129,404 Hits in 5.3 sec

Explainable Artificial Intelligence (XAI) for 6G: Improving Trust between Human and Machine [article]

Weisi Guo
2019 arXiv   pre-print
As we migrate from traditional model-based optimisation to deep learning, the trust we have in our optimisation modules decrease.  ...  This loss of trust means we cannot understand the impact of: 1) poor/bias/malicious data, and 2) neural network design on decisions; nor can we explain to the engineer or the public the network's actions  ...  Acknowledgements: The author wishes to acknowledge EC H2020 grant 778305: DAWN4IoE -Data Aware Wireless Network for Internet-of-Everything, and The Alan Turing Institute under the EPSRC grant EP/N510129  ... 
arXiv:1911.04542v2 fatcat:2lm7iyoyunbkhkfya5txeos3zm

Hardware-assisted Machine Learning in Resource-constrained IoT Environments for Security: Review and Future Prospective

Georgios Kornaros
2022 IEEE Access  
INDEX TERMS AI-based IoT security, Hardware-based machine learning, IoT intrusion detection, Trusted embedded devices I. INTRODUCTION  ...  This work investigates into machine learning (ML) and deep learning (DL) methodologies for IoT device security and examine the benefits, drawbacks, and potential.  ...  Additionally, to tackle complex and expensive on-chip learning-based approaches, a deep invasive methodology with a lightweight, low-power ML-based monitor for HT detection can give competitive benefits  ... 
doi:10.1109/access.2022.3179047 fatcat:damwrncpzzbxzamtghwlmrg6v4

PowerAlert: An Integrity Checker using Power Measurement [article]

Ahmed M. Fawaz, Mohammad Noureddine, William H. Sanders
2017 arXiv   pre-print
We compare the power measurement against a learned power model of the execution of the machine and validate that the execution was not tampered.  ...  We address those shortcomings by (1) using power measurements from the host to ensure that the checking code is executed and (2) checking a subset of the kernel space over a long period of time.  ...  We learn the normal Power Finite State machine (PFSM) model using training data from the machine.  ... 
arXiv:1702.02907v2 fatcat:ccnzfzc5ejcy7cvbo27a3j2fyy

Trusted Autonomy and Cognitive Cyber Symbiosis: Open Challenges

Hussein A. Abbass, Eleni Petraki, Kathryn Merrick, John Harvey, Michael Barlow
2015 Cognitive Computation  
CoCyS focuses on the architecture and interface of a Trusted Autonomous System.  ...  These entities can be humans, machines, or a mix of the two. Cognitive Cyber Symbiosis (CoCyS) is a cloud that uses humans and machines for decision-making.  ...  reproduction in any medium, provided you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made.  ... 
doi:10.1007/s12559-015-9365-5 pmid:27257440 pmcid:PMC4867784 fatcat:zi6klz6m2je25lsrljoejhmr7m

Catecholaminergic modulation of trust decisions

Cătălina E. Rățală, Sean J. Fallon, Marieke. E. van der Schaaf, Niels ter Huurne, Roshan Cools, Alan G. Sanfey
2019 Psychopharmacology  
Across game partners, we manipulated two aspects of trust: the facial trust level (high facial trust, low facial trust, and non-social) and the likelihood of reciprocation (high, low).  ...  and were low reciprocators.  ...  and high reciprocity, one with low facial trust and low reciprocity, one slot machine with high reciprocity, and one slot machine with low reciprocity.  ... 
doi:10.1007/s00213-019-5165-z fatcat:itmgo572dnh3rm6k7ez5rbcu2m

Modeling Dispositional and Initial learned Trust in Automated Vehicles with Predictability and Explainability [article]

Jackie Ayoub, X. Jessie Yang, Feng Zhou
2020 arXiv   pre-print
Compared to traditional regression models and black-box machine learning models, our findings show that this approach was powerful in providing a high level of explainability and predictability of trust  ...  This study aims to use these factors to predict people's dispositional and initial learned trust in AVs using a survey study conducted with 1175 participants.  ...  Therefore, machine learning techniques were proposed in modeling trust in AVs.  ... 
arXiv:2012.13603v1 fatcat:qzn66wg6b5hzjpluemxod5bkbq

SecureCPS: Defending a nanosatellite cyber-physical system

Lance Forbes, Huy Vu, Bogdan Udrea, Hamilton Hagar, Xenofon D. Koutsoukos, Mark Yampolskiy, Khanh D. Pham, Joseph L. Cox
2014 Sensors and Systems for Space Applications VII  
how to defeat them using the combination of a low-cost Root of Trust Module, Global InfoTek's Advanced Malware Analysis System (GAMAS), and Anomaly Detection by Machine Learning (ADML).  ...  Securing nanosatellites with maneuvering capability is challenging due to extreme cost, size, and power constraints.  ...  GAMAS also provides low-level instrumentation to support our Anomaly Detection by Machine Learning (ADML) subsystem.  ... 
doi:10.1117/12.2054162 fatcat:r4e4ehpoibaetjaqrwo7abpbbu

A Methodology for Evaluating Operator Usage of Machine Learning Recommendations for Power Grid Contingency Analysis

John Wenskovitch, Brett Jefferson, Alexander Anderson, Jessica Baweja, Danielle Ciesielski, Corey Fallon
2022 Frontiers in Big Data  
This work presents the application of a methodology to measure domain expert trust and workload, elicit feedback, and understand the technological usability and impact when a machine learning assistant  ...  The goal of this framework is to rapidly collect and analyze a broad variety of human factors data in order to accelerate the development and evaluation loop for deploying machine learning applications  ...  Slaven Kincic, and Mr. Blaine Mcgary for their contributions to this project.  ... 
doi:10.3389/fdata.2022.897295 pmid:35774852 pmcid:PMC9237339 fatcat:n7ss6dkohvfgbnlfmicvdafrkm

Neural Correlates of Variations in Human Trust in Human-like Machines during Non-reciprocal Interactions

Eun-Soo Jung, Suh-Yeon Dong, Soo-Young Lee
2019 Scientific Reports  
Monitoring human operators' trust is required for productive interactions between humans and machines. However, neurocognitive understanding of human trust in machines is limited.  ...  This research provides a theoretical basis for modelling human neural activities indicate trust in partner machines and can thereby contribute to the design of machines to promote efficient interactions  ...  Average EEG power variations after AC and AW cases for (A) sessions with highly trusted HF agents, (B) with low-trusted HF agents, (C) with highly trusted RF agents, and (D) with low-trusted RF agents.  ... 
doi:10.1038/s41598-019-46098-8 pmid:31292474 pmcid:PMC6620272 fatcat:3aajtar73neuddfezoxpidpfoy

A Comprehensive Study of Anomaly Detection Schemes in IoT Networks Using Machine Learning Algorithms

Abebe Diro, Naveen Chilamkurti, Van-Doan Nguyen, Will Heyne
2021 Sensors  
We also indicate that blockchain-based anomaly detection systems can collaboratively learn effective machine learning models to detect anomalies.  ...  In this paper, we aim to provide an in-depth review of existing works in developing anomaly detection solutions using machine learning for protecting an IoT system.  ...  Lack of Machine Learning Models Resiliency against Adversarial Attacks The lack of a low false-positive rate of existing machine learning models and the vulnerability to adversarial attacks during training  ... 
doi:10.3390/s21248320 pmid:34960414 pmcid:PMC8708212 fatcat:vogif3xvhbdvvb324iwpyq5vkm

VEDLIoT: Very Efficient Deep Learning in IoT [article]

Martin Kaiser, Rene Griessl, Nils Kucza, Carola Haumann, Lennart Tigges, Kevin Mika, Jens Hagemeyer, Florian Porrmann, Ulrich Rückert, Micha vor dem Berge, Stefan. Krupop, Mario Porrmann (+24 others)
2022 arXiv   pre-print
The VEDLIoT project targets the development of energy-efficient Deep Learning for distributed AIoT applications.  ...  A holistic approach is used to optimize algorithms while also dealing with safety and security challenges. The approach is based on a modular and scalable cognitive IoT hardware platform.  ...  VEDLIoT addresses the challenge of bringing Deep Learning to IoT devices with limited computing performance and low-power budgets.  ... 
arXiv:2207.00675v1 fatcat:mbjeq2zwk5frbhawuynqm5mlki

COREnect EuCNC workshop - Patrick Pipe

2021 Zenodo  
3X 5/6G Rise of Secure Edge Processing END DEVICES Billions EDGE CLOUD DATA-CENTERS Millions FUNCTIONAL SAFETY ULTRA LOW POWER REAL-TIME SYSTEM SECURITY LARGE PROCESSING POWER  ...  Trustworthy, secure, flexible o HW anchors for MPSoC o Open-source o Formally verified o Well documented o Allow for hierarchy and Machine Learning Connected Data Safety, Security, Privacy IOT  ... 
doi:10.5281/zenodo.4982666 fatcat:mda3vix3qfgznepfob7sgn3i54

Predicting User Roles in Social Networks Using Transfer Learning with Feature Transformation

Jun Sun, Jerome Kunegis, Steffen Staab
2016 2016 IEEE 16th International Conference on Data Mining Workshops (ICDMW)  
We present a transfer learning approach to network role classification based on feature transformations from each network's local feature distribution to a global feature space.  ...  trusted users in the identified top-k "Banned" users is low.  ...  Transfer Learning Traditionally, if we perform machine learning tasks such as classification, regression and clustering [3] , one assumption is made: The training data from which we learn, and the test  ... 
doi:10.1109/icdmw.2016.0026 dblp:conf/icdm/SunKS16 fatcat:ghpx7ntj2ndkzaw6ijfjyjdfwe

Monitoring Trust in Human-Machine Interactions for Public Sector Applications [article]

Farhana Faruqe, Ryan Watkins, Larry Medsker
2020 arXiv   pre-print
Researchers have routinely used standard machine-learning classifiers like artificial neural networks (ANN), support vector machines (SVM), and K-nearest neighbors (KNN).  ...  A key ingredient to applying trust-sensor research results to practical situations and monitoring trust in work environments is the understanding of which key features are contributing to trust and then  ...  Neera Jain and Kuman Akash at the Purdue University Jain Research Lab and the use of their EEG datasets.  ... 
arXiv:2010.08140v1 fatcat:5v5xip52dfb2rhilkindt5kd2q

Context and Machine Learning Based Trust Management Framework for Internet of Vehicles

Abdul Rehman, Mohd Fadzil Hassan, Yew Kwang Hooi, Muhammad Aasim Qureshi, Tran Duc Chung, Rehan Akbar, Sohail Safdar
2021 Computers Materials & Continua  
The proposed TM framework is based on context-based cognition and machine learning to be best suited to IoV dynamics.  ...  Machine learning is the best solution to utilize the big data produced by vehicle sensors. To handle the uncertainty Bayesian machine learning statistical model is used.  ...  The VANET and machine learning have strong coherence, explored in a comparative study between machine learning and VANETS [15] .  ... 
doi:10.32604/cmc.2021.017620 fatcat:4ursgsi6xjhghg64ni3vzwp37m
« Previous Showing results 1 — 15 out of 129,404 results