j-cb / Breaking_Down_OOD_Detection

Related projects: ⓘ

• j-cb / GOOD
  Provable Worst Case Guarantees for the Detection of Out-of-Distribution Data
  ☆13Updated 2 years ago
• schzhu / learning-adversarially-robust-representations
  Code for the paper: Learning Adversarially Robust Representations via Worst-Case Mutual Information Maximization (https://arxiv.org/abs/2…
  ☆23Updated 3 years ago
• pdejorge / N-FGSM
  Official repo for the paper "Make Some Noise: Reliable and Efficient Single-Step Adversarial Training" (https://arxiv.org/abs/2202.01181)
  ☆25Updated last year
• tml-epfl / adv-training-corruptions
  On the effectiveness of adversarial training against common corruptions [UAI 2022]
  ☆30Updated 2 years ago
• yangarbiter / rare-spurious-correlation
  Understanding Rare Spurious Correlations in Neural Network
  ☆11Updated 2 years ago
• fra31 / robust-finetuning
  Code relative to "Adversarial robustness against multiple and single $l_p$-threat models via quick fine-tuning of robust classifiers"
  ☆15Updated last year
• ChaojianYu / Understanding-Robust-Overfitting
  Implementation for <Understanding Robust Overftting of Adversarial Training and Beyond> in ICML'22.
  ☆12Updated 2 years ago
• deeplearning-wisc / Spurious_OOD
  ☆21Updated 2 years ago
• AKuzina / attack_vae
  Diagnosing Vulnerability of Variational Auto-Encoders to Adversarial Attacks
  ☆13Updated 2 years ago
• DequanWang / dent
  Fighting Gradients with Gradients: Dynamic Defenses against Adversarial Attacks
  ☆36Updated 3 years ago
• tml-epfl / sharpness-vs-generalization
  A modern look at the relationship between sharpness and generalization [ICML 2023]
  ☆42Updated last year
• jh-jeong / smoothmix
  Code for the paper "SmoothMix: Training Confidence-calibrated Smoothed Classifiers for Certified Robustness" (NeurIPS 2021)
  ☆21Updated last year
• AlexMeinke / certified-certain-uncertainty
  A way to achieve uniform confidence far away from the training data.
  ☆36Updated 3 years ago
• kaiwenzha / contrastive-poisoning
  [ICLR 2023, Spotlight] Indiscriminate Poisoning Attacks on Unsupervised Contrastive Learning
  ☆26Updated 9 months ago
• harshays / inputgradients
  Do input gradients highlight discriminative features? [NeurIPS 2021] (https://arxiv.org/abs/2102.12781)
  ☆13Updated last year
• LijieFan / AdvCL
  [NeurIPS 2021] “When does Contrastive Learning Preserve Adversarial Robustness from Pretraining to Finetuning?”
  ☆45Updated 2 years ago
• arpitbansal297 / Meta-Balance
  ☆24Updated 2 years ago
• yk / icml19_public
  ☆21Updated 4 years ago
• ryoungj / optdom
  [ICLR'22] Self-supervised learning optimally robust representations for domain shift.
  ☆23Updated 2 years ago
• dedeswim / vits-robustness-torch
  Code for the paper "A Light Recipe to Train Robust Vision Transformers" [SaTML 2023]
  ☆52Updated last year
• cassidylaidlaw / perceptual-advex
  Code and data for the ICLR 2021 paper "Perceptual Adversarial Robustness: Defense Against Unseen Threat Models".
  ☆54Updated 2 years ago
• davidstutz / confidence-calibrated-adversarial-training
  Implementation of Confidence-Calibrated Adversarial Training (CCAT).
  ☆45Updated 4 years ago
• goldblum / AdversariallyRobustDistillation
  Pytorch implementation of Adversarially Robust Distillation (ARD)
  ☆57Updated 5 years ago
• locuslab / perturbation_learning
  Learning perturbation sets for robust machine learning
  ☆64Updated 3 years ago
• liuchen11 / AdversaryLossLandscape
  On the Loss Landscape of Adversarial Training: Identifying Challenges and How to Overcome Them [NeurIPS 2020]
  ☆35Updated 3 years ago
• yaodongyu / ProjNorm
  Predicting Out-of-Distribution Error with the Projection Norm
  ☆17Updated 2 years ago
• locuslab / robust_union
  [ICML'20] Multi Steepest Descent (MSD) for robustness against the union of multiple perturbation models.
  ☆25Updated last month
• MadryLab / smoothed-vit
  Certified Patch Robustness via Smoothed Vision Transformers
  ☆41Updated 2 years ago
• JonasGeiping / dataaugs
  ☆17Updated last year
• AI-secure / Uncovering-the-Connections-BetweenAdversarial-Transferability-and-Knowledge-Transferability
  code for ICML 2021 paper in which we explore the relationship between adversarial transferability and knowledge transferability.
  ☆17Updated last year