280 citations · 665 across the 25 of their papers we have counts for
26 papers
SynthID-Image: Image watermarking at internet scale
Sven Gowal, Rudy Bunel, Florian Stimberg +23
We introduce SynthID-Image, a deep learning-based system for invisibly watermarking AI-generated imagery. This paper documents the technical desiderata, threat models, and practica…
Verified Neural Compressed Sensing
Rudy Bunel, Krishnamurthy Dvijotham, M. Pawan Kumar +2
We develop the first (to the best of our knowledge) provably correct neural networks for a precise computational task, with the proof of correctness generated by an automated verif…
Expressive Losses for Verified Robustness via Convex Combinations
Alessandro De Palma, Rudy Bunel, Krishnamurthy Dvijotham +3
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 ve…
Efficient Error Certification for Physics-Informed Neural Networks
Francisco Eiras, Adel Bibi, Rudy Bunel +3
Recent work provides promising evidence that Physics-Informed Neural Networks (PINN) can efficiently solve partial differential equations (PDE). However, previous works have failed…
DRIP: Domain Refinement Iteration with Polytopes for Backward Reachability Analysis of Neural Feedback Loops
Michael Everett, Rudy Bunel, Shayegan Omidshafiei
Safety certification of data-driven control techniques remains a major open problem. This work investigates backward reachability as a framework for providing collision avoidance g…
IBP Regularization for Verified Adversarial Robustness via Branch-and-Bound
Alessandro De Palma, Rudy Bunel, Krishnamurthy Dvijotham +2
Recent works have tried to increase the verifiability of adversarially trained networks by running the attacks over domains larger than the original perturbations and adding variou…
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…
Make Sure You're Unsure: A Framework for Verifying Probabilistic Specifications
Leonard Berrada, Sumanth Dathathri, Krishnamurthy Dvijotham +5
Most real world applications require dealing with stochasticity like sensor noise or predictive uncertainty, where formal specifications of desired behavior are inherently probabil…
Scaling the Convex Barrier with Sparse Dual Algorithms
Alessandro De Palma, Harkirat Singh Behl, Rudy Bunel +2
Tight and efficient neural network bounding is crucial to the scaling of neural network verification systems. Many efficient bounding algorithms have been presented recently, but t…
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…
An efficient nonconvex reformulation of stagewise convex optimization problems
Rudy Bunel, Oliver Hinder, Srinadh Bhojanapalli +2
Convex optimization problems with staged structure appear in several contexts, including optimal control, verification of deep neural networks, and isotonic regression. Off-the-she…
Contrastive Training for Improved Out-of-Distribution Detection
Jim Winkens, Rudy Bunel, Abhijit Guha Roy +10
Reliable detection of out-of-distribution (OOD) inputs is increasingly understood to be a precondition for deployment of machine learning systems. This paper proposes and investiga…
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…
Branch and Bound for Piecewise Linear Neural Network Verification
Rudy Bunel, Jingyue Lu, Ilker Turkaslan +3
The success of Deep Learning and its potential use in many safety-critical applications has motivated research on formal verification of Neural Network (NN) models. In this context…
Knowing When to Stop: Evaluation and Verification of Conformity to Output-size Specifications
Chenglong Wang, Rudy Bunel, Krishnamurthy Dvijotham +3
Models such as Sequence-to-Sequence and Image-to-Sequence are widely used in real world applications. While the ability of these neural architectures to produce variable-length out…
Verification of Non-Linear Specifications for Neural Networks
Chongli Qin, Krishnamurthy, Dvijotham +7
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 adve…
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…
Leveraging Grammar and Reinforcement Learning for Neural Program Synthesis
Rudy Bunel, Matthew Hausknecht, Jacob Devlin +2
Program synthesis is the task of automatically generating a program consistent with a specification. Recent years have seen proposal of a number of neural approaches for program sy…
Efficient Relaxations for Dense CRFs with Sparse Higher Order Potentials
Thomas Joy, Alban Desmaison, Thalaiyasingam Ajanthan +5
Dense conditional random fields (CRFs) have become a popular framework for modelling several problems in computer vision such as stereo correspondence and multi-class semantic segm…
A Unified View of Piecewise Linear Neural Network Verification
Rudy Bunel, Ilker Turkaslan, Philip H. S. Torr +2
The success of Deep Learning and its potential use in many safety-critical applications has motivated research on formal verification of Neural Network (NN) models. Despite the rep…
Neural Program Meta-Induction
Jacob Devlin, Rudy Bunel, Rishabh Singh +2
Most recently proposed methods for Neural Program Induction work under the assumption of having a large set of input/output (I/O) examples for learning any underlying input-output…
Learning to superoptimize programs - Workshop Version
Rudy Bunel, Alban Desmaison, M. Pawan Kumar +2
Superoptimization requires the estimation of the best program for a given computational task. In order to deal with large programs, superoptimization techniques perform a stochasti…
Efficient Linear Programming for Dense CRFs
Thalaiyasingam Ajanthan, Alban Desmaison, Rudy Bunel +3
The fully connected conditional random field (CRF) with Gaussian pairwise potentials has proven popular and effective for multi-class semantic segmentation. While the energy of a d…
Learning to superoptimize programs
Rudy Bunel, Alban Desmaison, M. Pawan Kumar +2
Code super-optimization is the task of transforming any given program to a more efficient version while preserving its input-output behaviour. In some sense, it is similar to the p…