As the digital landscape expands rapidly due to technological advancements, cybersecurity concerns have become more prevalent. Intrusion Detection Systems (IDSs), which are crucial for identifying unusual network traffic indicative of malicious activity, have become a necessity. These systems can be either hardware or software-based. However, traditional IDS models often fail to adequately protect data privacy and detect complex, unique breaches, particularly within Wireless Sensor Networks (WSNs). To address these limitations, this paper proposes a novel Stacked Convolutional Neural Network and Bidirectional Long Short Term Memory (SCNN-Bi-LSTM) model for intrusion detection in WSNs. This model leverages Federated Learning (FL) to enhance intrusion detection performance and safeguard privacy. The FL-based SCNN-Bi-LSTM model is unique in its approach, allowing multiple sensor nodes to collaboratively train a central global model without revealing private data, thereby alleviating privacy concerns. The deep learning methodology of the SCNN-Bi-LSTM model effectively identifies sophisticated and previously unknown cyber threats by meticulously examining both local and temporal linkages in network patterns. The model has been specifically designed to detect and categorize different types of Denial of Service (DoS) attacks using specialized WSN-DS and CIC-IDS-2017 datasets. Compared to traditional Artificial Deep Neural Network (ADNN) models, our proposed FL-SCNN-Bi-LSTM model demonstrated superior detection rates for complex and unknown attacks, significantly improving IDS performance. The model achieved a notable classification accuracy of approximately 99.9% precision and recall on both datasets, substantially reducing false positives and negatives. Our research underscores the potential of federated learning and deep learning in enhancing the security and privacy of WSNs. The proposed FL-SCNN-Bi-LSTM architecture not only facilitates the identification of complex cyber threats but also exemplifies how deep learning techniques can be employed to bolster intrusion detection systems while preserving user data privacy.

This paper deals with the estimation of the time-variant (TV) radial distance of a moving person in an indoor environment. The TV radial distance is obtained from the amplitude of the demodulated TV radar response. For simplicity, the body of a person is modelled by a single point scatterer. We start by determining the TV path delay caused by the motion of the person. Then, the TV radial distance is deduced from the estimated TV path delay. To confirm the validity of the estimation method, we conduct real-world measurements. In this regard, two experiments are carried out for which the radio-frequency (RF) data is collected using the Ancortek SDR-KIT 2400T2R4 radar system operating at 24GHz. In the first experiment, we consider a swinging pendulum acting as a single moving point scatterer. We compare the estimated TV radial distance of the pendulum with the corresponding theoretical expression that provides the ground truth information. For this experiment, the good match between the measured and analytical results demonstrates the proof of concept. In the second experiment, we consider a walking person acting as a single moving for which we can accurately compute the total travelled distance. The findings confirm the validity of the estimation method.

A robust and unobtrusive human activity recognition system is essential to a multitude of applications, such as health care, active assisted living, robotics, sports, and tele-immersion. Existing well-performing activity recognition methods are either vision- or wearable sensor-based. However, they are not fully passive. In this paper, we develop WiHAR-an unobtrusive Wi-Fi-based activity recognition system. WiHAR uses the Wi-Fi network interface card to capture the channel state information (CSI) data. These CSI data are effectively processed, and then amplitude and phase information is used to obtain the spectrogram. In the subsequent step, the time-variant mean Doppler shift (MDS) caused by the human body movements in the radio signals before their arrival at the receiver is estimated. The MDS is used to extract time and frequency domain features that are needed to train the supervised learning algorithms (i.e., decision tree, linear discriminant analysis, and support vector machines (SVM)) to assess the performance of the WiHAR. Our results show that WiHAR combined with SVM achieves 96.2% recognition accuracy on the data set consisting of 9 participants where each participant performed four activities including: walking, falling, picking up an object from the ground, and sitting on a chair.

This paper presents the design and open source implementation of Cormorant, an Android authentication framework able to increase usability and security of mobile authentication. It uses transparent behavioral and physiological biometrics like gait, face, voice, and keystrokes dynamics to continuously evaluate the user's identity without explicit interaction. Using signals like location, time of day, and nearby devices to assess the risk of unauthorized access, the required level of confidence in the user's identity is dynamically adjusted. Authentication results are shared securely, end-to-end encrypted using the Signal messaging protocol, with trusted devices to facilitate cross-device authentication for co-located devices, detected using Bluetooth low energy beacons. Cormorant is able to reduce the authentication overhead by up to 97% compared to conventional knowledge-based authentication whilst increasing security at the same time. We share our perspective on some of the successes and shortcomings we encountered implementing and evaluating Cormorant to hope to inform others working on similar projects.

As users start carrying multiple mobile devices, we propose a novel, token based mobile device unlocking approach. Mobile devices are conjointly shaken to transfer the authentication state from an unlocked token device to another device to unlock it. A common use case features a wrist watch as token device, which remains unlocked as long as it is strapped to the user's wrist, and a locked mobile phone, which is unlocked if both devices are shaken conjointly. Shaking can be done single-handedly, requires little user attention (users don't have to look at the device for unlocking it), and does not cause additional cognitive load on users. In case attackers gain control over the locked phone, forging shaking is difficult, which impedes malicious unlocks. We evaluate our approach using acceleration records from our 29 people sized ShakeUnlock database and discuss influence of its constituent parts on the system performance. We further present a performance study using an Android implementation and live data, which shows the true negative rate of observational attacks to be in the range of 0.8-if an attacker manages to gain control over the locked device and shake it in parallel to the device owner shaking the token device.

This work evaluates the security strength of a smartphone-based gait recognition system against zero-effort and live minimal-effort impersonation attacks under realistic scenarios. For this purpose, we developed an Android application, which uses a smartphone-based accelerometer to capture gait data continuously in the background, but only when an individual walks. Later, it analyzes the recorded gait data and establishes the identity of an individual. At first, we tested the performance of this system against zero-effort attacks by using a dataset of 35 participants. Later, live impersonation attacks were performed by five professional actors who are specialized in mimicking body movements and body language. These attackers were paired with their physiologically close victims, and they were given live audio and visual feedback about their latest impersonation attempt during the whole experiment. No false positives under impersonation attacks, indicate that mimicry does not improve chances of attackers being accepted by our gait authentication system. In 29 percent of total impersonation attempts, when attackers walked like their chosen victim, they lost regularity between their steps which makes impersonation even harder for attackers.

Mobile devices, ubiquitous in modern lifestyle, embody and provide convenient access to our digital lives. Being small and mobile, they are easily lost or stole, therefore require strong authentication to mitigate the risk of unauthorized access. Common knowledge-based mechanism like PIN or pattern, however, fail to scale with the high frequency but short duration of device interactions and ever increasing number of mobile devices carried simultaneously. To overcome these limitations, we present CORMORANT, an extensible framework for risk-aware multi-modal biometric authentication across multiple mobile devices that offers increased security and requires less user interaction.

The inherent weakness of typical mobile device unlocking approaches (PIN, password, graphic pattern) is that they demand time and attention, leading a majority of end users to disable them, effectively lowering device security.

Gait authentication using a cell phone based accelerometer sensor offers an unobtrusive, user-friendly, and periodic way of authenticating individuals on their cell phones. In this study, we present an approach to deal with inevitable errors induced by continuously changing sensor orientation and other noise under a realistic scenario (when the phone is placed inside the trouser pockets and the user is walking) by using the magnitude data of tri-axes accelerometer and wavelet based noise elimination modules. This study utilizes a gait data set of 35 participants collected at their respective normal walking pace in two different sessions with an average gap of 25 days between the sessions.

Biometric gait authentication using Personal Mobile Device (PMD) based accelerometer sensors offers a user-friendly, unobtrusive, and periodic way of authenticating individuals on PMD. In this paper, we present a technique for gait cycle extraction by incorporating the Piecewise Linear Approximation (PLA) technique. We also present two new approaches to classify gait features extracted from the cycle-based segmentation by using Support Vector Machines (SVMs); a) pre-computed data matrix, b) pre-computed kernel matrix. In the first approach, we used Dynamic Time Warping (DTW) distance to compute data matrices, and in the later DTW is used for constructing an elastic similarity measure based kernel function called Gaussian Dynamic Time Warp (GDTW) kernel. Both approaches utilize the DTW similarity measure and can be used for classifying equal length gait cycles, as well as different length gait cycles. To evaluate our approaches we used normal walk biometric gait data of 51 participants. This gait data is collected by attaching a PMD to the belt around the waist, on the right-hand side of the hip. Results show that these new approaches need to be studied more, and potentially lead us to design more robust and reliable gait authentication systems using PMD based accelerometer sensor.