activity
20152025
most citedSafe Exploration in Continuous Action Spaces

275 citations · 338 across the 13 of their papers we have counts for

collaborators
Showing cs.LGShow all

12 papers · 1 filter

cs.LG202116 cited

Improved Branch and Bound for Neural Network Verification via Lagrangian Decomposition

Alessandro De Palma, Rudy Bunel, Alban Desmaison +4

We improve the scalability of Branch and Bound (BaB) algorithms for formally proving input-output properties of neural networks. First, we propose novel bounding algorithms based o…

cs.LG202015 cited

Autoencoding Variational Autoencoder

A. Taylan Cemgil, Sumedh Ghaisas, Krishnamurthy Dvijotham +2

Does a Variational AutoEncoder (VAE) consistently encode typical samples generated from its decoder? This paper shows that the perhaps surprising answer to this question is `No'; a…

cs.LG20202 cited

Towards transformation-resilient provenance detection of digital media

Jamie Hayes, Krishnamurthy, Dvijotham +4

Advancements in deep generative models have made it possible to synthesize images, videos and audio signals that are difficult to distinguish from natural signals, creating opportu…

cs.LG202014 cited

Enabling certification of verification-agnostic networks via memory-efficient semidefinite programming

Sumanth Dathathri, Krishnamurthy Dvijotham, Alexey Kurakin +8

Convex relaxations have emerged as a promising approach for verifying desirable properties of neural networks like robustness to adversarial perturbations. Widely used Linear Progr…

cs.LG2020

Lagrangian Decomposition for Neural Network Verification

Rudy Bunel, Alessandro De Palma, Alban Desmaison +4

A fundamental component of neural network verification is the computation of bounds on the values their outputs can take. Previous methods have either used off-the-shelf solvers, d…

cs.LG2019

Achieving Robustness in the Wild via Adversarial Mixing with Disentangled Representations

Sven Gowal, Chongli Qin, Po-Sen Huang +4

Recent research has made the surprising finding that state-of-the-art deep learning models sometimes fail to generalize to small variations of the input. Adversarial training has b…