No abstract

No abstract

In this study, the authors propose a multi-objective optimisation-based feature selection (FS) method for the detection of distributed denial of service (DDoS) attacks in an internet of things (IoT) network. An intrusion detection system (IDS) is one approach for the detection of cyber-attacks. FS is required to reduce the dimensionality of data and improve the performance of the IDS. One of the reasons for the failure of an IDS is incorrect selection of features because most of the FS methods are based on a limited number of objectives such as accuracy or relevance of data, but these are not enough as they can be misleading for attack detection the contribution of this work is to develop appropriate FS method. They have implemented the nondominated sorting algorithm with its adapted jumping gene operator to solve the optimisation problem and exploited an extreme learning machine as the classifier for FS based on six important objectives for an IoT network. Experimental results verify that the proposed method performs well for FS and have achieved 99.9% and has reduced the total number of features by nearly 90%. The proposed method outperforms other proposed FS methods for the detection of DDoS attacks by an IDS.

Law enforcement agencies (LEAs) globally are facing high demand to view, process, and analyse digital evidence. Arrests for Indecent Images of Children (IIOC) have risen by a factor of 25 over the previous decade. A case typically requires the use of computing resources for between 2-4 weeks. The lengthy time is due to the sequential ordering of acquiring a forensically sound copy of all data, systematically extracting all images, before finally analysing each to automatically identify instances of known IIOC images (second-generation) or manually identifying new images (first-generation). It is therefore normal practice that an understanding of the image content is only obtained right at the end of the investigative process. A reduction in processing time would have a transformative impact, by enabling timely identification of victims, swift intervention with perpetrators to prevent re-offending, and reducing the traumatic psychological effects of any ongoing investigation for the accused and their families. In this paper, a new approach to the digital forensic processes containing suspected IIOC content is presented, whereby in-process metrics are used to prioritise case handling, ensuring cases with a high probability of containing IIOC content are prioritised. The use of automated planning (AP) enables a systematic approach to case priorisation. In this paper, a planning approach is presented where AP is used to generate investigative actions in 60-minute segments, before re-planning to account for discoveries made during the execution of planned actions. A case study is provided consisting of 5 benchmark cases, demonstrating on average a reduction of 36% in processing time and a 26% reduction in time required to discover IIOC content.