paper-with-me

Papers

HopSkipJumpAttack: A Query-Efficient Decision-Based Attack

2019-04-03 · Jianbo Chen, Michael. I. Jordan, Martin J. Wainwright

The goal of a decision-based adversarial attack on a trained model is to generate adversarial examples based solely on observing output labels returned by the targeted model. We develop HopSkipJumpAttack, a family of algorithms based on a novel estimate of the gradient direction using binary information at the decision boundary. The proposed family includes both untargeted and targeted attacks optimized for $\ell_2$ and $\ell_\infty$ similarity metrics respectively. Theoretical analysis is provided for the proposed algorithms and the gradient direction estimate. Experiments show HopSkipJumpAttack requires significantly fewer model queries than Boundary Attack. It also achieves competitive performance in attacking several widely-used defense mechanisms. (HopSkipJumpAttack was named Boundary Attack++ in a previous version of the preprint.)

📄 PDF Abstract BibTeX arXiv:1904.02144

Code (3)

Jianbo-Lab/BAPP 공식 구현 tf
Jianbo-Lab/HSJA 공식 구현 tf
nmcdermo/AdvML

Tasks

Adversarial Attack

Similar Papers 제목 키워드 기반

Query Efficient Decision Based Sparse Attacks Against Black-Box Deep Learning Models

2022-01-31 · Viet Quoc Vo, Ehsan Abbasnejad, Damith C. Ranasinghe

Despite our best efforts, deep learning models remain highly vulnerable to even tiny adversarial perturbations applied to the inputs. The ability to extract information from solely the output of a machine learning model …

BIG-bench Machine Learning

QUERY-EFFICIENT DECISION-BASED SPARSE ATTACKS AGAINST BLACK-BOX MACHINE LEARNING MODELS

2021-09-29 · ICLR 2022 4 · Viet Vo, Ehsan M Abbasnejad, Damith Ranasinghe

Despite our best efforts, deep learning models remain highly vulnerable to even tiny adversarial perturbations applied to the inputs. The ability to extract information from solely the output of a machine learning model …

BIG-bench Machine Learning

Query-Efficient Decision-based Black-Box Patch Attack

2023-07-02 · Zhaoyu Chen, Bo Li, Shuang Wu, Shouhong Ding 외

Deep neural networks (DNNs) have been showed to be highly vulnerable to imperceptible adversarial perturbations. As a complementary type of adversary, patch attacks that introduce perceptible perturbations to the images …

Face Verificationimage-classificationImage Classification

CGBA: Curvature-aware Geometric Black-box Attack

2023-08-06 · ICCV 2023 1 · Md Farhamdur Reza, Ali Rahmati, Tianfu Wu, Huaiyu Dai

Decision-based black-box attacks often necessitate a large number of queries to craft an adversarial example. Moreover, decision-based attacks based on querying boundary points in the estimated normal vector direction of…

PopSkipJump: Decision-Based Attack for Probabilistic Classifiers

2021-06-14 · Carl-Johann Simon-Gabriel, Noman Ahmed Sheikh, Andreas Krause

Most current classifiers are vulnerable to adversarial examples, small input perturbations that change the classification output. Many existing attack algorithms cover various settings, from white-box to black-box classi…