Vasisht Duddu
Ph.D. Student, Computer Science
Secure Systems Group
Cheriton School of Computer Science
CrySP Lab, University of Waterloo
vasisht.duddu at uwaterloo.ca



Home Publications Talks CV

Publications

Pre-Prints

• Combining Machine Learning Defenses without Conflicts Paper Code
  Vasisht Duddu, Rui Zhang, N. Asokan
  Under Submission


• LLM-CI: Assessing Contextual Integrity Norms in Language Models Paper Code
  Yan Shvartzshnaider, Vasisht Duddu, John Lacalamita
  Under Submission


• Laminator: Verifiable ML Property Cards using Hardware-assisted Attestations Paper Code Poster @ S&P'24
  Vasisht Duddu, Oskari Järvinen, Lachlan J. Gunn, N. Asokan
  Under Submission


• Espresso: Robust Concept Filtering in Text-to-Image Models Paper Code
  Anudeep Das, Vasisht Duddu, Rui Zhang, N. Asokan
  Under Submission

2024

• SoK: Unintended Interactions among Machine Learning Defenses and Risks Paper Code Blog
  Vasisht Duddu, Sebastian Szyller, N. Asokan
  IEEE S&P'24 IEEE Symposium on Security and Privacy ( Distinguished Paper Award) News
  Industry Impact: Amulet: A Library for Evaluating Interactions among ML Defenses and Risks Code


• GrOVe: Ownership Verification of Graph Neural Networks using Embeddings Paper Code
  Asim Waheed, Vasisht Duddu, N. Asokan
  IEEE S&P'24 IEEE Symposium on Security and Privacy


• Attesting Distributional Properties of Training Data for Machine Learning Paper Code
  Vasisht Duddu, Anudeep Das, Nora Khayata, Hossein Yalame, Thomas Schneider, N. Asokan
  ESORICS'24 European Symposium on Research in Computer Security


• On the Alignment of Group Fairness with Attribute Privacy Paper Code
  Jan Aalmoes, Vasisht Duddu, Antoine Boutet
  WISE'24 International Web Information Systems Engineering Conference

2023

• Comprehension from Chaos: What Users Understand and Expect from Private Computation Paper Code
  Bailey Kacsmar, Vasisht Duddu, Kyle Tilbury, Blase Ur, Florian Kerschbaum
  ACM CCS'23 ACM Conference on Computer and Communications Security

2022

• Inferring Sensitive Attributes from Model Explanations Paper Code
  Vasisht Duddu, Antoine Boutet
  ACM CIKM'22 ACM International Conference on Information and Knowledge Management


• Towards Privacy Aware Deep Learning for Embedded Systems Paper Code
  Vasisht Duddu, Antoine Boutet, Virat Shejwalkar
  ACM SAC'22 ACM Symposium On Applied Computing
  NeurIPS PPML'20 Workshop on Privacy Preserving Machine Learning

2021

• Good Artists Copy, Great Artists Steal: Model Extraction Attacks Against Image Translation GANs Paper Code
  Sebastian Szyller, Vasisht Duddu, Tommi Gröndahl, N. Asokan
  Technical Report'21

2020

• Quantifying Privacy Leakage in Graph Embedding Paper Code
  Vasisht Duddu, Antoine Boutet, Virat Shejwalkar
  MobiQuitous'20 EAI International Conference on Mobile and Ubiquitous Systems
  NeurIPS PPML'20 Workshop on Privacy Preserving Machine Learning


• Fault Tolerance of Neural Networks in Adversarial Settings Paper Code
  Vasisht Duddu, N. Rajesh Pillai, D. Vijay Rao, Valentina E. Balas
  JIFS'20 Journal of Intelligent & Fuzzy Systems


• Towards Enhancing Fault Tolerance in Neural Networks Paper Code
  Vasisht Duddu, D. Vijay Rao, Valentina E. Balas
  MobiQuitous'20 EAI International Conference on Mobile and Ubiquitous Systems


• Quantifying (Hyper) Parameter Leakage in Machine Learning Paper Code
  Vasisht Duddu, D. Vijay Rao
  IEEE BigMM'20 IEEE International Conference on Multimedia Big Data

2018

• Stealing Neural Networks via Timing Side Channels Paper
  Vasisht Duddu, Debasis Samanta, D Vijay Rao, Valentina E. Balas
  Technical Report'18

Theses

• Towards Effective Measurement of Membership Privacy Risk for Machine Learning Models Thesis
  Vasisht Duddu
  Master's Thesis, University of Waterloo, 2022
  Technical Report'21 SHAPr: An Efficient and Versatile Membership Privacy Risk Metric for Machine Learning
  Vasisht Duddu, Sebastian Szyller, N. Asokan