An average medium-sized organisation logs approx. 10 to 500 mln events per day on the system. Only less than 5% of threat alerts are being investigated by the specialised staff, leaving the security hole open for potential attacks. Insufficient information in alert message produced in machine-friendly rather than human-friendly format causes cognitive overload on currently limited cybersecurity resources. In this paper, the model that generates the report in natural language by means of applying novel storytelling techniques from security logs is proposed. The solution caters for different levels of reader expertise and preference by providing adjustable templates, filled from both local and global knowledge base. The validation is performed on case study from Security Operations Centre (SOC) at educational institution. The report generated proves superior to existing approach in terms of comprehension (increased cognition) and completeness (enriched context). The evaluation demonstrates power of storytelling in potential threats interpretation in cybersecurity context.
19 December 2022 in Journal of Industrial Information Integration
Due to the presence of noise in crowdsourced labels, label aggregation (LA) has become a standard procedure for post-processing these labels. LA methods estimate true labels from crowdsourced labels by modeling worker quality. However, most existing LA methods are iterative in nature. They require multiple passes through all crowdsourced labels, jointly and iteratively updating true labels and worker qualities until a termination condition is met. As a result, these methods are burdened with high space and time complexities, which restrict their applicability in scenarios where scalability and online aggregation are essential. Furthermore, defining a suitable termination condition for iterative algorithms can be challenging. In this article, we view LA as a dynamic system and represent it as a Dynamic Bayesian Network. From this dynamic model, we derive two lightweight and scalable algorithms: LAonepassand LAtwopass. These algorithms can efficiently and effectively estimate worker qualities and true labels by traversing all labels at most twice, thereby eliminating the need for explicit termination conditions and multiple traversals over the crowdsourced labels. Due to their dynamic nature, the proposed algorithms are also capable of performing label aggregation online. We provide theoretical proof of the convergence property of the proposed algorithms and bound the error of the estimated worker qualities. Furthermore, we analyze the space and time complexities of our proposed algorithms, demonstrating their equivalence to those of majority voting. Through experiments conducted on 20 real-world datasets, we demonstrate that our proposed algorithms can effectively and efficiently aggregate labels in both offline and online settings, even though they traverse all labels at most twice. The code is onhttps://github.com/yyang318/LA_onepass.