Get our free extension to see links to code for papers anywhere online!

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

Core Risk Minimization using Salient ImageNet


Mar 28, 2022
Sahil Singla, Mazda Moayeri, Soheil Feizi

Add code


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Provable Adversarial Robustness for Fractional Lp Threat Models


Mar 16, 2022
Alexander Levine, Soheil Feizi

Add code

* AISTATS 2022 accepted paper 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Understanding Failure Modes of Self-Supervised Learning


Mar 03, 2022
Neha Mukund Kalibhat, Kanika Narang, Liang Tan, Hamed Firooz, Maziar Sanjabi, Soheil Feizi

Add code


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Improved Certified Defenses against Data Poisoning with (Deterministic) Finite Aggregation


Feb 05, 2022
Wenxiao Wang, Alexander Levine, Soheil Feizi

Add code


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Certifying Model Accuracy under Distribution Shifts


Jan 28, 2022
Aounon Kumar, Alexander Levine, Tom Goldstein, Soheil Feizi

Add code


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

A Comprehensive Study of Image Classification Model Sensitivity to Foregrounds, Backgrounds, and Visual Attributes


Jan 26, 2022
Mazda Moayeri, Phillip Pope, Yogesh Balaji, Soheil Feizi

Add code


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Interpolated Joint Space Adversarial Training for Robust and Generalizable Defenses


Dec 12, 2021
Chun Pong Lau, Jiang Liu, Hossein Souri, Wei-An Lin, Soheil Feizi, Rama Chellappa

Add code

* Under submission 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Mutual Adversarial Training: Learning together is better than going alone


Dec 09, 2021
Jiang Liu, Chun Pong Lau, Hossein Souri, Soheil Feizi, Rama Chellappa

Add code

* Under submission 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Segment and Complete: Defending Object Detectors against Adversarial Patch Attacks with Robust Patch Detection


Dec 08, 2021
Jiang Liu, Alexander Levine, Chun Pong Lau, Rama Chellappa, Soheil Feizi

Add code

* Under submission 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Improving Deep Learning Interpretability by Saliency Guided Training


Nov 29, 2021
Aya Abdelsalam Ismail, Héctor Corrada Bravo, Soheil Feizi

Add code

* Thirty-fifth Conference on Neural Information Processing Systems 2021 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email
<<
1
2
3
4
5
6
7
8
>>