Search results for "adversarial"

showing 10 items of 30 documents

Crowd-Averse Robust Mean-Field Games: Approximation via State Space Extension

2016

We consider a population of dynamic agents, also referred to as players. The state of each player evolves according to a linear stochastic differential equation driven by a Brownian motion and under the influence of a control and an adversarial disturbance. Every player minimizes a cost functional which involves quadratic terms on state and control plus a cross-coupling mean-field term measuring the congestion resulting from the collective behavior, which motivates the term “crowd-averse.” Motivations for this model are analyzed and discussed in three main contexts: a stock market application, a production engineering example, and a dynamic demand management problem in power systems. For th…

0209 industrial biotechnologyStochastic stabilityMathematical optimizationCollective behaviorTechnologyComputer sciencePopulationcontrol designcrowd-averse robust mean-field games state space extension dynamic agents linear stochastic differential equation Brownian motion adversarial disturbance cost functional cross-coupling mean-field term collective behavior stock market application production engineering example dynamic demand management problem robust mean-field game approximation error stochastic stability microscopic dynamics macroscopic dynamicscontrol engineering02 engineering and technology01 natural sciencesStochastic differential equationoptimal control020901 industrial engineering & automationQuadratic equationAutomation & Control SystemsEngineeringClosed loop systemsSettore ING-INF/04 - AutomaticaApproximation errorRobustness (computer science)Control theory0102 Applied MathematicsState space0101 mathematicsElectrical and Electronic EngineeringeducationBrownian motioneducation.field_of_studyScience & TechnologyStochastic process010102 general mathematicsRelaxation (iterative method)Engineering Electrical & ElectronicOptimal controlComputer Science Applications0906 Electrical and Electronic EngineeringIndustrial Engineering & AutomationMean field theoryControl and Systems EngineeringSettore MAT/09 - Ricerca Operativa0913 Mechanical Engineering
researchProduct

Improving Speaker-Independent Lipreading with Domain-Adversarial Training

2017

We present a Lipreading system, i.e. a speech recognition system using only visual features, which uses domain-adversarial training for speaker independence. Domain-adversarial training is integrated into the optimization of a lipreader based on a stack of feedforward and LSTM (Long Short-Term Memory) recurrent neural networks, yielding an end-to-end trainable system which only requires a very small number of frames of untranscribed target data to substantially improve the recognition accuracy on the target speaker. On pairs of different source and target speakers, we achieve a relative accuracy improvement of around 40% with only 15 to 20 seconds of untranscribed target speech data. On mul…

030507 speech-language pathology & audiology03 medical and health sciencesAdversarial systemRecurrent neural networkComputer scienceSpeech recognitionFeed forwardTraining (meteorology)0305 other medical scienceAccuracy improvementIndependence (probability theory)Domain (software engineering)Interspeech 2017
researchProduct

Thompson Sampling Guided Stochastic Searching on the Line for Non-stationary Adversarial Learning

2015

This paper reports the first known solution to the N-Door puzzle when the environment is both non-stationary and deceptive (adversarial learning). The Multi-Armed-Bandit (MAB) problem is the iconic representation of the exploration versus exploitation dilemma. In brief, a gambler repeatedly selects and play, one out of N possible slot machines or arms and either receives a reward or a penalty. The objective of the gambler is then to locate the most rewarding arm to play, while in the process maximize his winnings. In this paper we investigate a challenging variant of the MAB problem, namely the non-stationary N-Door puzzle. Here, instead of directly observing the reward, the gambler is only…

Adversarial systemComputer scienceProperty (programming)business.industryProcess (computing)Reinforcement learningArtificial intelligencebusinessRepresentation (mathematics)Bayesian inferenceMulti-armed banditThompson sampling2015 IEEE 14th International Conference on Machine Learning and Applications (ICMLA)
researchProduct

Robust consensus in social networks and coalitional games

2014

We study an n-player averaging process with dynamics subject to controls and adversarial disturbances. The model arises in two distinct application domains: i) coalitional games with transferable utilities (TU) and ii) opinion propagation. We study conditions under which the average allocations achieve robust consensus to some predefined target set.

Adversarial systemMathematical optimizationProcess (engineering)Game theory networks allocations robust receding horizon control.EconomicsSettore MAT/09 - Ricerca OperativaSet (psychology)Mathematical economicsGame theory
researchProduct

Cloning and training collective intelligence with generative adversarial networks

2021

Industry 4.0 and highly automated critical infrastructure can be seen as cyber‐physical‐social systems controlled by the Collective Intelligence. Such systems are essential for the functioning of the society and economy. On one hand, they have flexible infrastructure of heterogeneous systems and assets. On the other hand, they are social systems, which include collaborating humans and artificial decision makers. Such (human plus machine) resources must be pre‐trained to perform their mission with high efficiency. Both human and machine learning approaches must be bridged to enable such training. The importance of these systems requires the anticipation of the potential and previously unknow…

Cognitive scienceTechnological innovations. AutomationCloning (programming)Computer scienceHD45-45.2Collective intelligenceManufacturestekoälyTraining (civil)Industrial and Manufacturing EngineeringTS1-2301Computer Science ApplicationsAdversarial systemkoneoppiminenArtificial IntelligenceHardware and Architectureautomaatiojärjestelmätihminen-konejärjestelmätälytekniikkaGenerative grammarIET Collaborative Intelligent Manufacturing
researchProduct

Crowd-Averse Cyber-Physical Systems: The Paradigm of Robust Mean-Field Games

2016

For a networked controlled system, we illustrate the paradigm of robust mean-field games. This is a modeling framework at the interface of differential game theory, mathematical physics, and $H_{\infty}$ - optimal control that tries to capture the mutual influence between a crowd and its individuals. First, we establish a mean-field system for such games including the effects of adversarial disturbances. Second, we identify the optimal response of the individuals for a given population behavior. Third, we provide an analysis of equilibria and their stability.

Computer Science::Computer Science and Game Theory0209 industrial biotechnologyTheoretical computer scienceComputer scienceInterface (computing)PopulationStability (learning theory)02 engineering and technology01 natural sciencesAdversarial system020901 industrial engineering & automationSettore ING-INF/04 - AutomaticaControl theoryRobustness (computer science)Differential game0101 mathematicsElectrical and Electronic Engineeringcrowd-averse cyber-physical systems robust mean-field games paradigm networked control system differential game theory mathematical physics H∞-optimal control mean-field system adversarial disturbance effecteducationeducation.field_of_studyCyber-physical systemOptimal controlComputer Science Applications010101 applied mathematicsControl and Systems EngineeringSettore MAT/09 - Ricerca OperativaIEEE Transactions on Automatic Control
researchProduct

Clinically-Driven Virtual Patient Cohorts Generation: An Application to Aorta

2021

The combination of machine learning methods together with computational modeling and simulation of the cardiovascular system brings the possibility of obtaining very valuable information about new therapies or clinical devices through in-silico experiments. However, the application of machine learning methods demands access to large cohorts of patients. As an alternative to medical data acquisition and processing, which often requires some degree of manual intervention, the generation of virtual cohorts made of synthetic patients can be automated. However, the generation of a synthetic sample can still be computationally demanding to guarantee that it is clinically meaningful and that it re…

Computer sciencePhysiologySample (statistics)Target populationMachine learningcomputer.software_genreData acquisitionVirtual patientPhysiology (medical)digital twinQP1-981support vector machineOriginal Researchbusiness.industrygenerative adversarial networkSampling (statistics)synthetic populationthoracic-aortaSupport vector machineReference samplein-silico trialsCohortArtificial intelligencevirtual cohortbusinesscomputerclinically-driven samplingFrontiers in Physiology
researchProduct

Countering Adversarial Inference Evasion Attacks Towards ML-Based Smart Lock in Cyber-Physical System Context

2021

Machine Learning (ML) has been taking significant evolutionary steps and provided sophisticated means in developing novel and smart, up-to-date applications. However, the development has also brought new types of hazards into the daylight that can have even destructive consequences required to be addressed. Evasion attacks are among the most utilized attacks that can be generated in adversarial settings during the system operation. In assumption, ML environment is benign, but in reality, perpetrators may exploit vulnerabilities to conduct these gradient-free or gradient-based malicious adversarial inference attacks towards cyber-physical systems (CPS), such as smart buildings. Evasion attac…

ExploitComputer sciencebusiness.industryCyber-physical systemevasion attacksEvasion (network security)Context (language use)Adversarial machine learningComputer securitycomputer.software_genreadversarial machine learningdefensive mechanismscyber-physical systemAdversarial systemSmart lockkoneoppiminenälytekniikkabusinesskyberturvallisuuscomputerverkkohyökkäyksetBuilding automation
researchProduct

Cross-Sensor Adversarial Domain Adaptation of Landsat-8 and Proba-V images for Cloud Detection

2021

The number of Earth observation satellites carrying optical sensors with similar characteristics is constantly growing. Despite their similarities and the potential synergies among them, derived satellite products are often developed for each sensor independently. Differences in retrieved radiances lead to significant drops in accuracy, which hampers knowledge and information sharing across sensors. This is particularly harmful for machine learning algorithms, since gathering new ground truth data to train models for each sensor is costly and requires experienced manpower. In this work, we propose a domain adaptation transformation to reduce the statistical differences between images of two…

FOS: Computer and information sciencesAtmospheric ScienceComputer Science - Machine LearningGenerative adversarial networks010504 meteorology & atmospheric sciencesComputer scienceRemote sensing applicationdomain adaptationGeophysics. Cosmic physics0211 other engineering and technologiesCloud computing02 engineering and technologycomputer.software_genre01 natural sciencesImage (mathematics)Data modelingMachine Learning (cs.LG)convolutional neural networksFOS: Electrical engineering electronic engineering information engineeringLandsat-8Computers in Earth SciencesAdaptation (computer science)TC1501-1800021101 geological & geomatics engineering0105 earth and related environmental sciencesbusiness.industryQC801-809Image and Video Processing (eess.IV)Electrical Engineering and Systems Science - Image and Video ProcessingOcean engineeringTransformation (function)cloud detectionSatelliteData miningProba-VTransfer of learningbusinesscomputer
researchProduct

Enforcing Perceptual Consistency on Generative Adversarial Networks by Using the Normalised Laplacian Pyramid Distance

2019

In recent years there has been a growing interest in image generation through deep learning. While an important part of the evaluation of the generated images usually involves visual inspection, the inclusion of human perception as a factor in the training process is often overlooked. In this paper we propose an alternative perceptual regulariser for image-to-image translation using conditional generative adversarial networks (cGANs). To do so automatically (avoiding visual inspection), we use the Normalised Laplacian Pyramid Distance (NLPD) to measure the perceptual similarity between the generated image and the original image. The NLPD is based on the principle of normalising the value of…

FOS: Computer and information sciencesComputer Science - Machine LearningComputer scienceImage qualitymedia_common.quotation_subjectComputer Vision and Pattern Recognition (cs.CV)Computer Science - Computer Vision and Pattern RecognitionComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONMachine Learning (stat.ML)Translation (geometry)Image (mathematics)Machine Learning (cs.LG)Consistency (database systems)Statistics - Machine LearningPerceptionFOS: Electrical engineering electronic engineering information engineeringmedia_commonbusiness.industryDeep learningImage and Video Processing (eess.IV)Contrast (statistics)Pattern recognitionGeneral MedicineImage segmentationElectrical Engineering and Systems Science - Image and Video ProcessingGenerative Adversarial NetworkPerceptionArtificial intelligencebusiness
researchProduct