Today, it is possible to perform external anomaly detection by analyzing the involuntary EM emanations of digital device components. However, one of the most important challenges of these methods is the manual collection of EM signals for fingerprinting. Indeed, this procedure must be conducted by a human expert and requires high precision. In this work, we introduce a framework that alleviates this requirement by relying on synthetic EM signals that have been generated from assembly code. The signals are produced with the use of a Generative Adversarial Network (GAN) model. Experimentally, we identify that the synthetic EM signals are extremely similar to the real and thus, can be used for training anomaly detection models effectively. Through experimental assessments, we prove that the anomaly detection models are capable of recognizing even minute alterations to the code with high accuracy.

WPA3-Personal renders the Simultaneous Authentication of Equals (SAE) password-authenticated key agreement method mandatory. The scheme achieves forward secrecy and is highly resistant to offline brute-force dictionary attacks. Given that SAE is based on the Dragonfly handshake, essentially a simple password exponential key exchange, it remains susceptible to clogging type of attacks at the Access Point side. To resist such attacks, SAE includes an anti-clogging scheme. To shed light on this contemporary and high-stakes issue, this work offers a full-fledged empirical study on Denial of Service (DoS) against SAE. By utilizing both real-life modern Wi-Fi 6 certified and non-certified equipment and the OpenBSD’s hostapd, we expose a significant number of novel DoS assaults affecting virtually any AP. No less important, more than a dozen of vendor-depended and severe zero-day DoS assaults are manifested, showing that the implementation of the protocol by vendors is not yet mature enough. The fallout of the introduced attacks to the associated stations ranges from a temporary loss of Internet connectivity to outright disconnection. To our knowledge, this work provides the first wholemeal appraisal of SAE’s mechanism endurance against DoS, and it is therefore anticipated to serve as a basis for further research in this timely and intriguing area.

This work provides an answer to the following key question: Are the Web-based management interfaces of the contemporary off-the-shelf wireless access points (WAP) free of flaws and vulnerabilities? The short answer is not very much. That is, after performing a vulnerability assessment on the Web interfaces of six different WAPs by an equal number of diverse renowned vendors, we reveal a significant number of assorted medium-to-high severity vulnerabilities that are straightforwardly or indirectly exploitable. Overall, 13 categories of vulnerabilities translated to 28 zero-day attacks are exposed. Our findings range from legacy path traversal, cross-site scripting, and clickjacking attacks to HTTP request smuggling and splitting, replay, denial of service, and information leakage among others. In the worst-case scenario, the attacker can acquire the administrator’s (admin) credentials and the WAP’s Wi-Fi passphrases or permanently lock the admin out of accessing the WAP’s Web interface. On top of everything else, we identify the already applied hardening measures by these devices and elaborate on extra countermeasures that are required to tackle the identified weaknesses. To our knowledge, this work contributes the first wholemeal appraisal of the security level of this kind of Web-based interfaces that go hand in glove with the myriads of WAPs out there, and it is therefore anticipated to serve as a basis for further research in this timely and challenging field.

This paper focuses on network anomaly-detection and especially the effectiveness of Machine Learning (ML) techniques in detecting Denial of Service (DoS) in SIP-based VoIP ecosystems. It is true that until now several works in the literature have been devoted to this topic, but only a small fraction of them have done so in an elaborate way. Even more, none of them takes into account high and low-rate Distributed DoS (DDoS) when assessing the efficacy of such techniques in SIP intrusion detection. To provide a more complete estimation of this potential, we conduct extensive experimentations involving 5 different classifiers and a plethora of realistically simulated attack scenarios representing a variety of (D)DoS incidents. Moreover, for DDoS ones, we compare our results with those produced by two other anomaly-based detection methods, namely Entropy and Hellinger Distance. Our results show that ML-powered detection scores a promising false alarm rate in the general case, and seems to outperform similar methods when it comes to DDoS.

The vast amounts of data generated, exchanged and consumed on a daily basis by contemporary networks and devices renders their analysis a cumbersome procedure with inherent difficulties. On the one hand, the need for efficient Machine Learning algorithms and tools that scale on large datasets is continuously growing. On the other, parallel or distributed solutions have proven to conceal many pitfalls. The MapReduce programming model has quickly emerged as the de facto model for executing simple algorithmic tasks over huge volumes of data, since it is simple, highly abstract and efficient. However, due to its unidirectional communication model and the inherent lack of support for iterative execution, few Machine Learning algorithms can easily be implemented on MapReduce. In this paper, we present a classification rule discovery algorithm, namely RuleMR, which despite its iterative nature, can capitalize on MapReduce. In order to construct quality rules in less iterations, the algorithm exploits the distributed nature of MapReduce to explore only the promising areas in the search space. We conduct a series of experimental evaluations which indicate that the proposed approach not only scales well with respect to the size of the training dataset, but also, in many cases, the resulting model is comparable to many well known algorithms in matters of accuracy.

Abstract It has been generally agreed that the security of electronic patient records and generally e‐health applications must meet or exceed the standard security that should be applied to paper medical records, yet the absence of clarity on the proper goals of protection has led to confusion. The primary purpose of this study was to investigate appropriate security mechanisms, which will help clinical professionals and patients discharge their ethical and legal responsibilities by selecting suitable systems and operating them safely and in short order. Thus, in this paper we propose a security model based on XML with the intention of developing a fast security policy mostly intended for mobile healthcare information systems. The proposed schema consists of a set of principles based on XML security models through the use of partial encryption, signature and integrity services and it was implemented by means of a web‐based m‐health application in a centralized three‐tier architecture utilizing wireless networks environment. Several experiments took place with the aim of measuring the client response time implementing a number of m‐health scenarios. The results showed that the response times required for the fulfilment of a client request with the XML security model are smaller compared to those corresponding to the conventional security mechanisms such as the application of SSL. By selectively applying confidentiality and integrity services either to the medical information as a whole or to some sensitive parts of it, the obtained results clearly demonstrate that XML security mechanisms overwhelm those of SSL and they are suitable for deployment in m‐health applications. Copyright © 2008 John Wiley & Sons, Ltd.