The growing popularity of Android requires malware detection systems that can keep up with the pace of new software being released. According to a recent study, a new piece of malware appears online every 12 seconds. To address this, we treat Android malware detection as a streaming data problem and explore the use of active online learning as a means of mitigating the problem of labelling applications in a timely and cost-effective manner. Specifically, we develop a semi-supervised active learning framework that incrementally trains online learning models using only samples with low prediction confidence, while detecting concept drift and retraining the models when drift is observed. Our resulting framework achieves accuracies of up to 96% on a balanced dataset, requires as little as 24% of the training data to be labelled, and compensates for concept drift that occurs between the release and labelling of an application. We also consider the broader practicalities of online learning within Android malware detection, and systematically explore the trade-offs between using different static, dynamic and hybrid feature sets to classify malware. We find that features derived from static API calls lead to the best performing models, though models based around lower-dimensional permission and opcode feature sets provide a potentially more practical basis for deployment, with only a marginal deficit in accuracy. Dynamic and hybrid feature sets are found to significantly increase feature extraction costs with no net benefit to predictive performance.

End-to-End Encryption (E2EE) has become a de facto standard in messengers, especially after the development of the secure messaging protocol – Signal. However, the adoption of E2EE has been limited to messengers, and has not yet seen a noticeable trace in social network platforms, despite the increase in users’ privacy violations. In this paper, we propose, verify, implement and evaluate a novel E2EE protocol – Stick. Stick is a Signal-based protocol tailored for social network platforms. We believe our protocol is the first to support re-establishable encryption sessions in an asynchronous multi-device setting while preserving forward secrecy and introducing backward secrecy. Stick includes several innovative features, including a new session concept, multiple pairwise sessions and refreshing identity keys. We verified Stick using Verifpal - a formal verification tool in the symbolic model. Our security analysis shows our protocol does achieve a form of post-compromise security in many-to-many communications – the trait most group protocols lack. Most importantly, the Stick protocol can re-establish encryption sessions while ensuring authentication and confidentiality. We implemented our protocol as a stand-alone open-source API. Our evaluation shows the Stick protocol can be used in a real-world social network app with no noticeable compromise on usability or performance.

It is estimated that around 70% of mobile phone users have an Android device. Due to this popularity, the Android operating system attracts a lot of malware attacks. The sensitive nature of data present on smartphones means that it is important to protect against these attacks. Classic signature-based detection techniques fall short when they come up against a large number of users and applications. Machine learning, on the other hand, appears to work well, and also helps in identifying zero-day attacks, since it does not require an existing database of malicious signatures. In this paper, we critically review past works that have used machine learning to detect Android malware. The review covers supervised, unsupervised, deep learning and online learning approaches, and organises them according to whether they use static, dynamic or hybrid features.

Asset management is important to all modern organizations. It becomes critical when assets are equipment on which lives depend. The development of communication and wireless technologies, such as the new Near Field Communication (NFC) has opened new doors for efficient asset management. Store managers and keepers can now use mobile lightweight devices for asset management. In this paper, we propose and implement the first NFC-based mobile asset management solution for medical equipment. Our solution provides a unique security feature that allows immediate detection of tampering with any equipment's description. Furthermore, we critically review existing works and compare them to our solution and show its efficiency.

With the proliferation of the use of peer-to-peer networks for distributing multimedia and software content, there is an increasing need for efficient and reliable data distribution mechanisms that can scale to large numbers of users. The peer-to-peer protocol BitTorrent is scalable and is widely used to share content. The lack of reputation techniques in BitTorrent makes it impossible to get any information about how reliable a peer is. In this paper, we propose a secure and reliable architecture for reputation in BitTorrent. Our framework allows a peer to securely share its feedback about another peer after a transaction. Then, allow other peers to securely retrieve this information when required. Furthermore, we discuss how secure our system is by studying how it protects against the well knows peer-to-peer attacks.

With the proliferation of the use of Internet for distributing multimedia and software content, there is an increasing need for efficient and reliable data distribution mechanisms that can scale to large numbers of users. The peer-to-peer protocol BitTorrent is scalable and is widely used to share content. The lack of reputation techniques in BitTorrent makes it impossible to get any information about how reliable a peer is. In this paper, we propose a secure framework for reputation in BitTorrent. Our framework allows peers to securely share their opinions (votes) about a peer after a transaction, then securely retrieve this information when required by another peer.

With the proliferation of the use of Internet for distributing multimedia and software content, there is an increasing need for efficient and secure data distribution mechanisms that can scale to large numbers of users. The peer-to-peer protocol BitTorrent is scalable and is widely used to share unprotected files. The lack of security in BitTorrent obstructs its deployment for business applications. P2P systems have developed up to a point where their use in a business context is hampered by the lack of security. We propose to add the missing security services, widening the range of use of P2P systems. In this paper we propose a new and scalable security architecture for BitTorrent that provides reliable mechanisms for authentication, authorization, and confidentiality. The security architecture we propose for BitTorrent could be used in both personal and business contexts, and its comparison to existing architectures shows its efficiency.