Search Results for author: Sven Gowal

Found 32 papers, 16 papers with code

Data Augmentation Can Improve Robustness

1 code implementation NeurIPS 2021 Sylvestre-Alvise Rebuffi, Sven Gowal, Dan A. Calian, Florian Stimberg, Olivia Wiles, Timothy Mann

Adversarial training suffers from robust overfitting, a phenomenon where the robust test accuracy starts to decrease during training.

Data Augmentation

A Fine-Grained Analysis on Distribution Shift

no code implementations ICLR 2022 Olivia Wiles, Sven Gowal, Florian Stimberg, Sylvestre Alvise-Rebuffi, Ira Ktena, Krishnamurthy Dvijotham, Taylan Cemgil

Despite this necessity, there has been little work in defining the underlying mechanisms that cause these shifts and evaluating the robustness of algorithms across multiple, different distribution shifts.

Improving Robustness using Generated Data

1 code implementation NeurIPS 2021 Sven Gowal, Sylvestre-Alvise Rebuffi, Olivia Wiles, Florian Stimberg, Dan Andrei Calian, Timothy Mann

Against $\ell_\infty$ norm-bounded perturbations of size $\epsilon = 8/255$, our models achieve 66. 10% and 33. 49% robust accuracy on CIFAR-10 and CIFAR-100, respectively (improving upon the state-of-the-art by +8. 96% and +3. 29%).

Adversarial Robustness

An Empirical Investigation of Learning from Biased Toxicity Labels

no code implementations4 Oct 2021 Neel Nanda, Jonathan Uesato, Sven Gowal

Collecting annotations from human raters often results in a trade-off between the quantity of labels one wishes to gather and the quality of these labels.

Fairness

Defending Against Image Corruptions Through Adversarial Augmentations

no code implementations ICLR 2022 Dan A. Calian, Florian Stimberg, Olivia Wiles, Sylvestre-Alvise Rebuffi, Andras Gyorgy, Timothy Mann, Sven Gowal

Modern neural networks excel at image classification, yet they remain vulnerable to common image corruptions such as blur, speckle noise or fog.

Image Classification

Fixing Data Augmentation to Improve Adversarial Robustness

4 code implementations2 Mar 2021 Sylvestre-Alvise Rebuffi, Sven Gowal, Dan A. Calian, Florian Stimberg, Olivia Wiles, Timothy Mann

In particular, against $\ell_\infty$ norm-bounded perturbations of size $\epsilon = 8/255$, our model reaches 64. 20% robust accuracy without using any external data, beating most prior works that use external data.

Adversarial Robustness Data Augmentation

Make Sure You're Unsure: A Framework for Verifying Probabilistic Specifications

1 code implementation NeurIPS 2021 Leonard Berrada, Sumanth Dathathri, Krishnamurthy Dvijotham, Robert Stanforth, Rudy Bunel, Jonathan Uesato, Sven Gowal, M. Pawan Kumar

In this direction, we first introduce a general formulation of probabilistic specifications for neural networks, which captures both probabilistic networks (e. g., Bayesian neural networks, MC-Dropout networks) and uncertain inputs (distributions over inputs arising from sensor noise or other perturbations).

Adversarial Robustness OOD Detection

Bridging the Gap Between Adversarial Robustness and Optimization Bias

1 code implementation17 Feb 2021 Fartash Faghri, Sven Gowal, Cristina Vasconcelos, David J. Fleet, Fabian Pedregosa, Nicolas Le Roux

We demonstrate that the choice of optimizer, neural network architecture, and regularizer significantly affect the adversarial robustness of linear neural networks, providing guarantees without the need for adversarial training.

Adversarial Robustness

Self-supervised Adversarial Robustness for the Low-label, High-data Regime

no code implementations ICLR 2021 Sven Gowal, Po-Sen Huang, Aaron van den Oord, Timothy Mann, Pushmeet Kohli

Experiments on CIFAR-10 against $\ell_2$ and $\ell_\infty$ norm-bounded perturbations demonstrate that BYORL achieves near state-of-the-art robustness with as little as 500 labeled examples.

Adversarial Robustness Self-Supervised Learning

Autoencoding Variational Autoencoder

1 code implementation7 Dec 2020 A. Taylan Cemgil, Sumedh Ghaisas, Krishnamurthy Dvijotham, Sven Gowal, Pushmeet Kohli

We provide experimental results on the ColorMnist and CelebA benchmark datasets that quantify the properties of the learned representations and compare the approach with a baseline that is specifically trained for the desired property.

The Autoencoding Variational Autoencoder

no code implementations NeurIPS 2020 Taylan Cemgil, Sumedh Ghaisas, Krishnamurthy Dvijotham, Sven Gowal, Pushmeet Kohli

We provide experimental results on the ColorMnist and CelebA benchmark datasets that quantify the properties of the learned representations and compare the approach with a baseline that is specifically trained for the desired property.

Uncovering the Limits of Adversarial Training against Norm-Bounded Adversarial Examples

4 code implementations7 Oct 2020 Sven Gowal, Chongli Qin, Jonathan Uesato, Timothy Mann, Pushmeet Kohli

In the setting with additional unlabeled data, we obtain an accuracy under attack of 65. 88% against $\ell_\infty$ perturbations of size $8/255$ on CIFAR-10 (+6. 35% with respect to prior art).

Adversarial Robustness

A FRAMEWORK FOR ROBUSTNESS CERTIFICATION OF SMOOTHED CLASSIFIERS USING F-DIVERGENCES

no code implementations ICLR 2020 Krishnamurthy (Dj) Dvijotham, Jamie Hayes, Borja Balle, Zico Kolter, Chongli Qin, Andras Gyorgy, Kai Xiao, Sven Gowal, Pushmeet Kohli

Formal verification techniques that compute provable guarantees on properties of machine learning models, like robustness to norm-bounded adversarial perturbations, have yielded impressive results.

Audio Classification Image Classification

Towards Verified Robustness under Text Deletion Interventions

no code implementations ICLR 2020 Johannes Welbl, Po-Sen Huang, Robert Stanforth, Sven Gowal, Krishnamurthy (Dj) Dvijotham, Martin Szummer, Pushmeet Kohli

Neural networks are widely used in Natural Language Processing, yet despite their empirical successes, their behaviour is brittle: they are both over-sensitive to small input changes, and under-sensitive to deletions of large fractions of input text.

Natural Language Inference Natural Language Processing

An empirical investigation of the challenges of real-world reinforcement learning

1 code implementation24 Mar 2020 Gabriel Dulac-Arnold, Nir Levine, Daniel J. Mankowitz, Jerry Li, Cosmin Paduraru, Sven Gowal, Todd Hester

We believe that an approach that addresses our set of proposed challenges would be readily deployable in a large number of real world problems.

Continuous Control reinforcement-learning

Achieving Robustness in the Wild via Adversarial Mixing with Disentangled Representations

no code implementations CVPR 2020 Sven Gowal, Chongli Qin, Po-Sen Huang, Taylan Cemgil, Krishnamurthy Dvijotham, Timothy Mann, Pushmeet Kohli

Specifically, we leverage the disentangled latent representations computed by a StyleGAN model to generate perturbations of an image that are similar to real-world variations (like adding make-up, or changing the skin-tone of a person) and train models to be invariant to these perturbations.

An Alternative Surrogate Loss for PGD-based Adversarial Testing

4 code implementations21 Oct 2019 Sven Gowal, Jonathan Uesato, Chongli Qin, Po-Sen Huang, Timothy Mann, Pushmeet Kohli

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 misclassified.

Scalable Neural Learning for Verifiable Consistency with Temporal Specifications

no code implementations25 Sep 2019 Sumanth Dathathri, Johannes Welbl, Krishnamurthy (Dj) Dvijotham, Ramana Kumar, Aditya Kanade, Jonathan Uesato, Sven Gowal, Po-Sen Huang, Pushmeet Kohli

Formal verification of machine learning models has attracted attention recently, and significant progress has been made on proving simple properties like robustness to small perturbations of the input features.

Adversarial Robustness Language Modelling

Adversarial Robustness through Local Linearization

no code implementations NeurIPS 2019 Chongli Qin, James Martens, Sven Gowal, Dilip Krishnan, Krishnamurthy Dvijotham, Alhussein Fawzi, Soham De, Robert Stanforth, Pushmeet Kohli

Using this regularizer, we exceed current state of the art and achieve 47% adversarial accuracy for ImageNet with l-infinity adversarial perturbations of radius 4/255 under an untargeted, strong, white-box attack.

Adversarial Defense Adversarial Robustness

Towards Stable and Efficient Training of Verifiably Robust Neural Networks

2 code implementations ICLR 2020 Huan Zhang, Hongge Chen, Chaowei Xiao, Sven Gowal, Robert Stanforth, Bo Li, Duane Boning, Cho-Jui Hsieh

In this paper, we propose a new certified adversarial training method, CROWN-IBP, by combining the fast IBP bounds in a forward bounding pass and a tight linear relaxation based bound, CROWN, in a backward bounding pass.

Verification of Non-Linear Specifications for Neural Networks

no code implementations ICLR 2019 Chongli Qin, Krishnamurthy, Dvijotham, Brendan O'Donoghue, Rudy Bunel, Robert Stanforth, Sven Gowal, Jonathan Uesato, Grzegorz Swirszcz, Pushmeet Kohli

We show that a number of important properties of interest can be modeled within this class, including conservation of energy in a learned dynamics model of a physical system; semantic consistency of a classifier's output labels under adversarial perturbations and bounding errors in a system that predicts the summation of handwritten digits.

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

9 code implementations30 Oct 2018 Sven Gowal, Krishnamurthy Dvijotham, Robert Stanforth, Rudy Bunel, Chongli Qin, Jonathan Uesato, Relja Arandjelovic, Timothy Mann, Pushmeet Kohli

Recent work has shown that it is possible to train deep neural networks that are provably robust to norm-bounded adversarial perturbations.

Training verified learners with learned verifiers

no code implementations25 May 2018 Krishnamurthy Dvijotham, Sven Gowal, Robert Stanforth, Relja Arandjelovic, Brendan O'Donoghue, Jonathan Uesato, Pushmeet Kohli

This paper proposes a new algorithmic framework, predictor-verifier training, to train neural networks that are verifiable, i. e., networks that provably satisfy some desired input-output properties.

A Dual Approach to Scalable Verification of Deep Networks

2 code implementations17 Mar 2018 Krishnamurthy, Dvijotham, Robert Stanforth, Sven Gowal, Timothy Mann, Pushmeet Kohli

In contrast, our framework applies to a general class of activation functions and specifications on neural network inputs and outputs.

Beyond Greedy Ranking: Slate Optimization via List-CVAE

1 code implementation ICLR 2019 Ray Jiang, Sven Gowal, Timothy A. Mann, Danilo J. Rezende

The conventional solution to the recommendation problem greedily ranks individual document candidates by prediction scores.

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