Code with experiments from paper "Continual learning for computer security"
-
Updated
May 10, 2023
Code with experiments from paper "Continual learning for computer security"
The official implementation of the ICONIP2021 paper: Condition-Invariant Physical Adversarial Attacks via Pixel-Wise Adversarial Learning
This study explores the vulnerability of the Federated Learning (FL) model where a portion of clients participating in the FL process is under the control of adversaries who don’t have access to the training data but can access the training model and its parameters.
Evaluating the Use of Fast Adversarial Training in Defending Against Adversarial Patch Attacks
Fast Gradient Sign Adversarial Attack(FGSM) examples creation using FashionMnist dataset
A deep-learning tool for detecting adversarial attacks on French text classifiers.
Replicating the code and results of the paper "Simple Black-box Adversarial Attacks"
Scripts for training adversarially robust classification models
Contains papers, blogs and articles on AI
DDoS attack thru a multithread Python script
MNIST recognition system, research adversarial attacks (FSGM)
Framework for creating Adversarial Attacks on Deep Neural Networks with Evolutionary Strategies (ES).
MATLAB code for generating adversarial images using GoogLeNet to test the robustness of deep learning models. Features both untargeted and targeted adversarial attacks.
A new kind of MLOps platform purpose built for production generative ai apps
This is the repo for exploring data augmentation for adversarial robustness
A collection of deprecated neural network defenses
Al HW submissions made during the "Adversarial Learning Course" Of Y-DATA, Yandex
Code for paper "Boosting Query Effificiency of Meta Attack with Dynamic Fine-tuning"
Textual adversarial training with textattack
Add a description, image, and links to the adversarial-attacks topic page so that developers can more easily learn about it.
To associate your repository with the adversarial-attacks topic, visit your repo's landing page and select "manage topics."