Politecnico di Torino

11/18/2021 | News release | Distributed by Public on 11/19/2021 03:20

DarkVec: Automatic Analysis of Darknet Traffic with Word Embeddings

Categoria: Seminari e Convegni

Stato: Corrente

SmartData@Covivio and on Microsoft Teams platform

SmartTalk of the SmartData@PoliTO center

Luca Gioacchini

Darknets are passive probes listening to traffic reaching IP addresses that host no services. Traffic reaching them is unsolicited by nature and often induced by scanners, malicious senders and misconfigured hosts. Its peculiar nature makes it a valuable source of information to learn about malicious activities. However, the massive amount of packets and sources that reach darknets makes it hard to extract meaningful insights. In particular, multiple senders contact the darknet while performing similar and coordinated tasks, which are often commanded by common controllers (botnets, crawlers, etc.). How to automatically identify and group such senders that share similar behaviors remains an open problem. We here introduce DarkVec, a methodology to identify clusters of senders (i.e., IP addresses) engaged in similar activities on darknets. DarkVec leverages word embedding techniques (e.g. Word2Vec) to capture the co-occurrence patterns of sources hitting the darknets. We extensively test DarkVec and explore its design space in a case study using one month of darknet data. We show that with a proper definition of service, the generated embeddings can be easily used to
(i) associate unknown senders' IP addresses to the correct known labels (more than 96% accuracy), and
(ii) identify new attack and scan groups of previously unknown senders.

Biography:Luca Gioacchini is a Ph.D. candidate at Politecnico di Torino (PoliTO) and member of SmartData@PoliTO research center for Big Data technologies. He received the B.Sc. in Electronic Engineering at Università Politecnica delle Marche (UnivPM) in 2017 and the M.Sc. in ICT for Smart Societies at Politecnico di Torino in 2021. His research interests are in the field of machine learning and data science techniques applied to networking and cybersecurity. During his studies Luca has focused on deep learning and unsupervised graph mining techniques to detect coordinated events in darknet traffic.

On Convivio, SmartData@PoliTO and Microsoft Teams

The current edition of the SmartTalks is also open to PhD students and external speakers: write if you are interested in proposing your SmartTalk.

For more information, vist the website.