Black Box Adversarial Attack

Black-box adversarial attacks aim to fool machine learning models without knowledge of their internal workings, primarily by crafting subtly altered inputs (adversarial examples) that cause misclassification. Current research focuses on improving attack efficiency and transferability across different models and datasets, employing techniques like meta-learning, Bayesian optimization, and reinforcement learning, often within specific application domains such as image recognition, natural language processing, and autonomous driving. These attacks highlight critical vulnerabilities in deployed machine learning systems, driving the development of more robust models and defenses with significant implications for security and reliability in various applications.

Papers

September 6, 2024

Learning to Learn Transferable Generative Attack for Person Re-Identification
Yuan Bian, Min Liu, Xueping Wang, Yunfeng Ma, Yaonan Wang
LeArning Abstract Adversarial Example Transferable Adversarial Attack Black Box Adversarial Attack Model Attack Generative Attack

July 18, 2024

PG-Attack: A Precision-Guided Adversarial Attack Framework Against Vision Foundation Models for Autonomous Driving
Jiyuan Fu, Zhaoyu Chen, Kaixun Jiang, Haijing Guo, Shuyong Gao, Wenqiang Zhang
Adversarial Attack Autonomous Driving Vision Foundation Model Black Box Adversarial Attack Perturbation Attack

June 7, 2024

ADBA:Approximation Decision Boundary Approach for Black-Box Adversarial Attacks
Feiyang Wang, Xingquan Zuo, Hai Huang, Gang Chen
Adversarial Attack Adversarial Example Decision Boundary Black Box Adversarial Attack Decision Based dlADMM Algorithm

May 29, 2024

Efficient Black-box Adversarial Attacks via Bayesian Optimization Guided by a Function Prior
Shuyu Cheng, Yibo Miao, Yinpeng Dong, Xiao Yang, Xiao-Shan Gao, Jun Zhu
Adversarial Attack Adversarial Example Bayesian Optimization Black Box Model Black Box Adversarial Attack Functional Prior

April 24, 2024

March 14, 2024

Counter-Samples: A Stateless Strategy to Neutralize Black Box Adversarial Attacks
Roey Bokobza, Yisroel Mirsky
Adversarial Example Black Box Attack Defense Method Black Box Adversarial Attack Unlabeled Client

November 3, 2023

Efficient Black-Box Adversarial Attacks on Neural Text Detectors
Vitalii Fishchuk, Daniel Braun
Language Model Text Based Text Detection Character Level Black Box Adversarial Attack

April 25, 2023

LSTM-based Load Forecasting Robustness Against Noise Injection Attack in Microgrid
Amirhossein Nazeri, Pierluigi Pisu
LSTM Network Load Forecasting LSTM Model DC Microgrid Application Black Box Adversarial Attack Load Prediction

January 1, 2023

Generalizable Black-Box Adversarial Attack with Meta Learning
Fei Yin, Yong Zhang, Baoyuan Wu, Yan Feng, Jingyi Zhang, Yanbo Fan, Yujiu Yang
Adversarial Attack Adversarial Example Adversarial Perturbation Black Box Attack Black Box Adversarial Attack

November 15, 2022

Universal Distributional Decision-based Black-box Adversarial Attack with Reinforcement Learning
Yiran Huang, Yexu Zhou, Michael Hefenbrock, Till Riedel, Likun Fang, Michael Beigl
Reinforcement Learning Adversarial Attack Adversarial Perturbation Black Box Adversarial Attack Decision Based ImageNet Attack

October 16, 2022

Object-Attentional Untargeted Adversarial Attack
Chao Zhou, Yuan-Gen Wang, Guopu Zhu
Adversarial Attack Black Box Adversarial Attack Untargeted Adversarial Attack

August 30, 2022

A Black-Box Attack on Optical Character Recognition Systems
Samet Bayram, Kenneth Barner
Adversarial Attack Adversarial Learning Black Box Attack Black Box Adversarial Attack Binary Image Classification

July 21, 2022

Knowledge-enhanced Black-box Attacks for Recommendations
Jingfan Chen, Wenqi Fan, Guanghui Zhu, Xiangyu Zhao, Chunfeng Yuan, Qing Li, Yihua Huang
Deep Learning Adversarial Attack Movie Recommendation New Attack Knowledge Enhancement Black Box Adversarial Attack Attack Graph

July 13, 2022

Interactive Machine Learning: A State of the Art Review
Natnael A. Wondimu, Cédric Buche, Ubbo Visser
Machine Learning Internal State Black Box Adversarial Attack Interactive Machine Learning Exploratory Learning Art Analysis

June 22, 2022

AdvSmo: Black-box Adversarial Attack by Smoothing Linear Structure of Texture
Hui Xia, Rui Zhang, Shuliang Jiang, Zi Kang
Adversarial Attack Adversarial Example Black Box Adversarial DEfense Texture Rather Black Box Adversarial Attack Linear Form

June 17, 2022

Query-Efficient and Scalable Black-Box Adversarial Attacks on Discrete Sequential Data via Bayesian Optimization
Deokjae Lee, Seungyong Moon, Junhyeok Lee, Hyun Oh Song
Adversarial Attack Adversarial Example Bayesian Optimization Black Box Attack Sequential Data Black Box Adversarial Attack

April 30, 2022

Optimizing One-pixel Black-box Adversarial Attacks
Tianxun Zhou, Shubhankar Agrawal, Prateek Manocha
Deep Neural Network Adversarial Attack Pixel Wise Black Box Adversarial Attack Image Perturbation ImageNet Attack

April 26, 2022

Restricted Black-box Adversarial Attack Against DeepFake Face Swapping
Junhao Dong, Yuan Wang, Jianhuang Lai, Xiaohua Xie
Generative Adversarial Network Black Box Adversarial Attack Deepfake Face

April 4, 2022

SecureSense: Defending Adversarial Attack for Secure Device-Free Human Activity Recognition
Jianfei Yang, Han Zou, Lihua Xie
Adversarial Attack Activity Recognition Black Box Adversarial Attack White Box Adversarial