Search Results for author:
Found 25 papers, 9 papers with code
Expressive Losses for Verified Robustness via Convex Combinations
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.
Provably Correct Physics-Informed Neural Networks
Recent work provides promising evidence that Physics-informed neural networks (PINN) can efficiently solve partial differential equations (PDE).
DRIP: Domain Refinement Iteration with Polytopes for Backward Reachability Analysis of Neural Feedback Loops
To address this issue, we introduce DRIP, an algorithm with a refinement loop on the relaxation domain, which substantially tightens the BP set bounds.
IBP Regularization for Verified Adversarial Robustness via Branch-and-Bound
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 various regularization terms to the objective.
Improved Branch and Bound for Neural Network Verification via Lagrangian Decomposition
Finally, we design a BaB framework, named Branch and Dual Network Bound (BaDNB), based on our novel bounding and branching algorithms.
Make Sure You're Unsure: A Framework for Verifying Probabilistic Specifications
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).
Scaling the Convex Barrier with Sparse Dual Algorithms
Tight and efficient neural network bounding is crucial to the scaling of neural network verification systems.
An efficient nonconvex reformulation of stagewise convex optimization problems
We establish theoretical properties of the nonconvex formulation, showing that it is (almost) free of spurious local minima and has the same global optimum as the convex problem.
Enabling certification of verification-agnostic networks via memory-efficient semidefinite programming
In this work, we propose a first-order dual SDP algorithm that (1) requires memory only linear in the total number of network activations, (2) only requires a fixed number of forward/backward passes through the network per iteration.
Contrastive Training for Improved Out-of-Distribution Detection
Reliable detection of out-of-distribution (OOD) inputs is increasingly understood to be a precondition for deployment of machine learning systems.
Ranked #12 on
Out-of-Distribution Detection
on CIFAR-100 vs CIFAR-10
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
Lagrangian Decomposition for Neural Network Verification
Both the algorithms offer three advantages: (i) they yield bounds that are provably at least as tight as previous dual algorithms relying on Lagrangian relaxations; (ii) they are based on operations analogous to forward/backward pass of neural networks layers and are therefore easily parallelizable, amenable to GPU implementation and able to take advantage of the convolutional structure of problems; and (iii) they allow for anytime stopping while still providing valid bounds.
Branch and Bound for Piecewise Linear Neural Network Verification
We use the data sets to conduct a thorough experimental comparison of existing and new algorithms and to provide an inclusive analysis of the factors impacting the hardness of verification problems.
Knowing When to Stop: Evaluation and Verification of Conformity to Output-size Specifications
This behavior can have severe consequences such as usage of increased computation and induce faults in downstream modules that expect outputs of a certain length.
Verification of Non-Linear Specifications for Neural Networks
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
Recent work has shown that it is possible to train deep neural networks that are provably robust to norm-bounded adversarial perturbations.
Efficient Relaxations for Dense CRFs with Sparse Higher Order Potentials
The presented algorithms can be applied to any labelling problem using a dense CRF with sparse higher-order potentials.
Leveraging Grammar and Reinforcement Learning for Neural Program Synthesis
Program synthesis is the task of automatically generating a program consistent with a specification.
Piecewise Linear Neural Networks verification: A comparative study
Motivated by the need of accelerating progress in this very important area, we investigate the trade-offs of a number of different approaches based on Mixed Integer Programming, Satisfiability Modulo Theory, as well as a novel method based on the Branch-and-Bound framework.
A Unified View of Piecewise Linear Neural Network Verification
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.
Neural Program Meta-Induction
In our first proposal, portfolio adaptation, a set of induction models is pretrained on a set of related tasks, and the best model is adapted towards the new task using transfer learning.
Learning to superoptimize programs - Workshop Version
Superoptimization requires the estimation of the best program for a given computational task.
Efficient Linear Programming for Dense CRFs
To this end, we develop a proximal minimization framework, where the dual of each proximal problem is optimized via block coordinate descent.
Learning to superoptimize programs
This approach involves repeated sampling of modifications to the program from a proposal distribution, which are accepted or rejected based on whether they preserve correctness, and the improvement they achieve.
Efficient Continuous Relaxations for Dense CRF
In contrast to the continuous relaxation-based energy minimisation algorithms used for sparse CRFs, the mean-field algorithm fails to provide strong theoretical guarantees on the quality of its solutions.
Adaptive Neural Compilation
We show that it is possible to compile programs written in a low-level language to a differentiable representation.
