Query-Efficient Black-box Adversarial Examples (superceded)
Andrew Ilyas, Logan Engstrom, Anish Athalye, Jessy Lin

TL;DR
This paper introduces a query-efficient black-box adversarial attack method using natural evolution strategies, enabling targeted attacks with limited information and successfully attacking a commercial API.
Contribution
It presents a novel, reliable approach for black-box adversarial attacks that significantly reduces query requirements and handles partial information scenarios.
Findings
Achieved 1000x fewer queries than previous methods.
First successful targeted attack on Google Cloud Vision API.
Demonstrated effectiveness in limited-information settings.
Abstract
Note that this paper is superceded by "Black-Box Adversarial Attacks with Limited Queries and Information."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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdversarial Robustness in Machine Learning · Domain Adaptation and Few-Shot Learning · Advanced Neural Network Applications
