Anis Yusof (NU Singapore)

To improve the preparedness of Security Operation Center (SOC), analysts may leverage provenance graphs to deepen their understanding of existing cyberattacks. However, the unknown nature of a cyberattack may result in a provenance graph with incomplete details, thus limiting the comprehensive knowledge of the cyberattack due to partial indicators. Furthermore, using outdated provenance graphs imposes a limit on the understanding of cyberattack trends. This negatively impacts SOC operations that are responsible for detecting and responding to threats and incidents. This paper introduces PROVCON, a framework that constructs a provenance graph representative of a cyberattack. Based on documented cyberattacks, the framework reproduces the cyberattack and generates the corresponding data for attack analysis. The knowledge gained from existing cyberattacks through the constructed provenance graph is instrumental in enhancing the understanding and improving decision-making in SOC. With the use of PROVCON, SOC can improve its cybersecurity posture by aligning its operations based on insights derived from documented observations.

View More Papers

Provably Unlearnable Data Examples

Derui Wang (CSIRO's Data61), Minhui Xue (CSIRO's Data61), Bo Li (The University of Chicago), Seyit Camtepe (CSIRO's Data61), Liming Zhu (CSIRO's Data61)

Read More

Diffence: Fencing Membership Privacy With Diffusion Models

Yuefeng Peng (University of Massachusetts Amherst), Ali Naseh (University of Massachusetts Amherst), Amir Houmansadr (University of Massachusetts Amherst)

Read More

DRAGON: Predicting Decompiled Variable Data Types with Learned Confidence...

Caleb Stewart, Rhonda Gaede, Jeffrey Kulick (University of Alabama in Huntsville)

Read More