Scholar
Chhavi Yadav
Google Scholar ID: -fhMN10AAAAJ
UC San Diego
Citations & Impact
Citations
291
H-index
6
i10-index
5
Publications
14
Co-authors
7
list available
Publications
Resume (English only)
Academic Achievements
- Paper 'FairProof: Confidential and Certifiable Fairness for Neural Networks' won the TensorOpera-FedML Best Paper Award at Privacy-ILR Workshop, ICLR 2024
- Paper 'Cold Case: The Lost MNIST Digits' received a Spotlight Oral Presentation (~2.9%) at NeurIPS 2019
- Paper 'On the design of CNNs for automatic detection of Alzheimer’s disease' received Best Paper Honorable Mention at NeurIPS 2019 ML for Health Workshop
- Received the 'Contributions to Diversity' Award from CSE Dept, UCSD in June 2024
- Selected as a Rising Star in Data Science 2024
- Serving on the Program Committee of SaTML'25
- Published multiple papers at top venues including ICML 2024, NeurIPS 2024, IJCAI 2024, NAACL 2023, and ECML PKDD 2021 on topics such as interpretability, model auditing, fairness, and unlearning
Background
- AI researcher broadly interested in the foundations of Trustworthy AI
- Focuses on AI Privacy, Security & Safety
- Aims to make AI systems accountable and incentive-aware by exposing vulnerabilities in existing Trustworthy AI tools (e.g., unlearning, attribution, XAI)
- Develops trustless verification systems using cryptographic tools like Zero-Knowledge Proofs
- Studies auditing of closed models both theoretically and practically
- Proposes evaluation frameworks and metrics for trustworthy AI
