AIConfPaper
← Search

Robert Stanforth

9 accepted papers

2024

Expressive Losses for Verified Robustness via Convex Combinations

Alessandro De Palma, Rudy R Bunel, Krishnamurthy Dj Dvijotham, M. Pawan Kumar, Robert Stanforth, Alessio Lomuscio
ICLR 2024poster

In order to train networks for verified adversarial robustness, it is common to over-approximate the worst-case loss over perturbation regions, resulting in networks that attain verifiability at the expense of standard performance. As shown in recent work, better trade-offs between accuracy and robu…

Cited by 13Source ↗PDF ↗code ↗Scholar ↗
2021

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

Leonard Berrada, Sumanth Dathathri, Krishnamurthy Dj Dvijotham, Robert Stanforth, Rudy R Bunel, Jonathan Uesato +2
NeurIPS 2021spotlight

Most real world applications require dealing with stochasticity like sensor noise or predictive uncertainty, where formal specifications of desired behavior are inherently probabilistic. Despite the promise of formal verification in ensuring the reliability of neural networks, progress in the direc…

Cited by 21Source ↗PDF ↗code ↗Scholar ↗
2020

Towards Stable and Efficient Training of Verifiably Robust Neural Networks

Huan Zhang, Hongge Chen, Chaowei Xiao, Sven Gowal, Robert Stanforth, Bo Li +2
ICLR 2020poster

Training neural networks with verifiable robustness guarantees is challenging. Several existing approaches utilize linear relaxation based neural network output bounds under perturbation, but they can slow down training by a factor of hundreds depending on the underlying network architectures. Meanw…

Cited by 396Source ↗Scholar ↗
2020

Towards Verified Robustness under Text Deletion Interventions

Johannes Welbl, Po-Sen Huang, Robert Stanforth, Sven Gowal, Krishnamurthy (Dj) Dvijotham, Martin Szummer +1
ICLR 2020poster

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. This paper aims to tackle under-sensitivity in th…

Cited by 3Source ↗Scholar ↗
2019

Adversarial Robustness through Local Linearization

Chongli Qin, James Martens, Sven Gowal, Dilip Krishnan, Krishnamurthy Dvijotham, Alhussein Fawzi +3
NeurIPS 2019poster

Adversarial training is an effective methodology for training deep neural networks that are robust against adversarial, norm-bounded perturbations. However, the computational cost of adversarial training grows prohibitively as the size of the model and number of input dimensions increase. Further, t…

Cited by 367Source ↗PDF ↗Scholar ↗
2019

Are Labels Required for Improving Adversarial Robustness?

Jean-Baptiste Alayrac, Jonathan Uesato, Po-Sen Huang, Alhussein Fawzi, Robert Stanforth, Pushmeet Kohli
NeurIPS 2019poster

Recent work has uncovered the interesting (and somewhat surprising) finding that training models to be invariant to adversarial perturbations requires substantially larger datasets than those required for standard classification. This result is a key hurdle in the deployment of robust machine learni…

Cited by 410Source ↗PDF ↗code ↗Scholar ↗
2019

Efficient Neural Network Verification with Exactness Characterization

Krishnamurthy (Dj) Dvijotham, Robert Stanforth, Sven Gowal, Chongli Qin, Soham De, Pushmeet Kohli
UAI 2019poster

Remarkable progress has been made on verification of neural networks, i.e., showing that neural networks are provably consistent with specifications encoding properties like adversarial robustness. Recent methods developed for scalable neural network verification are based on computing an upper bou…

Cited by 35Source ↗PDF ↗Scholar ↗
2019

Scalable Verified Training for Provably Robust Image Classification

Sven Gowal, Krishnamurthy (Dj) Dvijotham, Robert Stanforth, Rudy Bunel, Chongli Qin, Jonathan Uesato +3
ICCV 2019poster

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 minimizing an upper bound on the worst-case loss over all possible adversarial perturbations. While these techniques show pro…

Cited by 214PDF ↗Scholar ↗
2019

Verification of Non-Linear Specifications for Neural Networks

Chongli Qin, Krishnamurthy (Dj) Dvijotham, Brendan O'Donoghue, Rudy Bunel, Robert Stanforth, Sven Gowal +3
ICLR 2019poster

Prior work on neural network verification has focused on specifications that are linear functions of the output of the network, e.g., invariance of the classifier output under adversarial perturbations of the input. In this paper, we extend verification algorithms to be able to certify richer proper…

Cited by 50Source ↗PDF ↗Scholar ↗