Defense Slides

Hi! I'm Chhavi.

I'm an AI researcher, broadly interested in the foundations of Trustworthy AI and AI Security & Safety. Specifically, I aim to make AI systems accountable by

• exposing vulnerabilities and understanding behavior of existing Trustworthy AI tools (unlearning, attribution, xai)

• developing trustless verification systems using cryptographic tools such as Zero-Knowledge Proofs ,

• studying auditing of closed models both theoretically and practically and,

• proposing evaluation frameworks and metrics.

I obtained a PhD in Computer Science from UC San Diego, advised by Prof. Kamalika Chaudhuri. I'm also a co-founder of The Trustworthy ML Initiative.

I'm open to collaborations! Please shoot me an email if you have a cool idea and want to work together :)

Selected Papers

For an up-to-date list, check out my Google Scholar Profile. * := equal contribution

1. ExpProof: Operationalizing Explanations for Confidential Models with ZKPs. Chhavi Yadav*, Evan Monroe Laufer*, Dan Boneh, Kamalika Chaudhuri

ICML 2025

2. Evaluating Deep Unlearning in Large Language Models. Ruihan Wu, Chhavi Yadav, Russ Salakhutdinov, Kamalika Chaudhuri (Code)

3. Influence-based Attributions can be Manipulated. Chhavi Yadav*, Ruihan Wu*, Kamalika Chaudhuri

RegML and ATTRIB workshops @Neurips 2024

4. FairProof : Confidential and Certifiable Fairness for Neural Networks. Chhavi Yadav, Amrita Roy Chowdhury, Dan Boneh, Kamalika Chaudhuri

ICML 2024 (Code)(Short Blog)

🏆 TensorOpera-FedML Best Paper Award @Privacy-ILR Workshop ICLR 2024

5. Keeping Up with the Language Models: Systematic Benchmark Extension for Bias Auditing. Ioana Baldini Soares, Chhavi Yadav, Payel Das, Kush Varshney

TrustNLP @NAACL 2023

6. XAudit : A Theoretical Look at Auditing with Explanations. Chhavi Yadav, Michal Moshkovitz, Kamalika Chaudhuri

TMLR 2024

TrustAI Workshop IJCAI 2024 Oral

7. Behavior of k-NN as an Instance-Based Explanation Method. Chhavi Yadav, Kamalika Chaudhuri

Advances in Interpretable Machine Learning and Artificial Intelligence @ ECML PKDD 2021 Oral

8. Cold Case : The Lost MNIST Digits. Chhavi Yadav, Leon Bottou 

NeurIPS 2019 Spotlight Oral Presentation ~2.9%

9. On the design of CNNs for automatic detection of Alzheimer’s disease. Sheng Liu, Chhavi Yadav, Carlos Fernandez-Granda, Narges Razavian

Machine Learning for Health Workshop , NeurIPS 2019 🏆 Best Paper Honorable Mention

Latest News

May 2025 : I've graduated!

Dec 2024  : I will be at NeurIPS, presenting my papers on, FairProof @RegML workshop & Influence-based Attributions @RegML, ATTRIB workshops 🎉

Nov 2024  : I will be attending the Rising Star in Data Science'24 workshop and will be presenting my work there.

Oct 2024  : I am giving a talk on FairProof at the Encore Institute!

Sep 2024  : I have been selected as a Rising Star in Data Science'24 🎉

Sep 2024  : Organizing a workshop on Interpretability at NeurIPS 2024! Please check out https://interpretable-ai-workshop.github.io/ for details! 🎉

Aug 2024  : I am serving on the Program Committee of SaTML'25.

Aug 2024  : I gave a talk on XAudit at IJCAI Trustworthy AI Workshop 2024.

July 2024 : I presented FairProof at ICML 2024.

June 2024 : Delighted to have received the "Contributions to Diversity" Award from the CSE Dept @UCSD 🎉

May 2024  : My work FairProof received a Best Paper Award at the Privacy Workshop @ICLR 2024 🎊