Song, Xinyuan Yang, Junjie Jing, Bowen Ren, Jintao Song, Junhao Tseng, Hong-Ming Chen, Silin Wang, Yunze Liang, Chia Xin Xu, Jiawei Pan, Xuanhe Wang, Jinlang Niu, Qian Cryptography and Security Machine Learning Software Engineering Deep learning has transformed AI applications but faces critical security challenges, including adversarial attacks, data poisoning, model theft, and privacy leakage. This survey examines these vulnerabilities, detailing their mechanisms and impact on model integrity and confidentiality. Practical implementations, including adversarial examples, label flipping, and backdoor attacks, are explored alongside defenses such as adversarial training, differential privacy, and federated learning, highlighting their strengths and limitations. Advanced methods like contrastive and self-supervised learning are presented for enhancing robustness. The survey concludes with future directions, emphasizing automated defenses, zero-trust architectures, and the security challenges of large AI models. A balanced approach to performance and security is essential for developing reliable deep learning systems. |
| title | Deep Learning Model Security: Threats and Defenses |
| topic | Cryptography and Security Machine Learning Software Engineering |
| url | https://arxiv.org/abs/2412.08969 |