Researches in Artificial Intelligence (AI) have achieved many important breakthroughs, especially in recent years. In some cases, AI learns alone from scratch and performs human tasks faster and better than humans. With the recent advances in AI, it is natural to wonder whether Artificial Neural Networks will be used to successfully create or break cryptographic algorithms. Bibliographic review shows the main approach to this problem have been addressed throughout complex Neural Networks, but without understanding or proving the security of the generated model. This paper presents an analysis of the security of cryptographic algorithms generated by a new technique called Adversarial Neural Cryptography (ANC). Using the proposed network, we show limitations and directions to improve the current approach of ANC. Training the proposed Artificial Neural Network with the improved model of ANC, we show that artificially intelligent agents can learn the unbreakable One-Time Pad (OTP) algorithm, without human knowledge, to communicate securely through an insecure communication channel. This paper shows in which conditions an AI agent can learn a secure encryption scheme. However, it also shows that, without a stronger adversary, it is more likely to obtain an insecure one.

The Internet of Things (IoT) introduces significant security vulnerabilities, raising concerns about cyber-attacks. Attackers exploit these vulnerabilities to launch distributed denial-of-service (DDoS) attacks, compromising availability and causing financial damage to digital infrastructure. This study focuses on mitigating DDoS attacks in corporate local networks by developing a model that operates closer to the attack source. The model utilizes Host Intrusion Detection Systems (HIDS) to identify anomalous behaviors in IoT devices and employs network-based intrusion detection approaches through a Network Intrusion Detection System (NIDS) for comprehensive attack identification. Additionally, a Host Intrusion Detection and Prevention System (HIDPS) is implemented in a fog computing infrastructure for real-time and precise attack detection. The proposed model integrates NIDS with federated learning, allowing devices to locally analyze their data and contribute to the detection of anomalous traffic. The distributed architecture enhances security by preventing volumetric attack traffic from reaching internet service providers and destination servers. This research contributes to the advancement of cybersecurity in local network environments and strengthens the protection of IoT networks against malicious traffic. This work highlights the efficiency of using a federated training and detection procedure through deep learning to minimize the impact of a single point of failure (SPOF) and reduce the workload of each device, thus achieving accuracy of 89.753% during detection and increasing privacy issues in a decentralized IoT infrastructure with a near-real-time detection and mitigation system.

The innovations proposed by the cell phone market have grown steadily in recent years, along with the increasing complexity of the hardware, operating systems, and applications available in this market. These changes bring new challenges related to usability that need to be considered during the development process of these applications since the new forms of user-application interactions increasingly require adapting the behavior of smartphone users. In this situation, usability is an important issue that depends on factors such as the Users, their characteristics and abilities, the Task which the users intend to achieve and also the application usage Context. This work presents a systematic literature review with the objective of identifying the heuristics and usability metrics used in the literature and/or industry. Based on the review results, this work presents another contribution with a proposal of a set of usability heuristics focused in mobile applications on smartphones, considering the User, Task and Context as usability factors and Cognitive Load as an important attribute of usability. The components of this set are detailed in a model intended to be used in empirical validations allowing to dynamically incorporate improvements to the proposal.

The cyber security landscape is fundamentally changing over the past years. While technology is evolving and new sophisticated applications are being developed, a new threat scenario is emerging in alarming proportions. Sophisticated threats with multi-vectored, multi-staged and polymorphic characteristics are performing complex attacks, making the processes of detection and mitigation far more complicated. Thus, organizations were encouraged to change their traditional defense models and to use and to develop new systems with a proactive approach. Such changes are necessary because the old approaches are not effective anymore to detect advanced attacks. Also, the organizations are encouraged to develop the ability to respond to incidents in real-time using complex threat intelligence platforms. However, since the field is growing rapidly, today Cyber Threat Intelligence concept lacks a consistent definition and a heterogeneous market has emerged, including diverse systems and tools, with different capabilities and goals. This work aims to provide a comprehensive evaluation methodology of threat intelligence standards and cyber threat intelligence platforms. The proposed methodology is based on the selection of the most relevant candidates to establish the evaluation criteria. In addition, this work studies the Cyber Threat Intelligence ecosystem and Threat Intelligence standards and platforms existing in state-of-the-art.

Data breaches result in data loss, including personal, health, and financial information that are crucial, sensitive, and private. The breach is a security incident in which personal and sensitive data are exposed to unauthorized individuals, with the potential to incur several privacy concerns. As an example, the French newspaper Le Figaro breached approximately 7.4 billion records that included full names, passwords, and e-mail and physical addresses. To reduce the likelihood and impact of such breaches, it is fundamental to strengthen the security efforts against this type of incident and, for that, it is first necessary to identify patterns of its occurrence, primarily related to the number of data records leaked, the affected geographical region, and its regulatory aspects. To advance the discussion in this regard, we study a dataset comprising 428 worldwide data breaches between 2018 and 2019, providing a visualization of the related statistics, such as the most affected countries, the predominant economic sector targeted in different countries, and the median number of records leaked per incident in different countries, regions, and sectors. We then discuss the data protection regulation in effect in each country comprised in the dataset, correlating key elements of the legislation with the statistical findings. As a result, we have identified an extensive disclosure of medical records in India and government data in Brazil in the time range. Based on the analysis and visualization, we find some interesting insights that researchers seldom focus on before, and it is apparent that the real dangers of data leaks are beyond the ordinary imagination. Finally, this paper contributes to the discussion regarding data protection laws and compliance regarding data breaches, supporting, for example, the decision process of data storage location in the cloud.

Any network connected to the Internet is subject to cyber attacks. Strong security measures, forensic tools, and investigators contribute together to detect and mitigate those attacks, reducing the damages and enabling reestablishing the network to its normal operation, thus increasing the cybersecurity of the networked environment. This paper addresses the use of a forensic approach with Deep Packet Inspection to detect anomalies in the network traffic. As cyber attacks may occur on any layer of the TCP/IP networking model, Deep Packet Inspection is an effective way to reveal suspicious content in the headers or the payloads in any packet processing layer, excepting of course situations where the payload is encrypted. Although being efficient, this technique still faces big challenges. The contributions of this paper rely on the association of Deep Packet Inspection with forensics analysis to evaluate different attacks towards a Honeynet operating in a network laboratory at the University of Brasilia. In this perspective, this work could identify and map the content and behavior of attacks such as the Mirai botnet and brute-force attacks targeting various different network services. Obtained results demonstrate the behavior of automated attacks (such as worms and bots) and non-automated attacks (brute-force conducted with different tools). The data collected and analyzed is then used to generate statistics of used usernames and passwords, IP and services distribution, among other elements. This paper also discusses the importance of network forensics and Chain of Custody procedures to conduct investigations and shows the effectiveness of the mentioned techniques in evaluating different attacks in networks.