Alessio Lomuscio
YOU?
Author Swipe
View article: Dynamic Back-Substitution in Bound-Propagation-Based Neural Network Verification
Dynamic Back-Substitution in Bound-Propagation-Based Neural Network Verification Open
We improve the efficacy of bound-propagation-based neural network verification by reducing the computational effort required by state-of-the-art propagation methods without incurring any loss in precision. We propose a method that infers t…
View article: Verification of Neural Networks Against Convolutional Perturbations via Parameterised Kernels
Verification of Neural Networks Against Convolutional Perturbations via Parameterised Kernels Open
We develop a method for the efficient verification of neural networks against convolutional perturbations such as blurring or sharpening. To define input perturbations, we use well-known camera shake, box blur and sharpen kernels. We linea…
View article: LTL Verification of Memoryful Neural Agents
LTL Verification of Memoryful Neural Agents Open
We present a framework for verifying Memoryful Neural Multi-Agent Systems (MN-MAS) against full Linear Temporal Logic (LTL) specifications. In MN-MAS, agents interact with a non-deterministic, partially observable environment. Examples of …
View article: A Scalable Approach to Probabilistic Neuro-Symbolic Robustness Verification
A Scalable Approach to Probabilistic Neuro-Symbolic Robustness Verification Open
Neuro-Symbolic Artificial Intelligence (NeSy AI) has emerged as a promising direction for integrating neural learning with symbolic reasoning. Typically, in the probabilistic variant of such systems, a neural network first extracts a set o…
View article: Verification of Neural Networks against Convolutional Perturbations via Parameterised Kernels
Verification of Neural Networks against Convolutional Perturbations via Parameterised Kernels Open
We develop a method for the efficient verification of neural networks against convolutional perturbations such as blurring or sharpening. To define input perturbations we use well-known camera shake, box blur and sharpen kernels. We demons…
View article: Verification of Geometric Robustness of Neural Networks via Piecewise Linear Approximation and Lipschitz Optimisation
Verification of Geometric Robustness of Neural Networks via Piecewise Linear Approximation and Lipschitz Optimisation Open
We address the problem of verifying neural networks against geometric transformations of the input image, including rotation, scaling, shearing, and translation. The proposed method computes provably sound piecewise linear constraints for …
View article: Verification of Geometric Robustness of Neural Networks via Piecewise Linear Approximation and Lipschitz Optimisation
Verification of Geometric Robustness of Neural Networks via Piecewise Linear Approximation and Lipschitz Optimisation Open
We address the problem of verifying neural networks against geometric transformations of the input image, including rotation, scaling, shearing, and translation. The proposed method computes provably sound piecewise linear constraints for …
View article: Tightening the Evaluation of PAC Bounds Using Formal Verification Results
Tightening the Evaluation of PAC Bounds Using Formal Verification Results Open
Probably Approximately Correct (PAC) bounds are widely used to derive probabilistic guarantees for the generalisation of machine learning models. They highlight the components of the model which contribute to its generalisation capacity. H…
View article: Tight Verification of Probabilistic Robustness in Bayesian Neural Networks
Tight Verification of Probabilistic Robustness in Bayesian Neural Networks Open
We introduce two algorithms for computing tight guarantees on the probabilistic robustness of Bayesian Neural Networks (BNNs). Computing robustness guarantees for BNNs is a significantly more challenging task than verifying the robustness …
View article: Verification of Semantic Key Point Detection for Aircraft Pose Estimation
Verification of Semantic Key Point Detection for Aircraft Pose Estimation Open
We analyse Semantic Segmentation Neural Networks running on an autonomous aircraft to estimate its 6DOF pose during landing. We show that automated reasoning techniques from neural network verification can be used to analyse the conditions…
View article: Iteratively Enhanced Semidefinite Relaxations for Efficient Neural Network Verification
Iteratively Enhanced Semidefinite Relaxations for Efficient Neural Network Verification Open
We propose an enhanced semidefinite program (SDP) relaxation to enable the tight and efficient verification of neural networks (NNs). The tightness improvement is achieved by introducing a nonlinear constraint to existing SDP relaxations p…
View article: Robust Training of Neural Networks against Bias Field Perturbations
Robust Training of Neural Networks against Bias Field Perturbations Open
We introduce the problem of training neural networks such that they are robust against a class of smooth intensity perturbations modelled by bias fields. We first develop an approach towards this goal based on a state-of-the-art robust tra…
View article: A Semidefinite Relaxation Based Branch-and-Bound Method for Tight Neural Network Verification
A Semidefinite Relaxation Based Branch-and-Bound Method for Tight Neural Network Verification Open
We introduce a novel method based on semidefinite program (SDP) for the tight and efficient verification of neural networks. The proposed SDP relaxation advances the present state of the art in SDP-based neural network verification by addi…
View article: Expressive Losses for Verified Robustness via Convex Combinations
Expressive Losses for Verified Robustness via Convex Combinations Open
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 show…
View article: Tight Neural Network Verification via Semidefinite Relaxations and Linear Reformulations
Tight Neural Network Verification via Semidefinite Relaxations and Linear Reformulations Open
We present a novel semidefinite programming (SDP) relaxation that enables tight and efficient verification of neural networks. The tightness is achieved by combining SDP relaxations with valid linear cuts, constructed by using the reformul…
View article: Approximating Perfect Recall when Model Checking Strategic Abilities: Theory and Applications
Approximating Perfect Recall when Model Checking Strategic Abilities: Theory and Applications Open
The model checking problem for multi-agent systems against specifications in the alternating-time temporal logic AT L, hence AT L∗ , under perfect recall and imperfect information is known to be undecidable. To tackle this problem, in this…
View article: Synthesizing Best-effort Strategies under Multiple Environment Specifications
Synthesizing Best-effort Strategies under Multiple Environment Specifications Open
We formally introduce and solve the synthesis problem for LTL goals in the case of multiple, even contradicting, assumptions about the environment. Our solution concept is based on ``best-effort strategies'' which are agent plans that, for…
View article: Efficient Neural Network Verification via Layer-based Semidefinite Relaxations and Linear Cuts
Efficient Neural Network Verification via Layer-based Semidefinite Relaxations and Linear Cuts Open
We introduce an efficient and tight layer-based semidefinite relaxation for verifying local robustness of neural networks. The improved tightness is the result of the combination between semidefinite relaxations and linear cuts. We obtain …
View article: Reasoning About Agents That May Know Other Agents’ Strategies
Reasoning About Agents That May Know Other Agents’ Strategies Open
We study the semantics of knowledge in strategic reasoning. Most existing works either implicitly assume that agents do not know one another’s strategies, or that all strategies are known to all; and some works present inconsistent mixes o…
View article: Towards Scalable Complete Verification of Relu Neural Networks via Dependency-based Branching
Towards Scalable Complete Verification of Relu Neural Networks via Dependency-based Branching Open
We introduce an efficient method for the complete verification of ReLU-based feed-forward neural networks. The method implements branching on the ReLU states on the basis of a notion of dependency between the nodes. This results in dividin…
View article: DEEPSPLIT: An Efficient Splitting Method for Neural Network Verification via Indirect Effect Analysis
DEEPSPLIT: An Efficient Splitting Method for Neural Network Verification via Indirect Effect Analysis Open
We propose a novel, complete algorithm for the verification and analysis of feed-forward, ReLU-based neural networks. The algorithm, based on symbolic interval propagation, introduces a new method for determining split-nodes which evaluate…
View article: Towards verifying neural autonomous systems
Towards verifying neural autonomous systems Open
In this talk I will offer a personal perspective on the increasing challenges and the correspondingly more powerful solutions being developed in the area of verification of autonomous system. I will ground the presentation on the work carr…
View article: Synthesizing strategies under expected and exceptional environment behaviors
Synthesizing strategies under expected and exceptional environment behaviors Open
We consider an agent that operates with two models of the environment: one that captures expected behaviors and one that captures additional exceptional behaviors. We study the problem of synthesizing agent strategies that enforce a goal a…
View article: Verifying Strategic Abilities of Neural-symbolic Multi-agent Systems
Verifying Strategic Abilities of Neural-symbolic Multi-agent Systems Open
We investigate the problem of verifying the strategic properties of multi-agent systems equipped with machine learning-based perception units. We introduce a novel model of agents comprising both a perception system implemented via feed-fo…
View article: Verifying Fault-Tolerance in Probabilistic Swarm Systems
Verifying Fault-Tolerance in Probabilistic Swarm Systems Open
We present a method for reasoning about fault-tolerance in unbounded robotic swarms. We introduce a novel semantics that accounts for the probabilistic nature of both the swarm and possible malfunctions, as well as the unbounded nature of …
View article: Model Checking Temporal Epistemic Logic under Bounded Recall
Model Checking Temporal Epistemic Logic under Bounded Recall Open
We study the problem of verifying multi-agent systems under the assumption of bounded recall. We introduce the logic CTLKBR, a bounded-recall variant of the temporal-epistemic logic CTLK. We define and study the model checking problem agai…