# CorrAttack: Black-box Adversarial Attack with Structured Search

arXiv: https://arxiv.org/abs/2010.01250 · HTML: https://mlsanity.com/paper/2010.01250/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Oct 2020.

## Built on by (most cited first, 4 of 4)

- [Fast Adversarial Training with Adaptive Step Size](https://mlsanity.com/paper/2206.02417/) (2022)
- [Efficient Black-box Adversarial Attacks via Bayesian Optimization Guided by a Function Prior](https://mlsanity.com/paper/2405.19098/) (2024)
- [Meta-Learning the Search Distribution of Black-Box Random Search Based Adversarial Attacks](https://mlsanity.com/paper/2111.01714/) (2021)
- [Adversarial Attacks on Graph Classification via Bayesian Optimisation](https://mlsanity.com/paper/2111.02842/) (2021)

## Abstract (arXiv)

We present a new method for score-based adversarial attack, where the attacker queries the loss-oracle of the target model. Our method employs a parameterized search space with a structure that captures the relationship of the gradient of the loss function. We show that searching over the structured space can be approximated by a time-varying contextual bandits problem, where the attacker takes feature of the associated arm to make modifications of the input, and receives an immediate reward as the reduction of the loss function. The time-varying contextual bandits problem can then be solved by a Bayesian optimization procedure, which can take advantage of the features of the structured action space. The experiments on ImageNet and the Google Cloud Vision API demonstrate that the proposed method achieves the state of the art success rates and query efficiencies for both undefended and defended models.