Publications

Here are a few selected publications. You can also see them on Google Scholar or dblp. * indicates author order alphabetical.

Dissertations

• “New Directions in Efficient Privacy-Preserving Machine Learning”
  Sameer Wagh
  PhD Thesis
  [PDF]

Conference Publications

• A General Framework of Homomorphic Encryption for Multiple Parties with Non-Interactive Key-Aggregation
  Hyesun Kwak*, Dongwon Lee*, Yongsoo Song*, Sameer Wagh*
  International Conference on Applied Cryptography and Network Security (ACNS) 2024
  [PDF]

• ELSA: Secure Aggregation for Federated Learning with Malicious Actors
  Mayank Rathee, Conghao Shen, Sameer Wagh, Raluca Ada Popa
  IEEE Symposium on Security and Privacy 2023
  [PDF]

• Piranha: A GPU Platform for Secure Computation
  Jean-Luc Watson, Sameer Wagh, Raluca Ada Popa
  USENIX Security Symposium (USENIX) 2022
  [PDF] [Code]

• Pika: Secure Computation using Function Secret Sharing over Rings
  Sameer Wagh
  Privacy Enhancing Technologies Symposium (PETS) 2022
  [PDF]

• BarnOwl: Secure Comparisons using Silent Pseudorandom Correlation Generators
  Sameer Wagh
  Tech Report, 2022
  [PDF]

• “Towards Probabilistic Verification of Machine Unlearning”
  David Marco Sommer, Liwei Song, Sameer Wagh, Prateek Mittal
  Privacy Enhancing Technologies Symposium (PETS) 2022
  [PDF] [Code]

• Rabbit: Efficient Comparison for Secure Multi-Party Computation
  Eleftheria Makri*, Dragoș Rotaru*, Frederik Vercauteren*, Sameer Wagh*
  Financial Cryptography and Data Security (FC) 2021.
  [PDF] [Code]

• “Maliciously Secure Matrix Multiplication with Applications to Private Deep Learning”
  Hao Chen*, Miran Kim*, Ilya Razenshteyn*, Dragoș Rotaru*, Yongsoo Song*, Sameer Wagh*
  Annual International Conference on the Theory and Application of Cryptology and Information Security (AsiaCrypt) 2020
  [PDF] [Code]

• “FALCON: Honest-Majority Maliciously Secure Framework for Private Deep Learning”
  Sameer Wagh, Shruti Tople, Fabrice Benhamouda, Eyal Kushilevitz, Prateek Mittal, Tal Rabin
  Privacy Enhancing Technologies Symposium (PETS) 2021
  [PDF] [Qualcomm Award] [Facebook Award] [📌News] [📌News] [Code]

• “DP-Cryptography: Marrying Differential Privacy and Cryptography in Emerging Applications”
  Sameer Wagh, Xi He, Ashwin Machanavajjhala, Prateek Mittal
  Communications of the ACM (CACM) 2021
  [PDF]

• “Guard Placement Attacks on Path Selection Algorithms for Tor”
  Gerry Wan, Aaron Johnson, Ryan Wails, Sameer Wagh, Prateek Mittal
  Privacy Enhancing Technologies Symposium (PETS) 2019
  [PDF] [Code]

• “SecureNN: 3-Party Secure Computation for Neural Network Training”
  Sameer Wagh, Divya Gupta, Nishanth Chandran
  Privacy Enhancing Technologies Symposium (PETS) 2019
  [PDF] [Code] [💥Impact] [💥Impact]

• “DPSelect: A Differential Privacy Based Guard Relay Selection Algorithm for Tor”
  Hans Hanley, Yixin Sun, Sameer Wagh, Prateek Mittal
  Privacy Enhancing Technologies Symposium (PETS) 2019
  [PDF]

• “Differentially Private Oblivious RAM”
  Sameer Wagh, Paul Cuff, Prateek Mittal
  Privacy Enhancing Technologies Symposium (PETS) 2018
  [PDF] [Code] [📌News]

• “The Pyramid Scheme: Oblivious RAM for Trusted Processors”
  Olya Ohrimenko, Lawrence Esswood, Sameer Wagh, Felix Schuster, Manuel Costa
  Tech Report, 2017
  [PDF]

• “Camouflage: Memory Traffic Shaping to Mitigate Timing Attacks”
  Yanqi Zhou, Sameer Wagh, Prateek Mittal, David Wentzlaff
  International Symposium on High Performance Computer Architecture (HPCA) 2017
  [PDF]

Patents

• Code Analysis for Sensitive Data using LLMs
  Sameer Wagh, Kartik Chopra, and Sid Roy
  [Serial Number: 18/484,058]

• Federated Learning Platform and Methods for using same
  Sameer Wagh, Kartik Chopra, and Sid Roy
  [Serial Number: 18/447,874]

• Private Deep Neural Network Training
  Sameer Wagh, Divya Gupta, Nishanth Chandran
  [U.S. patent 10,460,234]

• Tunable Oblivious RAM
  Sameer Wagh, Paul Cuff, Prateek Mittal
  [US Patent]

Talks

• “Data Science Without Data: An industry Perspective”
  [Invited, Charles L. and Ann Lee Brown Distinguished Seminar Series, Virginia, USA]

• “Pika: Secure Computation using Function Secret Sharing over Rings”
  [PETS, Australia]

• “गोपनीयता और संगणना (Privacy and Computation)”
  [Mahatma Gandhi Antarrashtriya Hindi VishwaVidyalaya]

• “Maliciously Secure Matrix Multiplication with Applications to Private Deep Learning”
  [AsiaCrypt, Korea (Remote)]

• “FALCON: Honest-Majority Maliciously Secure Framework for Private Deep Learning”
  [Facebook AI Systems Faculty Summit] [OpenMined Privacy Conference]

• “The Rise of Privacy Enhancing Technologies”
  [Microsoft Research, Redmond] [AI Research, JP Morgan] [Aarhus University] [Katholieke Universiteit te Leuven (KU Leuven)] [École polytechnique fédérale de Lausanne (EPFL)] [RISE Lab, University of California, Berkeley]

• “Private Deep Learning Made Practical”
  [Qualcomm, San Diego]

• “SecureNN: 3-Party Secure Computation for Neural Network Training”
  [IBM Research] [Deepmind, Google] [FAIR, Facebook] [PETS, Barcelona]

• “Differentially Private Oblivious RAM”
  [PETS, Barcelona]

Book Chapters

• Protecting Privacy through Homomorphic Encryption
  Editors: Kristen Lauter, Wei Dai, Kim Laine
  [Springer International Publishing]