Scholar

Vasisht Duddu

Google Scholar ID: oszzIkUAAAAJ

University of Waterloo

Trustworthy AIAI SecurityData PrivacyAI Governance

Homepage↗Google Scholar↗

Citations & Impact

All-time

Citations

566

H-index

11

i10-index

12

Publications

20

Co-authors

0

Contact

No contact links provided.

Publications

9 items

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

Combining Machine Learning Defenses without Conflicts

arXiv.org · 2024

Cited

0

Investigating Privacy Bias in Training Data of Language Models

2024

Cited

1

Laminator: Verifiable ML Property Cards using Hardware-assisted Attestations

arXiv.org · 2024

Cited

0

Resume (English only)

Co-authors

0 total

Co-authors: 0 (list not available)