Search results for "Adversarial system"
showing 10 items of 12 documents
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…
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…
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.
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…
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.
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…
Generating Hyperspectral Skin Cancer Imagery using Generative Adversarial Neural Network
2020
In this study we develop a proof of concept of using generative adversarial neural networks in hyperspectral skin cancer imagery production. Generative adversarial neural network is a neural network, where two neural networks compete. The generator tries to produce data that is similar to the measured data, and the discriminator tries to correctly classify the data as fake or real. This is a reinforcement learning model, where both models get reinforcement based on their performance. In the training of the discriminator we use data measured from skin cancer patients. The aim for the study is to develop a generator for augmenting hyperspectral skin cancer imagery. peerReviewed
The two faces of Nordic management? Nordic firms and their employee relations in the Baltic States
2009
This study examines Nordic management styles in union and non-union industrial enterprises in the Baltic States (Estonia, Latvia, Lithuania) through case studies of nine Nordic subsidiary companies, based on on-site interviews with management and employees.1 This analysis construes the ‘Nordic model’ of management style as ‘bargained constitutional’ or ‘sophisticated consultative’, following Purcell and Ahlstrand's (1994) matrix of management styles in the highly unionized countries of origin, characterized as coordinated market economies. The case studies reveal that in the Baltic liberal-market environment, Nordic employers exhibit a variety of management styles, ranging from sophisticate…
The defendant’s guilt beyond a reasonable doubt in the Italian criminal justice system
2021
The criminal law standard of Beyond A Reasonable Doubt (BARD) constitutes an evidentiary and judicial rule, formulated and applied for centuries in common law jurisdictions, which was expressly stated in the Italian Code of Criminal Procedure only about fifteen years ago. Unfortunately, the concept of reasonable doubt is inherently complex and does not easily lend itself to definition or refinement. In this regard, the Author examines especially the various positions and elaborations developed by legal literature and case-law in Italy, proposing a specific interpretation of the BARD rule that enhances and completes the particular procedural connotations of the adversarial system adopted i…
Groups' warmth is a personal matter: Understanding consensus on stereotype dimensions reconciles adversarial models of social evaluation
2020
Abstract As proponents of two theories of social evaluation, we disagree whether people spontaneously differentiate societal groups' conservative-progressive beliefs (distinct claim of the agency-beliefs-communion or ABC model) or warmth/communion (distinct claim of the stereotype content model or SCM). Our adversarial collaboration provides one way to resolve this debate. Examining people from four continents who differentiated groups in their country (N = 2356), we found lower consensus on groups' warmth/communion compared to agency/~competence and beliefs (Studies 1–4). Consensus on groups' warmth/communion was lower because people differed in self-rated agency and beliefs, and they infe…