Biblio

Explainable Artificial Intelligence (XAI) research focuses on effective explanation techniques to understand and build AI models with trust, reliability, safety, and fairness. Feature importance explanation summarizes feature contributions for end-users to make model decisions. However, XAI methods may produce varied summaries that lead to further analysis to evaluate the consistency across multiple XAI methods on the same model and data set. This paper defines metrics to measure the consistency of feature contribution explanation summaries under feature importance order and saliency map. Driven by these consistency metrics, we develop an XAI process oriented on the XAI criterion of feature importance, which performs a systematical selection of XAI techniques and evaluation of explanation consistency. We demonstrate the process development involving twelve XAI methods on three topics, including a search ranking system, code vulnerability detection and image classification. Our contribution is a practical and systematic process with defined consistency metrics to produce rigorous feature contribution explanations.

Due to the low power of electromagnetic radiation (EMR), EM convert channel has been widely considered as a short-range attack that can be easily mitigated by shielding. This paper overturns this common belief by demonstrating how covert EM signals leaked from typical laptops, desktops and servers are decoded from hundreds of meters away, or penetrate aggressive shield previously considered as sufficient to ensure emission security. We achieve this by designing EMLoRa – a super resilient EM covert channel that exploits memory as a LoRa-like radio. EMLoRa represents the first attempt of designing an EM covert channel using state-of-the-art spread spectrum technology. It tackles a set of unique challenges, such as handling complex spectral characteristics of EMR, tolerating signal distortions caused by CPU contention, and preventing adversarial detectors from demodulating covert signals. Experiment results show that EMLoRa boosts communication range by 20x and improves attenuation resilience by up to 53 dB when compared with prior EM covert channels at the same bit rate. By achieving this, EMLoRa allows an attacker to circumvent security perimeter, breach Faraday cage, and localize air-gapped devices in a wide area using just a small number of inexpensive sensors. To countermeasure EMLoRa, we further explore the feasibility of uncovering EMLoRa's signal using energy- and CNN-based detectors. Experiments show that both detectors suffer limited range, allowing EMLoRa to gain a significant range advantage. Our results call for further research on the countermeasure against spread spectrum-based EM covert channels.

With the prevalence of personal Bluetooth devices, potential breach of user privacy has been an increasing concern. To date, sniffing Bluetooth traffic has been widely considered an extremely intricate task due to Bluetooth's indiscoverable mode, vendor-dependent adaptive hopping behavior, and the interference in the open 2.4 GHz band. In this paper, we present BlueEar -a practical Bluetooth traffic sniffer. BlueEar features a novel dual-radio architecture where two Bluetooth-compliant radios coordinate with each other on learning the hopping sequence of indiscoverable Bluetooth networks, predicting adaptive hopping behavior, and mitigating the impacts of RF interference. Experiment results show that BlueEar can maintain a packet capture rate higher than 90% consistently in real-world environments, where the target Bluetooth network exhibits diverse hopping behaviors in the presence of dynamic interference from coexisting Wi-Fi devices. In addition, we discuss the privacy implications of the BlueEar system, and present a practical countermeasure that effectively reduces the packet capture rate of the sniffer to 20%. The proposed countermeasure can be easily implemented on the Bluetooth master device while requiring no modification to slave devices like keyboards and headsets.