Untargeted Adversarial Attack

Untargeted adversarial attacks aim to degrade the overall performance of machine learning models without targeting specific inputs, focusing instead on reducing global accuracy or robustness. Current research explores these attacks across various model types, including deep neural networks, knowledge graph embeddings, and graph convolutional networks, employing techniques like rule-based perturbations, gradient-based methods, and object-attentional strategies to generate adversarial examples. This research is crucial for evaluating the security and reliability of machine learning systems in diverse applications, from network intrusion detection to robotic systems, highlighting vulnerabilities and informing the development of more robust defenses.

Papers

July 13, 2024

SemiAdv: Query-Efficient Black-Box Adversarial Attack with Unlabeled Images
Mingyuan Fan, Yang Liu, Cen Chen, Ximeng Liu
Adversarial Attack Adversarial Sample Unlabeled Image Untargeted Adversarial Attack

May 8, 2024

Untargeted Adversarial Attack on Knowledge Graph Embeddings
Tianzhe Zhao, Jiaoyan Chen, Yanchi Ru, Qika Lin, Yuxia Geng, Jun Liu
Adversarial Attack Knowledge Graph Knowledge Graph Embeddings Knowledge Graph Representation Learning Untargeted Adversarial Attack

October 5, 2023

Untargeted White-box Adversarial Attack with Heuristic Defence Methods in Real-time Deep Learning based Network Intrusion Detection System
Khushnaseeb Roshan, Aasim Zafar, Sheikh Burhan Ul Haque
Adversarial Attack Real Time Intrusion Detection Network Intrusion Detection Adversarial Scenario Untargeted Adversarial Attack

October 19, 2022

Effective Targeted Attacks for Adversarial Self-Supervised Learning
Minseon Kim, Hyeonjeong Ha, Sooel Son, Sung Ju Hwang
Adversarial Attack Adversarial Example Adversarial Training Attack Strategy Untargeted Adversarial 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

April 20, 2022

GUARD: Graph Universal Adversarial Defense
Jintang Li, Jie Liao, Ruofan Wu, Liang Chen, Zibin Zheng, Jiawang Dan, Changhua Meng, Weiqiang Wang
Adversarial Attack Adversarial Perturbation Graph Adversarial Attack Untargeted Adversarial Attack

February 13, 2022

Progressive Backdoor Erasing via connecting Backdoor and Adversarial Attacks
Bingxu Mu, Zhenxing Niu, Le Wang, Xue Wang, Rong Jin, Gang Hua
Adversarial Attack Backdoor Attack Backdoor Removal Untargeted Adversarial Attack