Multi-task adversarial attribution method based on hierarchical structure
Deep neural networks have demonstrated superior performance in various computer vision tasks. However, they have been found to be highly susceptible to adversarial attacks, which involve the addition of perturbations to examples during the inference phase that are imperceptible to the human eye. To...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
POSTS&TELECOM PRESS Co., LTD
2025-02-01
|
| Series: | 网络与信息安全学报 |
| Subjects: | |
| Online Access: | http://www.cjnis.com.cn/thesisDetails#10.11959/j.issn.2096-109x.2025009 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Deep neural networks have demonstrated superior performance in various computer vision tasks. However, they have been found to be highly susceptible to adversarial attacks, which involve the addition of perturbations to examples during the inference phase that are imperceptible to the human eye. To defend against adversarial attacks, some works have explored the reverse engineering of adversarial examples, known as the adversarial attribution problem. By attributing the attack algorithm and victim model used to generate adversarial examples, defenders can gain insights into the attacker’s knowledge and targets, thereby enabling the design of more effective defense algorithms against corresponding attacks. Existing methods have mostly approached the adversarial attribution problem as a single-task learning problem. However, as the scope of attack algorithms and victim models has expanded, single-task learning has faced the challenge of combinatorial explosion. To improve the accuracy of adversarial attribution and meet the requirements for different attribution granularities, attack algorithms and victim models were layered, and the dependencies between different levels were utilized. A multi-task adversarial attribution method based on a hierarchical structure was proposed. This method simultaneously performed the attribution tasks of attack algorithms and victim models at different levels and employed hierarchical path prediction to learn the dependencies between these levels. Experimental results on multiple datasets demonstrate that the proposed method achieves better attribution performance compared to other attribution methods. |
|---|---|
| ISSN: | 2096-109X |