23 Open source projects that are alternatives of or similar to athena

Adversarial Robustness Toolbox (ART) - Python Library for Machine Learning Security - Evasion, Poisoning, Extraction, Inference - Red and Blue Teams

SHIELD: Fast, Practical Defense and Vaccination for Deep Learning using JPEG Compression

Robustness benchmark for DNN models.

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

My entry for ICLR 2018 Reproducibility Challenge for paper Synthesizing robust adversarial examples https://openreview.net/pdf?id=BJDH5M-AW

Uncertainty Quantification 360 (UQ360) is an extensible open-source toolkit that can help you estimate, communicate and use uncertainty in machine learning model predictions.

EAD: Elastic-Net Attacks to Deep Neural Networks via Adversarial Examples

Fawkes, privacy preserving tool against facial recognition systems. More info at https://sandlab.cs.uchicago.edu/fawkes

Adversarial Ranking Attack and Defense, ECCV, 2020.

This is our official implementation for the paper: Jinhui Tang, Xiaoyu Du, Xiangnan He, Fajie Yuan, Qi Tian, and Tat-Seng Chua, Adversarial Training Towards Robust Multimedia Recommender System.

Adversarial Distributional Training (NeurIPS 2020)

Backdoors Framework for Deep Learning and Federated Learning. A light-weight tool to conduct your research on backdoors.

A curated list of awesome resources regarding machine learning reliability.

Scaleable input gradient regularization

A Closer Look at Accuracy vs. Robustness

Feature Scattering Adversarial Training

Code implementation of the paper "With Great Training Comes Great Vulnerability: Practical Attacks against Transfer Learning", at USENIX Security 2018

Source code for the ICLR 2021 work "Generating Adversarial Computer Programs using Optimized Obfuscations"

The goal of this survey is two-fold: (i) to present recent advances on adversarial machine learning (AML) for the security of RS (i.e., attacking and defense recommendation models), (ii) to show another successful application of AML in generative adversarial networks (GANs) for generative applications, thanks to their ability for learning (high-…

Attacking Vision based Perception in End-to-end Autonomous Driving Models

Task-agnostic universal black-box attacks on computer vision neural network via procedural noise (CCS'19)

Code for the paper: Adversarial Training Against Location-Optimized Adversarial Patches. ECCV-W 2020.

reproduction of Thermometer Encoding: One Hot Way To Resist Adversarial Examples in pytorch