paper-with-me

홈 › Papers

Simulating Unknown Target Models for Query-Efficient Black-box Attacks

2020-09-02 · CVPR 2021 1 · Chen Ma, Li Chen, Jun-Hai Yong

Many adversarial attacks have been proposed to investigate the security issues of deep neural networks. In the black-box setting, current model stealing attacks train a substitute model to counterfeit the functionality of the target model. However, the training requires querying the target model. Consequently, the query complexity remains high, and such attacks can be defended easily. This study aims to train a generalized substitute model called "Simulator", which can mimic the functionality of any unknown target model. To this end, we build the training data with the form of multiple tasks by collecting query sequences generated during the attacks of various existing networks. The learning process uses a mean square error-based knowledge-distillation loss in the meta-learning to minimize the difference between the Simulator and the sampled networks. The meta-gradients of this loss are then computed and accumulated from multiple tasks to update the Simulator and subsequently improve generalization. When attacking a target model that is unseen in training, the trained Simulator can accurately simulate its functionality using its limited feedback. As a result, a large fraction of queries can be transferred to the Simulator, thereby reducing query complexity. Results of the comprehensive experiments conducted using the CIFAR-10, CIFAR-100, and TinyImageNet datasets demonstrate that the proposed approach reduces query complexity by several orders of magnitude compared to the baseline method. The implementation source code is released at https://github.com/machanic/SimulatorAttack.

📄 PDF Abstract BibTeX arXiv:2009.00960

Code (1)

machanic/SimulatorAttack 공식 구현 pytorch

Tasks

Knowledge DistillationMeta-Learning

Similar Papers 제목 키워드 기반

Query Efficient Cross-Dataset Transferable Black-Box Attack on Action Recognition

2022-11-23 · Rohit Gupta, Naveed Akhtar, Gaurav Kumar Nayak, Ajmal Mian 외

Black-box adversarial attacks present a realistic threat to action recognition systems. Existing black-box attacks follow either a query-based approach where an attack is optimized by querying the target model, or a tran…

Action Recognition

Generalizable Black-Box Adversarial Attack with Meta Learning

2023-01-01 · Fei Yin, Yong Zhang, Baoyuan Wu, Yan Feng 외

In the scenario of black-box adversarial attack, the target model's parameters are unknown, and the attacker aims to find a successful adversarial perturbation based on query feedback under a query budget. Due to the lim…

Adversarial AttackMeta-Learning

On the Effectiveness of Small Input Noise for Defending Against Query-based Black-Box Attacks

2021-01-13 · Junyoung Byun, Hyojun Go, Changick Kim

While deep neural networks show unprecedented performance in various tasks, the vulnerability to adversarial examples hinders their deployment in safety-critical systems. Many studies have shown that attacks are also pos…

You Only Query Once: Effective Black Box Adversarial Attacks with Minimal Repeated Queries

2021-01-29 · Devin Willmott, Anit Kumar Sahu, Fatemeh Sheikholeslami, Filipe Condessa 외

Researchers have repeatedly shown that it is possible to craft adversarial attacks on deep classifiers (small perturbations that significantly change the class label), even in the "black-box" setting where one only has q…

Local Black-box Adversarial Attacks: A Query Efficient Approach

2021-01-04 · Tao Xiang, Hangcheng Liu, Shangwei Guo, Tianwei Zhang 외

Adversarial attacks have threatened the application of deep neural networks in security-sensitive scenarios. Most existing black-box attacks fool the target model by interacting with it many times and producing global pe…