Adversarial attacks topic
Adversarial attacks are techniques that craft intentionally perturbed inputs to mislead machine learning models into producing incorrect outputs. They are central to research in AI robustness, security, and trustworthiness.
mtcnnattack
The first real-world adversarial attack on MTCNN face detetction system to date
natural-adv-examples
A Harder ImageNet Test Set (CVPR 2021)
advrank
Adversarial Ranking Attack and Defense, ECCV, 2020.
awesome-3D-point-cloud-attacks
List of state of the art papers, code, and other resources
hard-label-attack
Natural Language Attacks in a Hard Label Black Box Setting.
perceptual-advex
Code and data for the ICLR 2021 paper "Perceptual Adversarial Robustness: Defense Against Unseen Threat Models".
DIAC2019-Adversarial-Attack-Share
DIAC2019基于Adversarial Attack的问题等价性判别比赛
FaceOff
Steps towards physical adversarial attacks on facial recognition
advertorch
A Toolbox for Adversarial Robustness Research
TextFooler
A Model for Natural Language Attack on Text Classification and Inference