# Query-Efficient Black-box Adversarial Examples (superceded)

arXiv: https://arxiv.org/abs/1712.07113 · HTML: https://mlsanity.com/paper/1712.07113/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Dec 2017.

## Built on by (most cited first, 5 of 5)

- [OFEI: A Semi-black-box Android Adversarial Sample Attack Framework Against DLaaS](https://mlsanity.com/paper/2105.11593/) (2021)
- [Evaluating the Cybersecurity Risk of Real World, Machine Learning Production Systems](https://mlsanity.com/paper/2107.01806/) (2021)
- [Certifiable Black-Box Attacks with Randomized Adversarial Examples: Breaking Defenses with Provable Confidence](https://mlsanity.com/paper/2304.04343/) (2023)
- [Online Adversarial Attacks](https://mlsanity.com/paper/2103.02014/) (2021)
- [Decision-BADGE: Decision-based Adversarial Batch Attack with Directional Gradient Estimation](https://mlsanity.com/paper/2303.04980/) (2023)

## Abstract (arXiv)

Note that this paper is superceded by "Black-Box Adversarial Attacks with Limited Queries and Information." Current neural network-based image classifiers are susceptible to adversarial examples, even in the black-box setting, where the attacker is limited to query access without access to gradients. Previous methods --- substitute networks and coordinate-based finite-difference methods --- are either unreliable or query-inefficient, making these methods impractical for certain problems. We introduce a new method for reliably generating adversarial examples under more restricted, practical black-box threat models. First, we apply natural evolution strategies to perform black-box attacks using two to three orders of magnitude fewer queries than previous methods. Second, we introduce a new algorithm to perform targeted adversarial attacks in the partial-information setting, where the attacker only has access to a limited number of target classes. Using these techniques, we successfully perform the first targeted adversarial attack against a commercially deployed machine learning system, the Google Cloud Vision API, in the partial information setting.