Search Results for author: Anvith Thudi

Found 10 papers, 2 papers with code

Unlearnable Algorithms for In-context Learning

no code implementations1 Feb 2024 Andrei Muresanu, Anvith Thudi, Michael R. Zhang, Nicolas Papernot

Machine unlearning is a desirable operation as models get increasingly deployed on data with unknown provenance.

In-Context Learning Language Modelling +2

Gradients Look Alike: Sensitivity is Often Overestimated in DP-SGD

no code implementations1 Jul 2023 Anvith Thudi, Hengrui Jia, Casey Meehan, Ilia Shumailov, Nicolas Papernot

Put all together, our evaluation shows that this novel DP-SGD analysis allows us to now formally show that DP-SGD leaks significantly less privacy for many datapoints (when trained on common benchmarks) than the current data-independent guarantee.

Training Private Models That Know What They Don't Know

no code implementations28 May 2023 Stephan Rabanser, Anvith Thudi, Abhradeep Thakurta, Krishnamurthy Dvijotham, Nicolas Papernot

Training reliable deep learning models which avoid making overconfident but incorrect predictions is a longstanding challenge.

Proof-of-Learning is Currently More Broken Than You Think

no code implementations6 Aug 2022 Congyu Fang, Hengrui Jia, Anvith Thudi, Mohammad Yaghini, Christopher A. Choquette-Choo, Natalie Dullerud, Varun Chandrasekaran, Nicolas Papernot

They empirically argued the benefit of this approach by showing how spoofing--computing a proof for a stolen model--is as expensive as obtaining the proof honestly by training the model.

Learning Theory

Selective Classification Via Neural Network Training Dynamics

no code implementations26 May 2022 Stephan Rabanser, Anvith Thudi, Kimia Hamidieh, Adam Dziedzic, Nicolas Papernot

Selective classification is the task of rejecting inputs a model would predict incorrectly on through a trade-off between input space coverage and model accuracy.

Classification

On the Necessity of Auditable Algorithmic Definitions for Machine Unlearning

no code implementations22 Oct 2021 Anvith Thudi, Hengrui Jia, Ilia Shumailov, Nicolas Papernot

Machine unlearning, i. e. having a model forget about some of its training data, has become increasingly more important as privacy legislation promotes variants of the right-to-be-forgotten.

Machine Unlearning

SoK: Machine Learning Governance

no code implementations20 Sep 2021 Varun Chandrasekaran, Hengrui Jia, Anvith Thudi, Adelin Travers, Mohammad Yaghini, Nicolas Papernot

The application of machine learning (ML) in computer systems introduces not only many benefits but also risks to society.

BIG-bench Machine Learning

Proof-of-Learning: Definitions and Practice

2 code implementations9 Mar 2021 Hengrui Jia, Mohammad Yaghini, Christopher A. Choquette-Choo, Natalie Dullerud, Anvith Thudi, Varun Chandrasekaran, Nicolas Papernot

In particular, our analyses and experiments show that an adversary seeking to illegitimately manufacture a proof-of-learning needs to perform *at least* as much work than is needed for gradient descent itself.

Cannot find the paper you are looking for? You can Submit a new open access paper.