CS Theory Colloquium Series

Fall 2023

Monday, October 9th, 3:30pm, Harold Frank Hall (HFH) room 1132 Speaker: Vinod Vaikuntanathan (MIT) Title: Continuous Learning with Errors and Applications: Gaussian Mixtures and Undetectable Backdoors Abstract: I will describe two results at the interface of statistics, machine learning and cryptography both of which build on the recently formulated continuous learning with errors (CLWE) problem. First, I will show that CLWE is as hard as the widely studied (discrete) learning with errors (LWE) problem using techniques from leakage-resilient cryptography. In turn, I will use this to show the nearly optimal hardness of the long-studied Gaussian mixture learning problem. Secondly, I will show an application of CLWE to machine learning. In the increasingly common setting where the training of models is outsourced, I will describe a method whereby a malicious trainer can use cryptography to insert an *undetectable* backdoor in a classifier. Using a secret key, the trainer can then slightly alter inputs to create large deviations in the model output. Without the secret key, the existence of the backdoor is hidden. The talk is based on joint works with Shafi Goldwasser, Michael P. Kim and Or Zamir; and with Aparna Gupte and Neekon Vafa. Bio: Vinod Vaikuntanathan is a professor of computer science at MIT and the chief cryptographer at Duality Technologies. His research is in the foundations of cryptography and its applications to theoretical computer science at large. He is known for his work on fully homomorphic encryption, a powerful cryptographic primitive that enables complex computations on encrypted data, as well as lattice-based cryptography, which lays down a new mathematical foundation for cryptography in the post-quantum world. His work has been recognized with the Simons Investigator Award (2023), the GĂ¶del Prize (2022), the MIT Harold E. Edgerton Faculty Award (2018) and the Sloan faculty fellowship (2013). He holds SM and PhD degrees from MIT and a BTech degree from the Indian Institute of Technology Madras. |