## About

177

Publications

15,834

Reads

**How we measure 'reads'**

A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more

2,005

Citations

Introduction

Additional affiliations

December 2006 - present

## Publications

Publications (177)

Vulnerability to adversarial attacks is one of the principal hurdles to the adoption of deep learning in safety-critical applications. Despite significant efforts, both practical and theoretical, training deep learning models robust to adversarial attacks is still an open problem. In this paper, we analyse the geometry of adversarial attacks in the...

Mean-field models are an established method to analyze large stochastic systems with N interacting objects by means of simple deterministic equations that are asymptotically correct when N tends to infinity. For finite N, mean-field equations provide an approximation whose accuracy is model- and parameter-dependent. Recent research has focused on r...

Model-checking for parametric stochastic models can be expressed as checking the satisfaction probability of a certain property as a function of the parameters of the model. Smoothed model checking (smMC) leverages Gaussian Processes (GP) to infer the satisfaction function over the entire parameter space from a limited set of observations obtained...

We introduce a similarity function on formulae of signal temporal logic (STL). It comes in the form of a kernel function, well known in machine learning as a conceptually and computationally efficient tool. The corresponding kernel trick allows us to circumvent the complicated process of feature extraction, i.e. the (typically manual) effort to ide...

Cyber-Physical Systems (CPS) consist of inter-wined computational (cyber) and physical components interacting through sensors and/or actuators. Computational elements are networked at every scale and can communicate with each other and with humans. Nodes can join and leave the network at any time or they can move to different spatial locations. In...

We introduce a similarity function on formulae of signal temporal logic (STL). It comes in the form of a kernel function , well known in machine learning as a conceptually and computationally efficient tool. The corresponding kernel trick allows us to circumvent the complicated process of feature extraction, i.e. the (typically manual) effort to id...

Monte Carlo estimation in plays a crucial role in stochastic reaction networks. However, reducing the statistical uncertainty of the corresponding estimators requires sampling a large number of trajectories. We propose control variates based on the statistical moments of the process to reduce the estimators' variances. We develop an algorithm that...

Markov Population Models are a widespread formalism used to model the dynamics of complex systems, with applications in Systems Biology and many other fields. The associated Markov stochastic process in continuous time is often analyzed by simulation, which can be costly for large or stiff systems, particularly when a massive number of simulations...

To understand the long-run behavior of Markov population models, the computation of the stationary distribution is often a crucial part. We propose a truncation-based approximation that employs a state-space lumping scheme, aggregating states in a grid structure. The resulting approximate stationary distribution is used to iteratively refine releva...

We consider the problem of predictive monitoring (PM), i.e., predicting at runtime future violations of a system from the current state. We work under the most realistic settings where only partial and noisy observations of the state are available at runtime. Such settings directly affect the accuracy and reliability of the reachability predictions...

Neural state classification (NSC) is a recently proposed method for runtime predictive monitoring of hybrid automata (HA) using deep neural networks (DNNs). NSC trains a DNN as an approximate reachability predictor that labels an HA state x as positive if an unsafe state is reachable from x within a given time bound, and labels x as negative otherw...

Stochastic reaction networks are a fundamental model to describe interactions between species where random fluctuations are relevant. The master equation provides the evolution of the probability distribution across the discrete state space consisting of vectors of population counts for each species. However, since its exact solution is often elusi...

Markov Population Models are a widespread formalism used to model the dynamics of complex systems, with applications in Systems Biology and many other fields. The associated Markov stochastic process in continuous time is often analyzed by simulation, which can be costly for large or stiff systems, particularly when a massive number of simulations...

Mean-field models are an established method to analyze large stochastic systems with N interacting objects by means of simple deterministic equations that are asymptotically correct when N tends to infinity. For finite N, mean-field equations provide an approximation whose accuracy is model- and parameter-dependent. Recent research has focused on r...

Cyber-Physical Systems (CPS) consist of inter-wined computational (cyber) and physical components interacting through sensors and/or actuators. Computational elements are networked at every scale and can communicate with each others and with humans. Nodes can join and leave the network at any time or they can move to different spatial locations. %o...

Can language relatedness be established without cognate words? This question has remained unresolved since the nineteenth century, leaving language prehistory beyond etymologically established families largely undefined. We address this problem through a theory of universal syntactic characters. We show that not only does syntax allow for compariso...

To understand the long-run behavior of Markov population models, the computation of the stationary distribution is often a crucial part. We propose a truncation-based approximation that employs a state-space lumping scheme, aggregating states in a grid structure. The resulting approximate stationary distribution is used to iteratively refine releva...

We present MoonLight, a tool for monitoring temporal and spatio-temporal properties of mobile and spatially distributed cyber-physical systems (CPS). In the proposed framework, space is represented as a weighted graph, describing the topological configurations in which the single CPS entities (nodes of the graph) are arranged. Both nodes and edges...

Many probabilistic inference problems such as stochastic filtering or the computation of rare event probabilities require model analysis under initial and terminal constraints. We propose a solution to this bridging problem for the widely used class of population-structured Markov jump processes. The method is based on a state-space lumping scheme...

We consider the problem of the stability of saliency-based explanations of Neural Network predictions under adversarial attacks in a classification task. We empirically show that, for deterministic Neural Networks, saliency interpretations are remarkably brittle even when the attacks fail, i.e. for attacks that do not change the classification labe...

We propose two training techniques for improving the robustness of Neural Networks to adversarial attacks, i.e. manipulations of the inputs that are maliciously crafted to fool networks into incorrect predictions. Both methods are independent of the chosen attack and leverage random projections of the original inputs, with the purpose of exploiting...

We introduce a novel learning-based approach to synthesize safe and robust controllers for autonomous Cyber-Physical Systems and, at the same time, to generate challenging tests. This procedure combines formal methods for model verification with Generative Adversarial Networks. The method learns two Neural Networks: the first one aims at generating...

We consider the problem of bounding mean first passage times and reachability probabilities for the class of population continuous-time Markov chains, which capture stochastic interactions between groups of identical agents. The quantitative analysis of such models is notoriously difficult since typically neither state-based numerical approaches no...

We study continuous-time multi-agent models, where agents interact according to a network topology. At any point in time, each agent occupies a specific local node state. Agents change their state at random through interactions with neighboring agents. The time until a transition happens can follow an arbitrary probability density. Stochastic (Mont...

Many probabilistic inference problems such as stochastic filtering or the computation of rare event probabilities require model analysis under initial and terminal constraints. We propose a solution to this bridging problem for the widely used class of population-structured Markov jump processes. The method is based on a state-space lumping scheme...

From the formation of traffic jams to the development of troublesome, whirlpool-like spirals in the heart's electrical activity, spatio-temporal patterns are key in understanding how complex behaviors can emerge in a network of locally interacting dynamical systems. One of the most important and intriguing questions is how to specify spatio-tempora...

We present MoonLight, a tool for monitoring temporal and spatio-temporal properties of mobile and spatially distributed cyber-physical systems (CPS). In the proposed framework, space is represented as a weighted graph, describing the topological configurations in which the single CPS entities (nodes of the graph) are arranged. Both nodes and edges...

We discuss how to define a kernel for Signal Temporal Logic (STL) formulae. Such a kernel allows us to embed the space of formulae into a Hilbert space, and opens up the use of kernel-based machine learning algorithms in the context of STL. We show an application of this idea to a regression problem in formula space for probabilistic models.

We introduce a novel learning-based approach to synthesize safe and robust controllers for autonomous Cyber-Physical Systems and, at the same time, to generate challenging tests. This procedure combines formal methods for model verification with Generative Adversarial Networks. The method learns two Neural Networks: the first one aims at generating...

The stochastic kinetics of chemical reaction networks can be described by the master equation, which provides the time course evolution of the probability distribution across the discrete state space consisting of vectors of population levels of the interacting species. Since solving the master equation exactly is very difficult in general due to t...

Vulnerability to adversarial attacks is one of the principal hurdles to the adoption of deep learning in safety-critical applications. Despite significant efforts, both practical and theoretical, the problem remains open. In this paper, we analyse the geometry of adversarial attacks in the large-data, overparametrized limit for Bayesian Neural Netw...

Nature-inspired paradigms have been proposed to design and forecast behaviour of open distributed systems, such as sensor networks and the internet of things. In these paradigms system behaviour emerges from (complex) interactions among a large number of agents. Modelling these interactions in terms of classical point-to-point communication is ofte...

Stochastic models in which agents interact with their neighborhood according to a network topology are a powerful modeling framework to study the emergence of complex dynamic patterns in real-world systems. Stochastic simulations are often the preferred—sometimes the only feasible—way to investigate such systems. Previous research focused primarily...

We consider the problem of bounding mean first passage times for a class of continuous-time Markov chains that captures stochastic interactions between groups of identical agents. The quantitative analysis of such probabilistic population models is notoriously difficult since typically neither state-based numerical approaches nor methods based on s...

Neural State Classification (NSC) is a recently proposed method for runtime predictive monitoring of Hybrid Automata (HA) using deep neural networks (DNNs). NSC trains a DNN as an approximate reachability predictor that labels a given HA state x as positive if an unsafe state is reachable from x within a given time bound, and labels x as negative o...

Neural State Classification (NSC) [19] is a scalable method for the analysis of hybrid systems, which consists in learning a neural network-based classifier able to detect whether or not an unsafe state can be reached from a certain configuration of a hybrid system. NSC has very high accuracy, yet it is prone to prediction errors that can affect sy...

Chemical reaction networks describe the interaction of different molecular species in a well-stirred reactor.

Stochastic simulation is a widely used method for estimating quantities in models of chemical reaction networks where uncertainty plays a crucial role. However, reducing the statistical uncertainty of the corresponding estimators requires the generation of a large number of simulation runs, which is computationally expensive. To reduce the number o...

Stochastic models in which agents interact with their neighborhood according to a network topology are a powerful modeling framework to study the emergence of complex dynamic patterns in real-world systems. Stochastic simulations are often the preferred-sometimes the only feasible-way to investigate such systems. Previous research focused primarily...

Markov Population Models are a widespread formalism, with applications in Systems Biology, Performance Evaluation, Ecology, and many other fields. The associated Markov stochastic process in continuous time is often analyzed by simulation, which can be costly for large or stiff systems, particularly when simulations have to be performed in a multi-...

Stochastic processes on complex networks, where each node is in one of several compartments, and neighboring nodes interact with each other, can be used to describe a variety of real-world spreading phenomena. However, computational analysis of such processes is hindered by the enormous size of their underlying state space.
In this work, we demons...

Stochastic simulation is a widely used method for estimating quantities in models of chemical reaction networks where uncertainty plays a crucial role. However, reducing the statistical uncertainty of the corresponding estimators requires the generation of a large number of simulation runs, which is computationally expensive. To reduce the number o...

Stochastic processes on complex networks, where each node is in one of several compartments and neighboring nodes interact with each other, can be used to describe a variety of real-world spreading phenomena. However, computational analysis of such processes is hindered by the enormous size of their underlying state space.
In this work, we demons...

Mean field approximation is a powerful tool to study the performance of large stochastic systems that is known to be exact as the system's size N goes to infinity. Recently, it has been shown that, when one wants to compute expected performance metric in steady-state, mean field approximation can be made more accurate by adding a term in 1/N to the...

Neural State Classification (NSC) is a recently proposed method for runtime predictive monitoring of Hybrid Automata (HA) using deep neural networks (DNNs). NSC trains a DNN as an approximate reachability predictor that labels a given HA state x as positive if an unsafe state is reachable from x within a given time bound, and labels x as negative o...

This book constitutes the refereed proceedings of the 17th International Conference on Computational Methods in Systems Biology, CMSB 2019, held in Trieste, Italy, in September 2019.
The 14 full papers, 7 tool papers and 11 posters were carefully reviewed and selected from 53 submissions. Topics of interest include formalisms for modeling biologic...

The success of modern Artificial Intelligence (AI) technologies depends critically on the ability to learn non-linear functional dependencies from large, high dimensional data sets. Despite recent high-profile successes, empirical evidence indicates that the high predictive performance is often paired with low robustness, making AI systems potentia...

Mean field approximation is a powerful tool to study the performance of large stochastic systems that is known to be exact as the system's size N goes to infinity. Recently, it has been shown that, when one wants to compute expected performance metric in steady-state, this approximation can be made more accurate by adding a term V∕N to the original...

We introduce a new logic called Signal Convolution Logic (\(\text {SCL}\)) that combines temporal logic with convolutional filters from digital signal processing. \(\text {SCL}\) enables to reason about the percentage of time a formula is satisfied in a bounded interval. We demonstrate that this new logic is a suitable formalism to effectively expr...

We introduce a new logic called Signal Convolution Logic (SCL) that combines temporal logic with convolutional filters from digital signal processing. SCL enables to reason about the percentage of time a formula is satisfied in a bounded interval. We demonstrate that this new logic is a suitable formalism to effectively express non-functional requi...

We consider the problem of mining signal temporal logical requirements from a dataset of regular (good) and anomalous (bad) trajectories of a dynamical system. We assume the training set to be labeled by human experts and that we have access only to a limited amount of data, typically noisy.
We provide a systematic approach to synthesize both the...

Parameterized verification of temporal properties is an active research area, being extremely relevant for model-based design of complex systems. In this paper, we focus on parameter synthesis for stochastic models, looking for regions of the parameter space where the model satisfies a linear time specification with probability greater (or less) th...

We consider the problem of mining signal temporal logical requirements from a dataset of regular (good) and anomalous (bad) trajectories of a dynamical system. We assume the training set to be labeled by human experts and that we have access only to a limited amount of data, typically noisy. We provide a systematic approach to synthesize both the s...

Many complex systems can be described by population models, in which a pool of agents interacts and produces complex collective behaviours. We consider the problem of verifying formal properties of the underlying mathematical representation of these models, which is a Continuous Time Markov Chain, often with a huge state space. To circumvent the st...

Cyber-Physical Systems (CPS) consist of collaborative, networked and tightly intertwined computational (logical) and physical components, each operating at different spatial and temporal scales. Hence, the spatial and temporal requirements play an essential role for their correct and safe execution. Furthermore, the local interactions among the sys...

Continuous-time Markov decision processes provide a very powerful mathematical framework to solve policy-making problems in a wide range of applications, ranging from the control of populations to cyber-physical systems. The key problem to solve for these models is to efficiently compute an optimal policy to control the system in order to maximise...

We present Signal Spatio-Temporal Logic (SSTL), a modal logic that can be used to specify spatio-temporal properties in linear time and for a discrete space. The logic is equipped with a Boolean and a quantitative semantics, and with accompanying monitoring algorithms. As such, it is suitable for real-time verification of both white box and black b...

Search-based testing is widely used to find bugs in models of complex Cyber-Physical Systems. Latest research efforts have improved this approach by casting it as a falsification procedure of formally specified temporal properties, exploiting the robustness semantics of Signal Temporal Logic. The scaling of this approach to highly complex engineeri...

The design of genetic or protein networks that satisfy a given set of behavioural specifications is one of the main challenges of synthetic biology. Model-based design is a natural choice in this respect. Here we consider the problem of tuning parameters of a stochastic model to force one or more behavioural goals to hold. In particular, we conside...

Biological systems are often modelled at different levels of abstraction depending on the particular aims/resources of a study. Such different models often provide qualitatively concordant predictions over specific parametrisations, but it is generally unclear whether model predictions are quantitatively in agreement, and whether such agreement hol...

Continuous-time Markov decision processes are an important class of models in a wide range of applications, ranging from cyber-physical systems to synthetic biology. A central problem is how to devise a policy to control the system in order to maximise the probability of satisfying a set of temporal logic specifications. Here we present a novel app...

We study the limiting behaviour of stochastic models of populations of interacting agents, as the number of agents goes to infinity. Classical mean-field results have established that this limiting behaviour is described by an ordinary differential equation (ODE) under two conditions: (1) that the dynamics is smooth; and (2) that the population is...

Continuous-time Markov decision processes are an important class of models in a wide range of applications, ranging from cyber-physical systems to synthetic biology. A central problem is how to devise a policy to control the system in order to maximise the probability of satisfying a set of temporal logic specifications. Here we present a novel app...

Patternformationisanimportantspatio-temporalemergentbehaviour in biology. Mathematical models of pattern formation in the stochastic setting are extremely challenging to execute and analyse. Here we propose a formal analysis of the emergent behaviour of stochastic reaction diffusion systems in terms of Signal Spatio-Temporal Logic, a recently propo...

Biological systems are often modelled at different levels of abstraction depending on the particular aims/resources of a study. Such different models often provide qualitatively concordant predictions over specific parametrisations, but it is generally unclear whether model predictions are quantitatively in agreement, and whether such agreement hol...