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

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

On the amplification of security and privacy risks by post-hoc explanations in machine learning models


Jun 28, 2022
Pengrui Quan, Supriyo Chakraborty, Jeya Vikranth Jeyakumar, Mani Srivastava

* 9 pages, appendix: 2 pages 

   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

Adversarial training in communication constrained federated learning


Mar 01, 2021
Devansh Shah, Parijat Dube, Supriyo Chakraborty, Ashish Verma


   Access Paper or Ask Questions

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

IBM Federated Learning: an Enterprise Framework White Paper V0.1


Jul 22, 2020
Heiko Ludwig, Nathalie Baracaldo, Gegi Thomas, Yi Zhou, Ali Anwar, Shashank Rajamoni, Yuya Ong, Jayaram Radhakrishnan, Ashish Verma, Mathieu Sinn, Mark Purcell, Ambrish Rawat, Tran Minh, Naoise Holohan, Supriyo Chakraborty, Shalisha Whitherspoon, Dean Steuer, Laura Wynter, Hifaz Hassan, Sean Laguna, Mikhail Yurochkin, Mayank Agarwal, Ebube Chuba, Annie Abay

* 17 pages 

   Access Paper or Ask Questions

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

Explaining Motion Relevance for Activity Recognition in Video Deep Learning Models


Mar 31, 2020
Liam Hiley, Alun Preece, Yulia Hicks, Supriyo Chakraborty, Prudhvi Gurram, Richard Tomsett


   Access Paper or Ask Questions

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

Improving Adversarial Robustness Through Progressive Hardening


Mar 18, 2020
Chawin Sitawarin, Supriyo Chakraborty, David Wagner

* Preprint. Under review 

   Access Paper or Ask Questions

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

Sanity Checks for Saliency Metrics


Nov 29, 2019
Richard Tomsett, Dan Harborne, Supriyo Chakraborty, Prudhvi Gurram, Alun Preece

* Accepted for publication at the Thirty Fourth AAAI conference on Artificial Intelligence (AAAI-20) 

   Access Paper or Ask Questions

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

Analyzing Federated Learning through an Adversarial Lens


Nov 29, 2018
Arjun Nitin Bhagoji, Supriyo Chakraborty, Prateek Mittal, Seraphin Calo

* 18 pages, 12 figures 

   Access Paper or Ask Questions

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

Stakeholders in Explainable AI


Sep 29, 2018
Alun Preece, Dan Harborne, Dave Braines, Richard Tomsett, Supriyo Chakraborty

* Presented at AAAI FSS-18: Artificial Intelligence in Government and Public Sector, Arlington, Virginia, USA 

   Access Paper or Ask Questions

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

Interpretable to Whom? A Role-based Model for Analyzing Interpretable Machine Learning Systems


Jun 20, 2018
Richard Tomsett, Dave Braines, Dan Harborne, Alun Preece, Supriyo Chakraborty

* presented at 2018 ICML Workshop on Human Interpretability in Machine Learning (WHI 2018), Stockholm, Sweden 

   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
>>