[Machine Learning 2023] Imbalanced Gradients: A Subtle Cause of Overestimated Adversarial Robustness
-
Updated
Apr 12, 2023 - Python
[Machine Learning 2023] Imbalanced Gradients: A Subtle Cause of Overestimated Adversarial Robustness
Code with experiments from paper "Continual learning for computer security"
Formalizing Attacker Scenarios for Adversarial Transferability
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.
Apply Carlini-Wagner Attack on CNN 🤖
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
This is my B.Tech Thesis Project which tries to attack the Neural network models in such a way that they will classify image incorrectly. It aims to expose the vulnerability and unreliability of various image processing models.
Comparing various adversarial attacks and defenses for CNN based Image classifiers from the IBM-Adversarial-toolbox
DDoS attack thru a multithread Python script
Variations of FGSM (fast gradient sign attack) explored for generating adversarial examples.
PyTorch versio of robust Drebin Malware Detection
MNIST recognition system, research adversarial attacks (FSGM)
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."