187 Hits in 5.9 sec

Fingerprinting Encrypted Voice Traffic on Smart Speakers with Deep Learning [article]

Chenggang Wang, Sean Kennedy, Haipeng Li, King Hudson, Gowtham Atluri, Xuetao Wei, Wenhai Sun, Boyang Wang
2020 arXiv   pre-print
This paper investigates the privacy leakage of smart speakers under an encrypted traffic analysis attack, referred to as voice command fingerprinting.  ...  In this attack, an adversary can eavesdrop both outgoing and incoming encrypted voice traffic of a smart speaker, and infers which voice command a user says over encrypted traffic.  ...  Selcuk Uluagac, for their insightful comments on this paper.  ... 
arXiv:2005.09800v1 fatcat:5broa65upjgfrck3slpk5zn77m

Fine-hearing Google Home: why silence will not protect your privacy

Davide Caputo, Luca Verderame, Andrea Ranieri, Alessio Merlo, Luca Caviglione
2020 Journal of Wireless Mobile Networks, Ubiquitous Computing, and Dependable Applications  
Smart speakers and voice-based virtual assistants are used to retrieve information, interact with other devices, and command a variety of Internet of Things (IoT) nodes.  ...  To this aim, smart speakers and voice-based assistants typically take advantage of cloud architectures: vocal commands of the user are sampled, sent through the Internet to be processed and transmitted  ...  Conclusions and Future Works In this paper, we investigated the feasibility of adopting machine learning techniques to breach the privacy of users interacting with smart speakers or voice assistants.  ... 
doi:10.22667/jowua.2020.03.31.035 dblp:journals/jowua/CaputoVRMC20 fatcat:mp2aphhxm5dcjnpec6nx3vcxty

A Survey on Amazon Alexa Attack Surfaces [article]

Yanyan Li, Sara Kim, Eric Sy
2021 arXiv   pre-print
The success of Alexa is based on its effortless usability, but in turn, that has led to a lack of sufficient security.  ...  Alexa's user-friendly, personalized vocal experience offers customers a more natural way of interacting with cutting-edge technology by allowing the ability to directly dictate commands to the assistant  ...  speakers through multiple deep learning models.  ... 
arXiv:2102.11442v1 fatcat:kyo7jhjd2zen5o2ebd26wuj4na

Side channel attacks on smart home systems: A short overview

Mohammad Ali Nassiri Abrishamchi, Abdul Hanan Abdullah, Adrian David Cheok, Kevin S. Bielawski
2017 IECON 2017 - 43rd Annual Conference of the IEEE Industrial Electronics Society  
Permanent repository link: Link to published version: http://dx.Abstract-This paper provides an overview on side-channel attacks with emphasis on vulnerabilities in  ...  This paper starts by reviewing side-channel attack categories, then it gives an overview on recent attack studies on different layers of a smart home and their malicious goals.  ...  Voice communication is a common activity in every home. [28] proposed a novel attack to identify speakers despite encrypted voice communication.  ... 
doi:10.1109/iecon.2017.8217429 dblp:conf/iecon/AbrishamchiACB17 fatcat:p5l6yaht2fekbncffx6h2c4vyu

Paper Titles

2019 2019 IEEE 8th Global Conference on Consumer Electronics (GCCE)  
Linux The Flow Control in Unmanned Stores with Sensing Floor The Impact of "Surround Sound on Eye and Head Movement While Watching Moving Images The Implementation of Traffic Analytics Using Deep Learning  ...  HSR Wireless Network Handover Mechanism for QoS Improvement on Control Plane Robust Detection and Recognition of Japanese Traffic Sign in the Complex Scenes Based on Deep Learning Robust Reflection Removal  ... 
doi:10.1109/gcce46687.2019.9015409 fatcat:6k3r6jixrvglrkrkzek636gb54

GCCE 2020 Subject Index

2020 2020 IEEE 9th Global Conference on Consumer Electronics (GCCE)  
Research for Unique Venue of Cultural Properties Made by Bricks in Japan Research on the Less Stress Acquisition Method for the Activity Information of Actual Residents Using the International Standard  ...  ECHONET Lite Research on the Less Stress Acquisition Method for the Activity Information of Actual Residents Using the International Standard ECHONET Lite S 3 7 A B C D E F G H I K L M N O P Q R S  ...  Text Scoring for Collaborative Learning Big Traffic Data Analytics for Smart Urban Intelligent Traffic System Using Machine Learning Techniques Big Traffic Data Analytics for Smart Urban Intelligent Traffic  ... 
doi:10.1109/gcce50665.2020.9291796 fatcat:bmnnn7xnxrefhaneq262fe4i6u

Biometrics for Internet-of-Things Security: A Review

Wencheng Yang, Song Wang, Nor Masri Sahri, Nickson M. Karie, Mohiuddin Ahmed, Craig Valli
2021 Sensors  
The purpose of this review is to provide a comprehensive survey on the current biometrics research in IoT security, especially focusing on two important aspects, authentication and encryption.  ...  As for encryption, biometric-cryptographic systems, which integrate biometrics with cryptography and take advantage of both to provide enhanced security for IoT, are thoroughly reviewed and discussed.  ...  For example, despite the strong authentication performance offered by using iris, voice is clearly a better choice than iris in the authentication scenario of smart speakers.  ... 
doi:10.3390/s21186163 pmid:34577370 fatcat:urk3rlktjbahvdc5evaanqjn3y

Security and Privacy Analysis of Youth-Oriented Connected Devices

Sonia Solera-Cotanilla, Mario Vega-Barbas, Jaime Pérez, Gregorio López, Javier Matanza, Manuel Álvarez-Campana
2022 Sensors  
This article focuses on analyzing the security and privacy of such devices to promote safe Internet use, especially by young people.  ...  Our results help other researchers address these issues with a more global perspective.  ...  In addition, knowledge of such security and privacy issues in connected devices will enable users to be aware of the threats associated with the use of these devices and to learn good usage practices to  ... 
doi:10.3390/s22113967 pmid:35684588 fatcat:ed7xm34h6fbsbbzeb4b5l5vmim

Spying on the Smart Home: Privacy Attacks and Defenses on Encrypted IoT Traffic [article]

Noah Apthorpe, Dillon Reisman, Srikanth Sundaresan, Arvind Narayanan, Nick Feamster
2017 arXiv   pre-print
Our experiments show that traffic shaping can effectively and practically mitigate many privacy risks associated with smart home IoT devices.  ...  We evaluate several strategies for mitigating the privacy risks associated with smart home device traffic, including blocking, tunneling, and rate-shaping.  ...  Supervised machine learning can accurately fingerprint smart home devices using Internet traffic rates.  ... 
arXiv:1708.05044v1 fatcat:d7x4izf5w5eo5aa3hym27qfcau

Empowering Things with Intelligence: A Survey of the Progress, Challenges, and Opportunities in Artificial Intelligence of Things [article]

Jing Zhang, Dacheng Tao
2020 arXiv   pre-print
Artificial intelligence (AI), especially deep learning, is now a proven success in various areas including computer vision, speech recognition, and natural language processing.  ...  This paper presents a comprehensive survey on AIoT to show how AI can empower the IoT to make it faster, smarter, greener, and safer.  ...  system for conferences), as well as the cloud computing with acceptable latency (e.g., on-line mode of smart voice assistant).  ... 
arXiv:2011.08612v1 fatcat:dflut2wdrjb4xojll34c7daol4

A Systematic Survey of Attack Detection and Prevention in Connected and Autonomous Vehicles [article]

Trupil Limbasiya, Ko Zheng Teng, Sudipta Chattopadhyay, Jianying Zhou
2022 arXiv   pre-print
There are some surveys with a limited discussion on Attacks Detection and Prevention Systems (ADPS), but such surveys provide only partial coverage of different types of ADPS for CAVs.  ...  The number of Connected and Autonomous Vehicles (CAVs) is increasing rapidly in various smart transportation services and applications due to many benefits to society, people, and the environment.  ...  Deep learning techniques use artificial or deep neural networks, algorithms inspired by the human brain.  ... 
arXiv:2203.14965v1 fatcat:4orttcmbjfei5dbhsjnaovmm7a

SDN-Enabled FiWi-IoT Smart Environment Network Traffic Classification Using Supervised ML Models

Elaiyasuriyan Ganesan, I-Shyan Hwang, Andrew Tanny Liem, Mohammad Syuhaimi Ab-Rahman
2021 Photonics  
This paper, we propose a machine learning supervised network traffic classification scheduling model in SDN enhanced-FiWi-IoT that can intelligently learn and guarantee traffic based on its QoS requirements  ...  We capture the different IoT and non-IoT device network traffic trace files based on the traffic flow and analyze the traffic traces to extract statistical attributes (port source and destination, IP address  ...  network (WLAN) traffic, based on the quality of service class identification (QoS-CI) for traffic types such as voice, video, IoT and data.  ... 
doi:10.3390/photonics8060201 fatcat:xte7aviqrzdkrntp6mkgeq3qma

Non-Invasive Challenge Response Authentication for Voice Transactions with Smart Home Behavior

Victor Hayashi, Wilson Ruggiero
2020 Sensors  
Smart speakers, such as Alexa and Google Home, support daily activities in smart home environments.  ...  The Coloured Petri Net model was created for synthetic data generation, and one month data were collected in test bed with real users.  ...  Figure 2 . 2 Open Smart Speaker Architecture with non-invasive Authorization that is based on data-driven approach.  ... 
doi:10.3390/s20226563 pmid:33212905 pmcid:PMC7698362 fatcat:aotvt7hcavbzxepjap7cq5jxki

AI-Assisted Authentication: State of the Art, Taxonomy and Future Roadmap [article]

Guangyi Zhu, Yasir Al-Qaraghuli
2022 arXiv   pre-print
With the emerging AI-assisted authentication schemes, our comprehensive survey provides an overall understanding on a high level, which paves the way for future research in this area.  ...  In contrast to other relevant surveys, our research is the first of its kind to focus on the roles of AI in authentication.  ...  Such neural networks are naturally compatible with ordinal problems like voice recognition. 1.1.2 Supervised, Semi-Supervised and Reinforcement Learning Supervised learning is one of the subcategories  ... 
arXiv:2204.12492v1 fatcat:vdeuhy63cvawjdhclricvkq42q

Towards Privacy Preserving IoT Environments: A Survey

Mohamed Seliem, Khalid Elgazzar, Kasem Khalil
2018 Wireless Communications and Mobile Computing  
However, with the increasing wide adoption of IoT, come significant privacy concerns to lose control of how our data is collected and shared with others.  ...  IoT promises to enable a plethora of smart services in almost every aspect of our daily interactions and improve the overall quality of life.  ...  Several strategies have been investigated to avoid the privacy risks associated with smart home traffic monitoring such as traffic blocking, tunnelling, and rate-shaping.  ... 
doi:10.1155/2018/1032761 fatcat:j76yhuc5rjhvbifkk5foq3klzq
« Previous Showing results 1 — 15 out of 187 results