Defense of adversarial attacks on FDD models. fdd-defense is a python library with adversarial attacks on Fault Detection and Diagnostic (FDD) models and defense methods against attacks.

Este projeto foi desenvolvido durante a formação em Typescript da Alura no qual fomos instruídos sobre como criar regras de negócios, como desenvolver aplicações seguras com a "programação defensiva" e também desenvolvemos e aprofundamos os conhecimentos em POO com o TS.

Geometric Adversarial Attacks and Defenses on 3D Point Clouds (3DV 2021)

🔒| Evaluating the security (exploiting and fixing vulnerabilities) of Open eClass 2.3 (University of Athens) platform.

DiaLog is a powerful Log File Analyzer that can also do passive analysis of malicious IP's Found in web-server Traffic

ICCV 2021 papers and code focus on adversarial attacks and defense

This is the codebase for defense framework described in USENIX '21 paper "WaveGuard: Understanding and Mitigating Audio Adversarial Examples"

Athena: A Framework for Defending Machine Learning Systems Against Adversarial Attacks

A stochastic input pre-processing technique based on a process of down-sampling/up-sampling using convolution and transposed convolution layers. Defending convolutional neural network against adversarial attacks.

Implementation of our proposed defense strategy against adversarial attacks "Defensive Approximation (DA)"

Defense methods that utilize randomness to mitigate adversarial attacks on NLP models

Code implementing the experiments described in the NeurIPS 2018 paper "With Friends Like These, Who Needs Adversaries?".