Spanning Attack: Reinforce Black-box Attacks with Unlabeled Data

by   Lu Wang, et al.
Nanjing University, Inc.

Adversarial black-box attacks aim to craft adversarial perturbations by querying input-output pairs of machine learning models. They are widely used to evaluate the robustness of pre-trained models. However, black-box attacks often suffer from the issue of query inefficiency due to the high dimensionality of the input space, and therefore incur a false sense of model robustness. In this paper, we relax the conditions of the black-box threat model, and propose a novel technique called the spanning attack. By constraining adversarial perturbations in a low-dimensional subspace via spanning an auxiliary unlabeled dataset, the spanning attack significantly improves the query efficiency of black-box attacks. Extensive experiments show that the proposed method works favorably in both soft-label and hard-label black-box attacks. Our code is available at


page 13

page 14


EvoBA: An Evolution Strategy as a Strong Baseline forBlack-Box Adversarial Attacks

Recent work has shown how easily white-box adversarial attacks can be ap...

Certified Zeroth-order Black-Box Defense with Robust UNet Denoiser

Certified defense methods against adversarial perturbations have been re...

On the Challenges of Using Black-Box APIs for Toxicity Evaluation in Research

Perception of toxicity evolves over time and often differs between geogr...

MagDR: Mask-guided Detection and Reconstruction for Defending Deepfakes

Deepfakes raised serious concerns on the authenticity of visual contents...

Harnessing Adversarial Distances to Discover High-Confidence Errors

Given a deep neural network image classification model that we treat as ...

PROPS: Probabilistic personalization of black-box sequence models

We present PROPS, a lightweight transfer learning mechanism for sequenti...

Sparse-RS: a versatile framework for query-efficient sparse black-box adversarial attacks

A large body of research has focused on adversarial attacks which requir...

Please sign up or login with your details

Forgot password? Click here to reset