Qatar Foundation for Education, Science and Community Development

Stevens Institute of Technology

Qatar Foundatiion

Ting Yu

Issa M Khalil

Mohamed Nabeel

Haipei Sun

Hui Wang

Sencun Zhu

Marc C Dacier

Eui J Choo

Euijin Choo

Lun-Pin Yuan

Autoencoder-based anomaly detection methods have been used in identifying anomalous users from large-scale enterprise logs with the assumption that adversarial activities do not follow past habitual patterns. Most existing approaches typically build models by reconstructing single-day and individual-user behaviors. However, without capturing long-term signals and group-correlation signals, the models cannot identify low-signal yet long-lasting threats, and will incorrectly report many normal users as anomalies on busy days, which, in turn, leads to a high false positive rate. A method is provided based on compound behavior, which takes into consideration long-term patterns and group behaviors. The provided method leverages a novel behavior representation and an ensemble of deep autoencoders and produces an ordered investigation list.

Anomalous user account detection systems and methods

The present disclosure provides new and innovative systems and methods for filtering encrypted messages. In an example, a computer-implemented method includes obtaining a message, determining sender profiling features of the message, determining enterprise graph features of the message, determining header features of the message, determining a message flag based on the sender profiling features, the enterprise graph features, and the header features, and processing the message based on the message flag.

Systems and methods for encrypted message filtering

The presently disclosed method and system exploits information and traces contained in DNS data to determine the maliciousness of a domain based on the relationship it has with other domains. A method may comprise providing data to a machine learning module that was previously trained on domain and IP address attributes or classifiers. The method then may comprise classifying apex domains and IP addresses based on the IP address and domain attributes or classifiers. Additionally, the method may comprise associated each of the domains and IP addresses based on the corresponding classification. The method may further comprise building a weighted domain graph at real-time utilizing the DNS data based on the aforementioned associations among domains. The method may then comprise assessing the maliciousness of a domain based on the weighted domain graph that was built.

Method and system for domain maliciousness assessment via real-time graph inference

Methods and systems for detecting malicious domains. The method comprises storing domain data for a plurality of domains and selecting a relationship parameter which represents a relationship between at least two of the domains. The method further comprises generating a graph for the domains by identifying a plurality of domain nodes, connecting the domain nodes with a plurality of edges and calculating an edge weight for each edge. The method further comprises identifying at least one domain node as a known malicious domain node and the other domain nodes as candidate domain nodes, calculating a malicious score for each candidate domain node based on the edge weights and identifying a domain in the plurality of domains as malicious if the malicious score is within a predetermined range.

Method to identify malicious web domain names thanks to their dynamics

Growing community of inventors

Doha, Qatar

Ting Yu