black-box attacks

SoK: Pitfalls in Evaluating Black-Box Attacks
We propose a taxonomy to categorize and better understand black-box attacks revealing unexplored threat spaces and other interesting findings, and emphasize the need to consider resource costs like attack runtime to evaluating attacks.
Fnu Suya, Anshuman Suri, Tingwei Zhang, Jingtao Hong, Yuan Tian, David Evans
PDF Cite Code
SoK: Pitfalls in Evaluating Black-Box Attacks
We propose a taxonomy to categorize and better understand black-box attacks revealing unexplored threat spaces and other interesting findings, and emphasize the need to consider resource costs like attack runtime to evaluating attacks.
Fnu Suya, Anshuman Suri, Tingwei Zhang, Jingtao Hong, Yuan Tian, David Evans
Last updated on Dec 20, 2023
PDF Cite Code
Hybrid Batch Attacks: Finding Black-box Adversarial Examples with Limited Queries
We propose query-efficient black-box attacks that innovatively combine existing methods and prioritize targeting more vulnerable seeds.
Fnu Suya, Jianfeng Chi, David Evans, Yuan Tian
PDF Cite Code Slides Video
Hybrid Batch Attacks: Finding Black-box Adversarial Examples with Limited Queries
We propose query-efficient black-box attacks that innovatively combine existing methods and prioritize targeting more vulnerable seeds.
Fnu Suya, Jianfeng Chi, David Evans, Yuan Tian
Last updated on Nov 27, 2023
PDF Cite Code Slides Video
Poster: Adversaries Don't Care About Averages: Batch Attacks on Black-Box Classifiers
We design batch attacks to priotize targeting more vulnerable seeds.
Fnu Suya, David Evans, Yuan Tian
PDF Cite
Poisoning Attacks and Subpopulation Susceptibility
We apply Bayesian optimization technique to design query efficient black-box attacks.
Fnu Suya, David Evans, Yuan Tian
PDF Cite Code