Unsupervised Learning for Trustworthy IoT

The advancement of Internet-of-Things (IoT) edge devices with various types of sensors enables us to harness diverse information with Mobile Crowd-Sensing applications (MCS). This highly dynamic setting entails the collection of ubiquitous data traces, originating from sensors carried by people, introducing new information security challenges; one of them being the preservation of data trustworthiness. What is needed in these settings is the timely analysis of these large datasets to produce accurate insights on the correctness of user reports. Existing data mining and other artificial intelligence methods are the most popular to gain hidden insights from IoT data, albeit with many challenges. In this paper, we first model the cyber trustworthiness of MCS reports in the presence of intelligent and colluding adversaries. We then rigorously assess, using real IoT datasets, the effectiveness and accuracy of well-known data mining algorithms when employed towards IoT security and privacy. By taking into account the spatio-temporal changes of the underlying phenomena, we demonstrate how concept drifts can masquerade the existence of attackers and their impact on the accuracy of both the clustering and classification processes. Our initial set of results clearly show that these unsupervised learning algorithms are prone to adversarial infection, thus, magnifying the need for further research in the field by leveraging a mix of advanced machine learning models and mathematical optimization techniques.

[1]  Hojung Cha,et al.  Collaborative classification for daily activity recognition with a smartwatch , 2016, 2016 IEEE International Conference on Systems, Man, and Cybernetics (SMC).

[2]  Fabio Roli,et al.  Evasion Attacks against Machine Learning at Test Time , 2013, ECML/PKDD.

[3]  Panagiotis Papadimitratos,et al.  Trustworthy People-Centric Sensing: Privacy, security and user incentives road-map , 2014, 2014 13th Annual Mediterranean Ad Hoc Networking Workshop (MED-HOC-NET).

[4]  Subutai Ahmad,et al.  Unsupervised real-time anomaly detection for streaming data , 2017, Neurocomputing.

[5]  Juhan Nam,et al.  Multimodal Deep Learning , 2011, ICML.

[6]  Athanasios V. Vasilakos,et al.  Data Mining for the Internet of Things: Literature Review and Challenges , 2015, Int. J. Distributed Sens. Networks.

[7]  Leandro L. Minku,et al.  FEDD: Feature Extraction for Explicit Concept Drift Detection in time series , 2016, 2016 International Joint Conference on Neural Networks (IJCNN).

[8]  Wei Liu,et al.  Adversarial learning games with deep learning models , 2017, 2017 International Joint Conference on Neural Networks (IJCNN).

[9]  Naphtali Rishe,et al.  Safe cities. A participatory sensing approach , 2012, 37th Annual IEEE Conference on Local Computer Networks.

[10]  George Loukas,et al.  Assessing the cyber-trustworthiness of human-as-a-sensor reports from mobile devices , 2017, 2017 IEEE 15th International Conference on Software Engineering Research, Management and Applications (SERA).

[11]  Cesare Alippi,et al.  Credit card fraud detection and concept-drift adaptation with delayed supervised information , 2015, 2015 International Joint Conference on Neural Networks (IJCNN).

[12]  Dimosthenis Kyriazis,et al.  A Comparative Study of Classification Techniques for Managing IoT Devices of Common Specifications , 2017, GECON.

[13]  Moloud Abdar,et al.  Performance analysis of classification algorithms on early detection of liver disease , 2017, Expert Syst. Appl..

[14]  Ling Huang,et al.  Approaches to adversarial drift , 2013, AISec.

[15]  Yanmin Zhu,et al.  A Survey on Trajectory Data Mining: Techniques and Applications , 2016, IEEE Access.

[16]  Panagiotis Papadimitratos,et al.  SHIELD: a data verification framework for participatory sensing systems , 2015, WISEC.

[17]  Steve A. Schneider,et al.  Privacy-enhanced capabilities for VANETs using direct anonymous attestation , 2017, 2017 IEEE Vehicular Networking Conference (VNC).

[18]  Pedro M. Domingos,et al.  Adversarial classification , 2004, KDD.

[19]  Minho Shin,et al.  AnonySense: A system for anonymous opportunistic sensing , 2011, Pervasive Mob. Comput..

[20]  Francesco Piazza,et al.  Acoustic novelty detection with adversarial autoencoders , 2017, 2017 International Joint Conference on Neural Networks (IJCNN).

[21]  Xin Sun,et al.  Detection, Classification and Characterization of Android Malware Using API Data Dependency , 2015, SecureComm.

[22]  Yang Zhang,et al.  CarTel: a distributed mobile sensor computing system , 2006, SenSys '06.

[23]  Miguel A. Labrador,et al.  P-Sense: A participatory sensing system for air pollution monitoring and control , 2011, 2011 IEEE International Conference on Pervasive Computing and Communications Workshops (PERCOM Workshops).

[24]  Panagiotis Papadimitratos,et al.  SPPEAR: security & privacy-preserving architecture for participatory-sensing applications , 2014, WiSec '14.

[25]  Emiliano Miluzzo,et al.  Tapping into the Vibe of the city using VibN, a continuous sensing application for smartphones , 2011, SCI '11.

[26]  Emilio Corchado,et al.  A survey of multiple classifier systems as hybrid systems , 2014, Inf. Fusion.

[27]  Emmanouil A. Panaousis,et al.  A game-theoretic approach for minimizing security risks in the Internet-of-Things , 2015, 2015 IEEE International Conference on Communication Workshop (ICCW).

[28]  Urbano Nunes,et al.  Platooning of autonomous vehicles with intervehicle communications in SUMO traffic simulator , 2010, 13th International IEEE Conference on Intelligent Transportation Systems.

[29]  Panagiotis Papadimitratos,et al.  Secure and Privacy-Preserving Smartphone-Based Traffic Information Systems , 2015, IEEE Transactions on Intelligent Transportation Systems.

[30]  Wen Hu,et al.  Towards trustworthy participatory sensing , 2009 .