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

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

Renyi Differential Privacy of Propose-Test-Release and Applications to Private and Robust Machine Learning


Sep 16, 2022
Jiachen T. Wang, Saeed Mahloujifar, Shouda Wang, Ruoxi Jia, Prateek Mittal

* NeurIPS 2022 

   Access Paper or Ask Questions

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

A Light Recipe to Train Robust Vision Transformers


Sep 15, 2022
Edoardo Debenedetti, Vikash Sehwag, Prateek Mittal

* Code available at https://github.com/dedeswim/vits-robustness-torch 

   Access Paper or Ask Questions

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

Just Rotate it: Deploying Backdoor Attacks via Rotation Transformation


Jul 22, 2022
Tong Wu, Tianhao Wang, Vikash Sehwag, Saeed Mahloujifar, Prateek Mittal

* 25 pages 

   Access Paper or Ask Questions

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

Understanding Robust Learning through the Lens of Representation Similarities


Jun 20, 2022
Christian Cianfarani, Arjun Nitin Bhagoji, Vikash Sehwag, Ben Zhao, Prateek Mittal

* 35 pages, 29 figures 

   Access Paper or Ask Questions

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

Neurotoxin: Durable Backdoors in Federated Learning


Jun 12, 2022
Zhengming Zhang, Ashwinee Panda, Linyue Song, Yaoqing Yang, Michael W. Mahoney, Joseph E. Gonzalez, Kannan Ramchandran, Prateek Mittal

* Appears in ICML 2022 

   Access Paper or Ask Questions

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

Fight Poison with Poison: Detecting Backdoor Poison Samples via Decoupling Benign Correlations


May 26, 2022
Xiangyu Qi, Tinghao Xie, Saeed Mahloujifar, Prateek Mittal


   Access Paper or Ask Questions

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

Circumventing Backdoor Defenses That Are Based on Latent Separability


May 26, 2022
Xiangyu Qi, Tinghao Xie, Saeed Mahloujifar, Prateek Mittal


   Access Paper or Ask Questions

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

Formulating Robustness Against Unforeseen Attacks


Apr 28, 2022
Sihui Dai, Saeed Mahloujifar, Prateek Mittal


   Access Paper or Ask Questions

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

ObjectSeeker: Certifiably Robust Object Detection against Patch Hiding Attacks via Patch-agnostic Masking


Feb 03, 2022
Chong Xiang, Alexander Valtchanov, Saeed Mahloujifar, Prateek Mittal


   Access Paper or Ask Questions

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

SparseFed: Mitigating Model Poisoning Attacks in Federated Learning with Sparsification


Dec 12, 2021
Ashwinee Panda, Saeed Mahloujifar, Arjun N. Bhagoji, Supriyo Chakraborty, Prateek Mittal


   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
>>