Search

Despite being the most popular privacy-enhancing network, Tor is increasingly adopted by cybercriminals to obfuscate malicious traffic, hindering the identification of malware-related communications between compromised devices and Command and Control (C&C) servers. This malicious traffic can induce congestion and reduce Tor's performance, while encouraging network administrators to block Tor traffic. Recent research, however, demonstrates the potential for accurately classifying captured Tor traffic as malicious or benign. While existing efforts have addressed malware class identification, their performance remains limited, with micro-average precision and recall values around 70%. Accurately classifying specific malware classes is crucial for effective attack prevention and mitigation. Furthermore, understanding the unique patterns and attack vectors employed by different malware classes helps the development of robust and adaptable defence mechanisms. We utilise a multi-label classification technique based on Message-Passing Neural Networks, demonstrating its superiority over previous approaches such as Binary Relevance, Classifier Chains, and Label Powerset, by achieving micro-average precision (MAP) and recall (MAR) exceeding 90%. Compared to previous work, we significantly improve performance by 19.98%, 10.15%, and 59.21% in MAP, MAR, and Hamming Loss, respectively. Next, we employ Explainable Artificial Intelligence (XAI) techniques to interpret the decision-making process within these models. Finally, we assess the robustness of all techniques by crafting adversarial perturbations capable of manipulating classifier predictions and generating false positives and negatives.

Tiny Machine Learning (TinyML) is an upsurging research field that proposes to democratize the use of Machine Learning and Deep Learning on highly energy-efficient frugal Microcontroller Units. Considering the general assumption that TinyML can only run inference, growing interest in the domain has led to work that makes them reformable, i.e., solutions that permit models to improve once deployed. This work presents a survey on reformable TinyML solutions with the proposal of a novel taxonomy. Here, the suitability of each hierarchical layer for reformability is discussed. Furthermore, we explore the workflow of TinyML and analyze the identified deployment schemes, available tools and the scarcely available benchmarking tools. Finally, we discuss how reformable TinyML can impact a few selected industrial areas and discuss the challenges and future directions.

The infection rate of COVID-19 and lack of an approved vaccine has forced governments and health authorities to adopt lockdowns, increased testing, and contact tracing to reduce the spread of the virus. Digital contact tracing has become a supplement to the traditional manual contact tracing process. However, although there have been a number of digital contact tracing apps proposed and deployed, these have not been widely adopted owing to apprehensions surrounding privacy and security. In this paper, we propose a blockchain-based privacy-preserving contact tracing protocol, "Did I Meet You" (DIMY), that provides full-lifecycle data privacy protection on the devices themselves as well as on the back-end servers, to address most of the privacy concerns associated with existing protocols. We have employed Bloom filters to provide efficient privacy-preserving storage, and have used the Diffie-Hellman key exchange for secret sharing among the participants. We show that DIMY provides resilience against many well known attacks while introducing negligible overheads. DIMY's footprint on the storage space of clients' devices and back-end servers is also significantly lower than other similar state of the art apps.

Anonymity networks are becoming increasingly popular in today's online world as more users attempt to safeguard their online privacy. Tor is currently the most popular anonymity network in use and provides anonymity to both users and services (hidden services). However, the anonymity provided by Tor is also being misused in various ways. Hosting illegal sites for selling drugs, hosting command and control servers for botnets, and distributing censored content are but a few such examples. As a result, various parties, including governments and law enforcement agencies, are interested in attacks that assist in de-anonymising the Tor network, disrupting its operations, and bypassing its censorship circumvention mechanisms. In this survey paper, we review known Tor attacks and identify current techniques for the de-anonymisation of Tor users and hidden services. We discuss these techniques and analyse the practicality of their execution method. We conclude by discussing improvements to the Tor framework that help prevent the surveyed de-anonymisation attacks., Comment: This work is published in IEEE Communications Surveys & Tutorials and is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/. Link to the article https://ieeexplore.ieee.org/abstract/document/9471821

The recent outbreak of COVID-19 has taken the world by surprise, forcing lockdowns and straining public health care systems. COVID-19 is known to be a highly infectious virus, and infected individuals do not initially exhibit symptoms, while some remain asymptomatic. Thus, a non-negligible fraction of the population can, at any given time, be a hidden source of transmissions. In response, many governments have shown great interest in smartphone contact tracing apps that help automate the difficult task of tracing all recent contacts of newly identified infected individuals. However, tracing apps have generated much discussion around their key attributes, including system architecture, data management, privacy, security, proximity estimation, and attack vulnerability. In this article, we provide the first comprehensive review of these much-discussed tracing app attributes. We also present an overview of many proposed tracing app examples, some of which have been deployed countrywide, and discuss the concerns users have reported regarding their usage. We close by outlining potential research directions for next-generation app design, which would facilitate improved tracing and security performance, as well as wide adoption by the population at large., Comment: Paper has been accepted for publication in IEEE Access. Currently available on IEEE ACCESS early access (see DOI)

The video footage produced by the surveillance cameras is an important evidence to support criminal investigations. Video evidence can be sourced from public (trusted) as well as private (untrusted) surveillance systems. This raises the issue of establishing integrity and auditability for information provided by the untrusted video sources. In this paper, we focus on a airport ecosystem, where multiple entities with varying levels of trust are involved in producing and exchanging video surveillance information. We present a framework to ensure the data integrity of the stored videos, allowing authorities to validate whether video footage has not been tampered. Our proposal uses a lightweight blockchain technology to store the video metadata as blockchain transactions to support the validation of video integrity. The proposed framework also ensures video auditability and non-repudiation. Our evaluations show that the overhead introduced by employing the blockchain to create and query the transactions introduces a very minor latency of a few milliseconds.

The networking industry, compared to the compute industry, has been slow in evolving from a closed ecosystem with limited abstractions to a more open ecosystem with well-defined sophisticated high level abstractions. This has resulted in an ossified Internet architecture that inhibits innovation and is unnecessarily complex. Fortunately, there has been an exciting flux of rapid developments in networking in recent times with prominent trends emerging that have brought us to the cusp of a major paradigm shift. In particular, the emergence of technologies such as cloud computing, software defined networking (SDN), and network virtualization are driving a new vision of `networking as a service' (NaaS) in which networks are managed flexibly and efficiently cloud computing style. These technologies promise to both facilitate architectural and technological innovation while also simplifying commissioning, orchestration, and composition of network services. In this article, we introduce our readers to these technologies. In the coming few years, the trends of cloud computing, SDN, and network virtualization will further strengthen each other's value proposition symbiotically and NaaS will increasingly become the dominant mode of commissioning new networks., Comment: Accepted in IEEE Potentials

In recent times, there have been a lot of efforts for improving the ossified Internet architecture in a bid to sustain unstinted growth and innovation. A major reason for the perceived architectural ossification is the lack of ability to program the network as a system. This situation has resulted partly from historical decisions in the original Internet design which emphasized decentralized network operations through co-located data and control planes on each network device. The situation for wireless networks is no different resulting in a lot of complexity and a plethora of largely incompatible wireless technologies. The emergence of "programmable wireless networks", that allow greater flexibility, ease of management and configurability, is a step in the right direction to overcome the aforementioned shortcomings of the wireless networks. In this paper, we provide a broad overview of the architectures proposed in literature for building programmable wireless networks focusing primarily on three popular techniques, i.e., software defined networks, cognitive radio networks, and virtualized networks. This survey is a self-contained tutorial on these techniques and its applications. We also discuss the opportunities and challenges in building next-generation programmable wireless networks and identify open research issues and future research directions., Comment: 19 pages

Software cost estimation (SCE) of a project is pivotal to the acceptance or rejection of the development of software project. Various SCE techniques have been in practice with their own strengths and limitations. The latest of these is object-oriented one. Currently object-oriented approach for SCE is based on Line of Code (LOC), function points, functions and classes etc. Relatively less attention has been paid to the SCE in component-based software engineering (CBSE). So there is a pressing need to search parameters/variables that have a vital role for the SCE using CBSE which is taken up in this paper. This paper further looks at level of significance of all the parameters/variables thus searched. The time is being used as an independent variable because time is a parameter which is almost, all previous in one. Therefore this approach may be in a way an alternate of all previous approaches. Infact the underlying research ultimately may lead towards SCE of complex systems, using CBSE, in a scientific, systematic and comprehensive way., Comment: ISSN: 0030-9877