Hi! I'm Chhavi.
I'm a Machine Learning (ML) researcher, broadly interested in ML Security & Safety and the foundations of Trustworthy ML. My research is in trustless verification using cryptographic tools, evaluations & measurements, unlearning and explainability. Currently, I'm pursuing a PhD (final year) in the Computer Science & Engineering Department at 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 :)
I often get asked about the meaning & correct pronunciation of my name, so here you go : 'chhavi' means reflection (eg. you are your mother's 'chhavi' if your looks/mannerisms are like her) & is pronounced as ch uh v ih !
Latest News
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.
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 🎊
Selected Publications
For an up-to-date list, check out my Google Scholar Profile. * := equal contribution
Influence-based Attributions can be Manipulated. Chhavi Yadav*, Ruihan Wu*, Kamalika Chaudhuri
Under Submission
FairProof : Confidential and Certifiable Fairness for Neural Networks. Chhavi Yadav, Amrita Roy Chowdhury, Dan Boneh, Kamalika Chaudhuri
ICML 2024 (Code)
TensorOpera-FedML Best Paper Award @Privacy-ILR Workshop ICLR 2024
Keeping Up with the Language Models: Systematic Benchmark Extension for Bias Auditing. Ioana Baldini Soares, Chhavi Yadav, Payel Das, Kush Varshney
TrustNLP @NAACL 2023
A Learning-Theoretic Framework for Certified Auditing of Machine Learning Models. Chhavi Yadav, Michal Moshkovitz, Kamalika Chaudhuri
TMLR 2024
TrustAI Workshop IJCAI 2024 Oral
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
Cold Case : The Lost MNIST Digits. Chhavi Yadav, Leon Bottou
NeurIPS 2019 Spotlight Oral Presentation ~2.9%
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
Some shenanigans @ the PhDs