Hard-label based Small Query Black-box Adversarial Attack
Authors:
- 3 January 2024
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 3974-3983
Abstract
We consider the hard-label based black-box adversarial attack setting which solely observes the target model’s predicted class. Most of the attack methods in this setting suffer from impractical number of queries required to achieve a successful attack. One approach to tackle this drawback is utilising the adversarial transferability between white-box surrogate models and black-box target model. However, the majority of the methods adopting this approach are soft-label based to take the full advantage of zeroth-order optimisation. Unlike mainstream methods, we propose a new practical setting of hard-label based attack with an optimisation process guided by a pre-trained surrogate model. Experiments show the proposed method significantly improves the query efficiency of the hard-label based black-box attack across various target model architectures. We find the proposed method achieves approximately 5 times higher attack success rate compared to the benchmarks, especially at the small query budgets as 100 and 250.Keywords
All Related Versions
This publication has 17 references indexed in Scilit:
- Adversarial Eigen Attack on BlackBox Models2022
- Enhancing the Transferability of Adversarial Attacks through Variance Tuning2021
- QEBA: Query-Efficient Boundary-Based Blackbox Attack2020
- Evading Defenses to Transferable Adversarial Examples by Translation-Invariant Attacks2019
- Improving Transferability of Adversarial Examples With Input Diversity2019
- Practical Black-Box Attacks on Deep Neural Networks Using Efficient Query Mechanisms2018
- Boosting Adversarial Attacks with Momentum2018
- DeepFool: A Simple and Accurate Method to Fool Deep Neural Networks2016
- ImageNet: A large-scale hierarchical image database2009
- Empirical Comparison of “Hard” and “Soft” Label Propagation for Relational Classification2008