madrylab Goto Github PK

adversarial_spatial

Investigating the robustness of state-of-the-art CNN architectures to simple spatial transformations.

advex_tutorial

aiaas_supply_chains

Dataset and overview

backdoor_data_poisoning

backgrounds_challenge

bias-transfer

blackbox-bandits

Code for "Prior Convictions: Black-Box Adversarial Attacks with Bandits and Priors"

breeds-benchmarks

cifar10_challenge

A challenge to explore adversarial robustness of neural networks on CIFAR10.

constructed-datasets

Datasets for the paper "Adversarial Examples are not Bugs, They Are Features"

context-cite

Attribute (or cite) statements generated by LLMs back to in-context information.

copriors

Combining Diverse Feature Priors

cox

A lightweight experimental logging library

d3m

Debiasing Through Data Attribution

data-transfer

datamodels

datamodels-data

Data for "Datamodels: Predicting Predictions with Training Data"

dataset-interfaces

Dataset Interfaces: Diagnosing Model Failures Using Controllable Counterfactual Generation

dataset-replication-analysis

davidcpage-cifar

debuggabledeepnetworks

detectron

FAIR's research platform for object detection research, implementing popular algorithms like Mask R-CNN and RetinaNet.

detectron2

Detectron2 is FAIR's next-generation platform for object detection and segmentation.

dsdm

editingclassifiers

failure-directions

Distilling Model Failures as Directions in Latent Space

fast_l1

fastai-imgnet-benchmark

Code to reproduce "imagenet in 18 minutes" DAWN-benchmark entry

fastai-imgnet-benchmark-v2

Train ImageNet in 18 minutes on AWS

glm_saga

Minimal, standalone library for solving GLMs in PyTorch