1 citations · 2 across the 5 of their papers we have counts for
7 papers
Statistically Undetectable Backdoors in Deep Neural Networks
Andrej Bogdanov, Alon Rosen, Neekon Vafa
We show how an adversarial model trainer can plant backdoors in a large class of deep, feedforward neural networks. These backdoors are statistically undetectable in the white-box…
Adaptive Robustness of Hypergrid Johnson-Lindenstrauss
Andrej Bogdanov, Alon Rosen, Neekon Vafa +1
Johnson and Lindenstrauss (Contemporary Mathematics, 1984) showed that for , a scaled random projection from to is an approximate…
Symmetric Perceptrons, Number Partitioning and Lattices
Neekon Vafa, Vinod Vaikuntanathan
The symmetric binary perceptron () problem with parameter is an average-case search problem defined as follows: given a random Gau…
Oblivious Defense in ML Models: Backdoor Removal without Detection
Shafi Goldwasser, Jonathan Shafer, Neekon Vafa +1
As society grows more reliant on machine learning, ensuring the security of machine learning systems against sophisticated attacks becomes a pressing concern. A recent result of Go…
Sparse Linear Regression and Lattice Problems
Aparna Gupte, Neekon Vafa, Vinod Vaikuntanathan
Sparse linear regression (SLR) is a well-studied problem in statistics where one is given a design matrix and a response vector for a -sp…
Continuous LWE is as Hard as LWE & Applications to Learning Gaussian Mixtures
Aparna Gupte, Neekon Vafa, Vinod Vaikuntanathan
We show direct and conceptually simple reductions between the classical learning with errors (LWE) problem and its continuous analog, CLWE (Bruna, Regev, Song and Tang, STOC 2021).…
Moonshine for All Finite Groups
Samuel DeHority, Xavier Gonzalez, Neekon Vafa +1
In recent literature, moonshine has been explored for some groups beyond the Monster, for example the sporadic O'Nan and Thompson groups. This collection of examples may suggest th…