Alert button
Picture for Ambrish Rawat

Ambrish Rawat

Alert button

Detectors for Safe and Reliable LLMs: Implementations, Uses, and Limitations

Mar 09, 2024
Swapnaja Achintalwar, Adriana Alvarado Garcia, Ateret Anaby-Tavor, Ioana Baldini, Sara E. Berger, Bishwaranjan Bhattacharjee, Djallel Bouneffouf, Subhajit Chaudhury, Pin-Yu Chen, Lamogha Chiazor, Elizabeth M. Daly, Rogério Abreu de Paula, Pierre Dognin, Eitan Farchi, Soumya Ghosh, Michael Hind, Raya Horesh, George Kour, Ja Young Lee, Erik Miehling, Keerthiram Murugesan, Manish Nagireddy, Inkit Padhi, David Piorkowski, Ambrish Rawat, Orna Raz, Prasanna Sattigeri, Hendrik Strobelt, Sarathkrishna Swaminathan, Christoph Tillmann, Aashka Trivedi, Kush R. Varshney, Dennis Wei, Shalisha Witherspooon, Marcel Zalmanovici

Viaarxiv icon

Domain Adaptation for Time series Transformers using One-step fine-tuning

Jan 12, 2024
Subina Khanal, Seshu Tirupathi, Giulio Zizzo, Ambrish Rawat, Torben Bach Pedersen

Viaarxiv icon

FairSISA: Ensemble Post-Processing to Improve Fairness of Unlearning in LLMs

Dec 12, 2023
Swanand Ravindra Kadhe, Anisa Halimi, Ambrish Rawat, Nathalie Baracaldo

Viaarxiv icon

Privacy-Preserving Federated Learning over Vertically and Horizontally Partitioned Data for Financial Anomaly Detection

Oct 30, 2023
Swanand Ravindra Kadhe, Heiko Ludwig, Nathalie Baracaldo, Alan King, Yi Zhou, Keith Houck, Ambrish Rawat, Mark Purcell, Naoise Holohan, Mikio Takeuchi, Ryo Kawahara, Nir Drucker, Hayim Shaul, Eyal Kushnir, Omri Soceanu

Viaarxiv icon

Matching Pairs: Attributing Fine-Tuned Models to their Pre-Trained Large Language Models

Jun 15, 2023
Myles Foley, Ambrish Rawat, Taesung Lee, Yufang Hou, Gabriele Picco, Giulio Zizzo

Figure 1 for Matching Pairs: Attributing Fine-Tuned Models to their Pre-Trained Large Language Models
Figure 2 for Matching Pairs: Attributing Fine-Tuned Models to their Pre-Trained Large Language Models
Figure 3 for Matching Pairs: Attributing Fine-Tuned Models to their Pre-Trained Large Language Models
Figure 4 for Matching Pairs: Attributing Fine-Tuned Models to their Pre-Trained Large Language Models
Viaarxiv icon

Robust Learning Protocol for Federated Tumor Segmentation Challenge

Dec 16, 2022
Ambrish Rawat, Giulio Zizzo, Swanand Kadhe, Jonathan P. Epperlein, Stefano Braghin

Figure 1 for Robust Learning Protocol for Federated Tumor Segmentation Challenge
Figure 2 for Robust Learning Protocol for Federated Tumor Segmentation Challenge
Figure 3 for Robust Learning Protocol for Federated Tumor Segmentation Challenge
Figure 4 for Robust Learning Protocol for Federated Tumor Segmentation Challenge
Viaarxiv icon

Federated Unlearning: How to Efficiently Erase a Client in FL?

Jul 12, 2022
Anisa Halimi, Swanand Kadhe, Ambrish Rawat, Nathalie Baracaldo

Figure 1 for Federated Unlearning: How to Efficiently Erase a Client in FL?
Figure 2 for Federated Unlearning: How to Efficiently Erase a Client in FL?
Figure 3 for Federated Unlearning: How to Efficiently Erase a Client in FL?
Viaarxiv icon

Challenges and Pitfalls of Bayesian Unlearning

Jul 07, 2022
Ambrish Rawat, James Requeima, Wessel Bruinsma, Richard Turner

Figure 1 for Challenges and Pitfalls of Bayesian Unlearning
Figure 2 for Challenges and Pitfalls of Bayesian Unlearning
Figure 3 for Challenges and Pitfalls of Bayesian Unlearning
Viaarxiv icon

Towards an Accountable and Reproducible Federated Learning: A FactSheets Approach

Feb 25, 2022
Nathalie Baracaldo, Ali Anwar, Mark Purcell, Ambrish Rawat, Mathieu Sinn, Bashar Altakrouri, Dian Balta, Mahdi Sellami, Peter Kuhn, Ulrich Schopp, Matthias Buchinger

Figure 1 for Towards an Accountable and Reproducible Federated Learning: A FactSheets Approach
Figure 2 for Towards an Accountable and Reproducible Federated Learning: A FactSheets Approach
Figure 3 for Towards an Accountable and Reproducible Federated Learning: A FactSheets Approach
Figure 4 for Towards an Accountable and Reproducible Federated Learning: A FactSheets Approach
Viaarxiv icon

Certified Federated Adversarial Training

Dec 20, 2021
Giulio Zizzo, Ambrish Rawat, Mathieu Sinn, Sergio Maffeis, Chris Hankin

Figure 1 for Certified Federated Adversarial Training
Figure 2 for Certified Federated Adversarial Training
Figure 3 for Certified Federated Adversarial Training
Figure 4 for Certified Federated Adversarial Training
Viaarxiv icon