Hi! I'm Chhavi.

I'm an AI researcher, broadly interested in post-training, with a focus on AI Safety, Security & Privacy. These days I think about

(1) the risks of AI systems to society and ways to reduce the resulting harm,

(2) ways to make agents safe for deployment in practical tasks,

(3) how to make AI systems smarter, via enhanced reasoning and continual learning.

I am currently a postdoctoral researcher in the Machine Learning Department @CMU and a Fellow at Simons Institute, UC Berkeley.

I obtained a PhD in Computer Science from UC San Diego, advised by Prof. Kamalika Chaudhuri. I also organize events at 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. Influence-based Attributions can be Manipulated. Chhavi Yadav*, Ruihan Wu*, Kamalika Chaudhuri AISTATS 2026

2. Evaluating Deep Unlearning in Large Language Models. Ruihan Wu, Chhavi Yadav, Russ Salakhutdinov, Kamalika Chaudhuri SaTML 2026 (Code)

3. Research in Collaborative Learning Does Not Serve Cross-Silo Federated Learning in Practice SaTML 2026

4. Can we infer confidential properties of training data from LLMs? NeurIPS 2025 (Spotlight paper)

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

ICML 2025

6. 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

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

TMLR 2024, TrustAI Workshop IJCAI 2024 Oral

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

TrustNLP @NAACL 2023

9. 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

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

NeurIPS 2019 Spotlight Oral Presentation ~2.9%

11. 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 🎊