# An Efficient and Margin-Approaching Zero-Confidence Adversarial Attack

arXiv: https://arxiv.org/abs/1910.00511 · HTML: https://mlsanity.com/paper/1910.00511/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Oct 2019.

## Built on by (most cited first, 1 of 1)

- [Certified Robustness for Large Language Models with Self-Denoising](https://mlsanity.com/paper/2307.07171/) (2023)

## Abstract (arXiv)

There are two major paradigms of white-box adversarial attacks that attempt to impose input perturbations. The first paradigm, called the fix-perturbation attack, crafts adversarial samples within a given perturbation level. The second paradigm, called the zero-confidence attack, finds the smallest perturbation needed to cause mis-classification, also known as the margin of an input feature. While the former paradigm is well-resolved, the latter is not. Existing zero-confidence attacks either introduce significant ap-proximation errors, or are too time-consuming. We therefore propose MARGINATTACK, a zero-confidence attack framework that is able to compute the margin with improved accuracy and efficiency. Our experiments show that MARGINATTACK is able to compute a smaller margin than the state-of-the-art zero-confidence attacks, and matches the state-of-the-art fix-perturbation at-tacks. In addition, it runs significantly faster than the Carlini-Wagner attack, currently the most ac-curate zero-confidence attack algorithm.