Devops Gathering 2020 Building A Graph User Interface For Malware Analysis By Stefan Hausotte

Building A Graph User Interface For Malware Analysis By Stefan Hausotte Building a graph user interface for malware analysis data considerations there are several strategies we used to help performance and usability • the minimal dataset to accomplish the problem rendered to the screen. (don't render everything) • search functionality to find nodes of interest. This year i presented the joint effort of g data cyberdefense and expero inc. to build a graph user interface for our threat intelligence database. the technology used to create the graphql backend and corresponding web frontend was the focus of the presentation.

Presenting A Graph Based User Interface At The Global Graph Summit End of january 2020, the global graph summit took place in austin tx, usa. the summit is the biggest conference in the world with a focus on graph computation and graph related technologies. stefan hausotte from g data presented the work of his team for the second time at the global graph summit. Speaker deck pro: add privacy options and schedule the publishing of your decks upgrade. The document discusses using graph analytics and mining techniques for malware detection. specifically, it explores using graphs to extract malware dictionaries from dns traffic to detect dictionary generated domain algorithms (dga). Abstract detecting malware using dynamic analysis techniques is an efficient method. those familiar techniques such as signature based detection perform poorly when attempting to identify zero day malware, and it is also a challenging and time consuming task to manually engineer malicious behaviors.

Presenting A Graph Based User Interface At The Global Graph Summit The document discusses using graph analytics and mining techniques for malware detection. specifically, it explores using graphs to extract malware dictionaries from dns traffic to detect dictionary generated domain algorithms (dga). Abstract detecting malware using dynamic analysis techniques is an efficient method. those familiar techniques such as signature based detection perform poorly when attempting to identify zero day malware, and it is also a challenging and time consuming task to manually engineer malicious behaviors. In this section, we present graph based malware detection for android platform, starting from the global methodology to build graphs from disassembled android applications, to the review of existing works that leverage grl for the detection of malware. We extract entities by building a customized named entity recognizer called `malware entity extractor' (mee). we then build a neural network to predict how pairs of `malware entities' are related to each other. This initiative focuses on the creation of a comprehensive knowledge graph from detailed malware analysis reports. this graph not only categorizes malware instances but also connects them to related threat actors and campaigns, revealing the broader narrative of cyber threats. In this paper, we propose a framework that aims to enhance the performance of gnn based models for malware detection by integrating a graph reduction module into the learning process.