Vasisht Duddu
Distinguished Postdoctoral Fellow
Vector Institute for Artificial Intelligence
vasisht.duddu at outlook.com (see "Contact" below)



Home Publications Awards Talks Mentoring Service Blog CV

I am a distinguished postdoctoral fellow at Vector Institute for Artificial Intelligence advised by Tim Rudner and Xi He. I received my Ph.D. and Master’s in Computer Science from University of Waterloo advised by N. Asokan, and my undergraduate from IIIT-Delhi.

Research: I work on trustworthy machine learning systems by grounding my research in systems security principles:

• Assessing Risks: Define realistic threat models to evaluate risks to security, privacy, safety, fairness, transparency
• Designing Defenses: Formulate design requirements for defenses (e.g., effective, efficient, robust)
• Holistic System Analysis: Study interactions of ML models with system components
• Technical Governance: Design mechanisms for accountability and regulatory compliance

Selected Publications:

• Assessing Risks: ICML'25, PETS'26, ArXiv'26
• Designing Defenses: S&P'24, CODASPY'25 (best paper), EACL Findings'26, ACL'26
• Holistic System Analysis: CIKM'22, S&P'24 (distinguished paper), TMLR'25, USENIX SEC'26
• Technical Governance: CCS'23, ESORICS'24, CODASPY'25, ArXiv'26

Selected Research Awards (full list):

• ML and Systems Rising Star (2026) News News
• Best Paper Award @ ACM CODASPY (2025) News
• IBM PhD Fellowship (2024) News
• Distinguished Paper Award @ IEEE S&P (2024) News

Contact: You can reach me at {nvduddu, vasisht.duddu} [at] uwaterloo.ca, vasisht15137 [at] iiitd.ac.in (for sharing Google Docs), or vasisht.duddu [at] vectorinstitute.ai; all of these addresses forward to vasisht.duddu [at] outlook.com.