activity
20152022
most citedAn Alternative Surrogate Loss for PGD-based Adversarial Testing

51 citations · 94 across the 8 of their papers we have counts for

collaborators
Showing cs.LGShow all

10 papers · 1 filter

cs.LG20206 cited

Balancing Constraints and Rewards with Meta-Gradient D4PG

Dan A. Calian, Daniel J. Mankowitz, Tom Zahavy +4

Deploying Reinforcement Learning (RL) agents to solve real-world applications often requires satisfying complex system constraints. Often the constraint thresholds are incorrectly…

cs.LG2020

Robust Constrained Reinforcement Learning for Continuous Control with Model Misspecification

Daniel J. Mankowitz, Dan A. Calian, Rae Jeong +5

Many real-world physical control systems are required to satisfy constraints upon deployment. Furthermore, real-world systems are often subject to effects such as non-stationarity,…

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…

cs.LG201951 cited

An Alternative Surrogate Loss for PGD-based Adversarial Testing

Sven Gowal, Jonathan Uesato, Chongli Qin +3

Adversarial testing methods based on Projected Gradient Descent (PGD) are widely used for searching norm-bounded perturbations that cause the inputs of neural networks to be miscla…

cs.LG201921 cited

A Bayesian Approach to Robust Reinforcement Learning

Esther Derman, Daniel Mankowitz, Timothy Mann +1

Robust Markov Decision Processes (RMDPs) intend to ensure robustness with respect to changing or adversarial system behavior. In this framework, transitions are modeled as arbitrar…

cs.LG2018

On the Effectiveness of Interval Bound Propagation for Training Verifiably Robust Models

Sven Gowal, Krishnamurthy Dvijotham, Robert Stanforth +6

Recent work has shown that it is possible to train deep neural networks that are provably robust to norm-bounded adversarial perturbations. Most of these methods are based on minim…