Computer Forensics is mainly about investigating crime where computers have been involved. There are many tools available to aid the investigator with this task. We have created a prototype of a new type of tool called CyberForensic TimeLab where all evidence is indexed by their time variables and plotted on a timeline. We believed that this way of visualizing the evidence allows the investigators to find coherent evidence faster and more intuitively. We have performed a user test where a group of people has evaluated our prototype tool against a modern commercial computer forensic tool and the results of this preliminary test are very promising. The results show that users completed the task in shorter time, with greater accuracy and with less errors using CyberForensic TimeLab. The subjects also experienced that the prototype were more intuitive to use and that it allowed them to easier locate evidence that was coherent in time

Classifying e-mails into distinct labels can have a great impact on customer support. By using machine learning to label e-mails, the system can set up queues containing e-mails of a specific category. This enables support personnel to handle request quicker and more easily by selecting a queue that match their expertise. This study aims to improve a manually defined rule-based algorithm, currently implemented at a large telecom company, by using machine learning. The proposed model should have higher $$F_1$$F1 -score and classification rate. Integrating or migrating from a manually defined rule-based model to a machine learning model should also reduce the administrative and maintenance work. It should also make the model more flexible. By using the frameworks, TensorFlow, Scikit-learn and Gensim, the authors conduct a number of experiments to test the performance of several common machine learning algorithms, text-representations, word embeddings to investigate how they work together. A long short-term memory network showed best classification performance with an $$F_1$$F1 -score of 0.91. The authors conclude that long short-term memory networks outperform other non-sequential models such as support vector machines and AdaBoost when predicting labels for e-mails. Further, the study also presents a Web-based interface that were implemented around the LSTM network, which can classify e-mails into 33 different labels.

The importance of cellular networks continuously increases as we assume ubiquitous connectivity in our daily lives. As a result, the underlying core telecom systems have very high reliability and availability requirements, that are sometimes hard to meet. This study presents a proactive approach that could aid satisfying these high requirements on reliability and availability by predicting future base station alarms. A data set containing 231 internal performance measures from cellular (4G) base stations is correlated with a data set containing base station alarms. Next, two experiments are used to investigate (i) the alarm prediction performance of six machine learning models, and (ii) how different predict-ahead times (ranging from 10 min to 48 hours) affect the predictive performance. A 10-fold cross validation evaluation approach and statistical analysis suggested that the Random Forest models showed best performance. Further, the results indicate the feasibility of predicting severe alarms one hour in advance with a precision of 0.812 (±0.022, 95 % CI), recall of 0.619 (±0.027) and F ₁ -score of 0.702 (±0.022). A model interpretation package, ELI5, was used to identify the most influential features in order to gain model insight. Overall, the results are promising and indicate the potential of an early-warning system that enables a proactive means for achieving high reliability and availability requirements.

The popularity of Online Social Networks (OSNs) has increased the visibility of users profiles and interactions performed between users. In this paper we structure different privacy threats related to OSNs and describe six different types of privacy threats. One of these threats, named public information harvesting, is previously not documented so we therefore present it in further detail by also presenting the results from a proof-of-concept implementation of that threat. The basis of the attack is gathering of user interactions from various open groups on Facebook which then is transformed into a social interaction graph. Since the data gathered from the OSN originates from open groups it could be executed by any third-party connected to the Internet independently of the users' privacy settings. In addition to presenting the different privacy threats we also we propose a range of different protection techniques.