Scholar
Vasisht Duddu
Google Scholar ID: oszzIkUAAAAJ
University of Waterloo
Trustworthy AI
AI Security
Data Privacy
AI Governance
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
566
H-index
11
i10-index
12
Publications
20
Co-authors
0
Publications
12 items
Trusted Model Environment for Private Semantic Computations
2026
Cited
0
"People can change, and patterns can be broken": Contextualizing Tradeoffs in Automated Decision-Making Systems
2026
Cited
0
SoK: Colluding Adversaries in Machine Learning Pipelines
2026
Cited
0
PAL*M: Property Attestation for Large Generative Models
2026
Cited
0
Locket: Robust Feature-Locking Technique for Language Models
2025
Cited
0
PATCH: Mitigating PII Leakage in Language Models with Privacy-Aware Targeted Circuit PatcHing
2025
Cited
0
Amulet: a Python Library for Assessing Interactions Among ML Defenses and Risks
2025
Cited
0
Position: Contextual Integrity Washing for Language Models
2025
Cited
0
Load more
