Physical-layer security is regaining traction in the research community, due to the performance boost introduced by deep learning classification algorithms. This is particularly true for sender authentication in wireless communications via radio fingerprinting. However, previous research mainly focused on terrestrial wireless devices while, to the best of our knowledge, none of the previous work considered satellite transmitters. The satellite scenario is generally challenging because, among others, satellite radio transducers feature non-standard electronics (usually aged and specifically designed for harsh conditions). Moreover, the fingerprinting task is specifically difficult for Low-Earth Orbit (LEO) satellites (like the ones we focus in this paper) since they feature a low bit-rate and orbit at about 800 Km from the Earth, at a speed of around 25,000 Km/h, thus making the receiver experiencing a down-link with unique attenuation and fading characteristics. In this paper, we investigate the effectiveness and main limitations of AI-based solutions to the physical-layer authentication of LEO satellites. Our study is performed on massive real data—more than$100M$I-Q samples—collected from an extensive measurements campaign on the IRIDIUM LEO satellites constellation, lasting 589 hours. Our results show that Convolutional Neural Networks (CNN) and autoencoders (if properly calibrated) can be successfully adopted to authenticate the satellite transducers, with an accuracy spanning between 0.8 and 1, depending on prior assumptions. However, the relatively high number of I-Q samples required by the proposed methodology, coupled with the low bandwidth of satellite link, might prevent the detection of the spoofing attack under certain configuration parameters.

Abstract Classifying a weapon based on its muzzle blast is a challenging task that has significant applications in various security and military fields. Most of the existing works rely on ad-hoc deployment of spatially diverse microphone sensors to capture multiple replicas of the same gunshot, which enables accurate detection and identification of the acoustic source. However, carefully controlled setups are difficult to obtain in scenarios such as crime scene forensics, making the aforementioned techniques inapplicable and impractical. We introduce a novel technique that requires zero knowledge about the recording setup and is completely agnostic to the relative positions of both the microphone and shooter. Our solution can identify the category, caliber, and model of the gun, reaching over 90% accuracy on a dataset composed of 3655 samples that are extracted from YouTube videos. Our results demonstrate the effectiveness and efficiency of applying Convolutional Neural Network (CNN) in gunshot classification eliminating the need for an ad-hoc setup while significantly improving the classification performance.

In this paper we are concerned with geolocating the anonymous crowds of Dark Web forums. We do not focus on single users, but on the crowd as a whole. We work in two directions: The first idea is to exploit the time of all posts in the Dark Web forums to build profiles of the visiting crowds and to match the crowd profiles to that of users from known regions. Then, we develop a new dataset to detect the native language of the crowds to support and integrate this match. We assess the effectiveness of our methodology on the standard web and two Dark Web forums with users of known origin, and apply it to three controversial anonymous Dark Web forums. We believe that this work helps the community better understand the Dark Web from a sociological point of view and supports the investigation of authorities when the security of citizens is at stake.

Fake news propagation is a complex phenomenon influenced by a multitude of factors whose identification and impact assessment is challenging. Although many models have been proposed in the literature, the one capturing all the properties of a real fake-news propagation phenomenon is inevitably still missing. Modern propagation models, mainly inspired by old epidemiological models, attempt to approximate the fake-news propagation phenomena by blending psychological factors, social relations, and user behavior. This work provides an in-depth analysis of the current state of fake-news propagation models supported by real-world datasets. We highlighted similarities and differences in the modeling approaches, wrapping up the main research trends. Propagation models, transitions, network topologies, and performance metrics have been identified and discussed in detail. The thorough analysis we provided in this article, coupled with the highlighted research hints, have a high potential to pave the way for future research in the area.

The massive deployment of IoT devices being utilized by home automation, industrial and military scenarios demands for high security and privacy standards to be achieved through innovative solutions. This paper proposes KaFHCa, a crypto-less protocol that generates shared secret keys by combining random frequency hopping collisions and source indistinguishability independently of the radio channel status. While other solutions tie the secret bit rate generation to the current radio channel conditions, thus becoming unpractical in static environments, KaFHCa guarantees almost the same secret bit rate independently of the channel conditions. KaFHCa generates shared secrets through random collisions of the transmitter and the receiver in the radio spectrum, and leverages on the fading phenomena to achieve source indistinguishability, thus preventing unauthorized eavesdroppers from inferring the key. The proposed solution is (almost) independent of the adversary position, works under the conservative assumption of channel fading (σ=8dB), and is capable of generating a secret key of 128 bits with less than 564 transmissions.

Cryptojacking occurs when an adversary illicitly runs crypto-mining software over the devices of unaware users. This novel cybersecurity attack, that is emerging in both the literature and in the wild, has proved to be very effective given the simplicity of running a crypto-client into a target device. Several countermeasures have recently been proposed, with different features and performance, but all characterized by a host-based architecture. The cited solutions, designed to protect the individual user, are not suitable for efficiently protecting a corporate network, especially against insiders. In this paper, we propose a network-based approach to detect and identify crypto-clients activities by solely relying on the network traffic, even when encrypted and mixed with non-malicious traces. First, we provide a detailed analysis of the real network traces generated by three major cryptocurrencies, Bitcoin, Monero, and Bytecoin, considering both the normal traffic and the one shaped by a VPN. Then, we propose Crypto-Aegis, a Machine Learning (ML) based framework built over the results of our investigation, aimed at detecting cryptocurrencies related activities, e.g., pool mining, solo mining, and active full nodes. Our solution achieves a striking 0.96 of F1-score and 0.99 of AUC for the ROC, while enjoying a few other properties, such as device and infrastructure independence. Given the extent and novelty of the addressed threat we believe that our approach, supported by its excellent results, pave the way for further research in this area.

Wireless devices resorting to event-triggered communications have been proved to suffer critical privacy issues, due to the intrinsic leakage associated with radio-frequency (RF) emissions.

The Software Defined Networking (SDN) paradigm decouples the logic module from the forwarding module on traditional network devices, bringing a wave of innovation to computer networks. Firewalls, as well as other security appliances, can largely benefit from this novel paradigm. Firewalls can be easily implemented by using the default OpenFlow rules, but the logic must reside in the control plane due to the dynamic nature of their rules that cannot be handled by data plane devices. This leads to a nonnegligible overhead in the communication channel between layers, as well as introducing an additional computational load on the control plane. To address the above limitations, we propose the architectural design of FORTRESS: a stateful firewall for SDN networks that leverages the stateful data plane architecture to move the logic of the firewall from the control plane to the data plane. FORTRESS can be implemented according to two different architectural designs: Stand-Alone and Cooperative, each one with its own peculiar advantages. We compare FORTRESS against FlowTracker, the state-of-the-art solution for SDN firewalling, and show how our solution outperforms the competitor in terms of the number of packets exchanged between the control plane and the data plane—we require 0 packets for the Stand-Alone architecture and just 4 for the Cooperative one. Moreover, we discuss how the adaptability, elegant and modular design, and portability of FORTRESS contribute to make it the ideal candidate for SDN firewalling. Finally, we also provide further research directions.

Dark Web platforms like the infamous Silk Road market, or other cyber-criminal or terrorism related forums, are only accessible by using anonymity mechanisms like Tor. In this paper we are concerned with geolocating the crowds accessing Dark Web forums. We do not focus on single users. We aim at uncovering the geographical distribution of groups of visitors into time-zones as a whole. Our approach, to the best of our knowledge, is the first of its kind applied to the Dark Web. The idea is to exploit the time of all posts in the Dark Web forums to build profiles of the visiting crowds. Then, to uncover the geographical origin of the Dark Web crowd by matching the crowd profile to that of users from known regions on regular web platforms. We assess the effectiveness of our methodology on standard web and two Dark Web platforms with users of known origin, and apply it to three controversial anonymous Dark Web forums. We believe that this work helps the community better understand the Dark Web from a sociological point of view and support the investigation of authorities when the security of citizens is at stake.