Discover jfc43/stratified-adv-rej Open Source project

Stars
3
Rank 3,963,521 (Top 79 %)
Language
Python
License
Apache License 2.0
Created over 1 year ago
Updated over 1 year ago

jfc43

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Study adversarially-robust classification with rejection where rejection has cost monotonically non-increasing in the perturbation magnitude, and propose a novel defense method with strong performance.

robust-ood-detection

Robust Out-of-distribution Detection in Neural Networks

Python

informative-outlier-mining

We propose a theoretically motivated method, Adversarial Training with informative Outlier Mining (ATOM), which improves the robustness of OOD detection to various types of adversarial OOD inputs and establishes state-of-the-art performance.

Python

robust-attribution-regularization

Robust Attribution Regularization

Jupyter Notebook

self-training-ensembles

Propose a principled and practically effective framework for unsupervised accuracy estimation and error detection tasks with theoretical analysis and state-of-the-art performance.

Python

pixel-discretization

Pixel discretization defense against adversarial attacks

Python

advex

Jupyter Notebook

eval-transductive-robustness

Exploring evaluating the adversarial robustness of transductive-learning based defenses.

Python

Low-Precision-SGD-and-Tree-Boosting

Project for Course CS 744 Big Data System

Cuda

jfc43/stratified-adv-rej

jfc43

Reviews

Repository Details

More Repositories