A Practical Trigger-Free Backdoor Attack on Neural Networks
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_ | 1866916363980767232 |
|---|---|
| author | Wang, Jiahao Zhang, Xianglong Cheng, Xiuzhen Hu, Pengfei Zhang, Guoming |
| author_facet | Wang, Jiahao Zhang, Xianglong Cheng, Xiuzhen Hu, Pengfei Zhang, Guoming |
| contents | Backdoor attacks on deep neural networks have emerged as significant security threats, especially as DNNs are increasingly deployed in security-critical applications. However, most existing works assume that the attacker has access to the original training data. This limitation restricts the practicality of launching such attacks in real-world scenarios. Additionally, using a specified trigger to activate the injected backdoor compromises the stealthiness of the attacks. To address these concerns, we propose a trigger-free backdoor attack that does not require access to any training data. Specifically, we design a novel fine-tuning approach that incorporates the concept of malicious data into the concept of the attacker-specified class, resulting the misclassification of trigger-free malicious data into the attacker-specified class. Furthermore, instead of relying on training data to preserve the model's knowledge, we employ knowledge distillation methods to maintain the performance of the infected model on benign samples, and introduce a parameter importance evaluation mechanism based on elastic weight constraints to facilitate the fine-tuning of the infected model. The effectiveness, practicality, and stealthiness of the proposed attack are comprehensively evaluated on three real-world datasets. Furthermore, we explore the potential for enhancing the attack through the use of auxiliary datasets and model inversion. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_11444 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | A Practical Trigger-Free Backdoor Attack on Neural Networks Wang, Jiahao Zhang, Xianglong Cheng, Xiuzhen Hu, Pengfei Zhang, Guoming Cryptography and Security Backdoor attacks on deep neural networks have emerged as significant security threats, especially as DNNs are increasingly deployed in security-critical applications. However, most existing works assume that the attacker has access to the original training data. This limitation restricts the practicality of launching such attacks in real-world scenarios. Additionally, using a specified trigger to activate the injected backdoor compromises the stealthiness of the attacks. To address these concerns, we propose a trigger-free backdoor attack that does not require access to any training data. Specifically, we design a novel fine-tuning approach that incorporates the concept of malicious data into the concept of the attacker-specified class, resulting the misclassification of trigger-free malicious data into the attacker-specified class. Furthermore, instead of relying on training data to preserve the model's knowledge, we employ knowledge distillation methods to maintain the performance of the infected model on benign samples, and introduce a parameter importance evaluation mechanism based on elastic weight constraints to facilitate the fine-tuning of the infected model. The effectiveness, practicality, and stealthiness of the proposed attack are comprehensively evaluated on three real-world datasets. Furthermore, we explore the potential for enhancing the attack through the use of auxiliary datasets and model inversion. |
| title | A Practical Trigger-Free Backdoor Attack on Neural Networks |
| topic | Cryptography and Security |
| url | https://arxiv.org/abs/2408.11444 |