Bio-inspired enhancement of reputation systems for intelligent environments

Improving data quality with an accumulated reputation model in participatory sensing systems

The ubiquity of mobile devices brings forth a sensing paradigm, participatory sensing, to collect and interpret sensory information from the environment. Participants join in multifarious sensing tasks and share their data. The sensing result can be obtained in light of shared data. It is not uncommon that some corrupted data is provided by participants, which makes sensing result unreliable accordingly. To address this nontrivial issue, we proposed the accumulated reputation model (ARM) to improve the accuracy of the sensing result. In ARM, participants' reputation will be computed and accumulated based on their sensing data. The sensing data from reputable participants make higher contributions to the sensing result. ARM performs well on calculating accurate sensing results, even in extreme scenarios, where there are many inexperienced or malicious participants.

Detecting unknown attacks in wireless sensor networks that contain mobile nodes

As wireless sensor networks are usually deployed in unattended areas, security policies cannot be updated in a timely fashion upon identification of new attacks. This gives enough time for attackers to cause significant damage. Thus, it is of great importance to provide protection from unknown attacks. However, existing solutions are mostly concentrated on known attacks. On the other hand, mobility can make the sensor network more resilient to failures, reactive to events, and able to support disparate missions with a common set of sensors, yet the problem of security becomes more complicated. In order to address the issue of security in networks with mobile nodes, we propose a machine learning solution for anomaly detection along with the feature extraction process that tries to detect temporal and spatial inconsistencies in the sequences of sensed values and the routing paths used to forward these values to the base station. We also propose a special way to treat mobile nodes, which is the main novelty of this work. The data produced in the presence of an attacker are treated as outliers, and detected using clustering techniques. These techniques are further coupled with a reputation system, in this way isolating compromised nodes in timely fashion. The proposal exhibits good performances at detecting and confining previously unseen attacks, including the cases when mobile nodes are compromised.