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.

List Adversarial attacks repositories

mtcnnattack

71
Stars
15
Forks
Watchers

The first real-world adversarial attack on MTCNN face detetction system to date

advrank

24
Stars
5
Forks
Watchers

Adversarial Ranking Attack and Defense, ECCV, 2020.

awesome-3D-point-cloud-attacks

90
Stars
13
Forks
Watchers

List of state of the art papers, code, and other resources

hard-label-attack

38
Stars
10
Forks
Watchers

Natural Language Attacks in a Hard Label Black Box Setting.

perceptual-advex

54
Stars
9
Forks
Watchers

Code and data for the ICLR 2021 paper "Perceptual Adversarial Robustness: Defense Against Unseen Threat Models".

DIAC2019-Adversarial-Attack-Share

81
Stars
12
Forks
Watchers

DIAC2019基于Adversarial Attack的问题等价性判别比赛

FaceOff

79
Stars
14
Forks
Watchers

Steps towards physical adversarial attacks on facial recognition

TextFooler

475
Stars
78
Forks
Watchers

A Model for Natural Language Attack on Text Classification and Inference