Coordinated Machine Learning-Based Vulnerability & Security Patching for Resilient Virtual Computing Infrastructure

PI(s), Co-PI(s), Researchers:

PI: Helen Gu; Researchers: Olufogorehan Tunde-Onadele (Fogo)

HARD PROBLEM(S) ADDRESSED
This refers to Hard Problems, released November 2012.

Resilient Architectures

Our research aims at aiding administrators of virtualized computing infrastructures in making services more resilient to security attacks through applying machine learning to reduce both security and functionality risks in software patching by continually monitoring patched and unpatched software to discover vulnerabilities and triggering proper security updates.

PUBLICATIONS
Papers written as a result of your research from the current quarter only.

Toward Just-in-Time Patching for Containerized Applications, Olufogorehan Tunde-Onadele,Yuhang Lin,Jingzhu He, Xiaohui Gu, HotSoS 2020 (poster).

KEY HIGHLIGHTS
Each effort should submit one or two specific highlights. Each item should include a paragraph or two along with a citation if available. Write as if for the general reader of IEEE S&P.
The purpose of the highlights is to give our immediate sponsors a body of evidence that the funding they are providing (in the framework of the SoS lablet model) is delivering results that "more than justify" the investment they are making.

In this quarter, we focused on refining our runtime targeted patching system implementation and design. We wrote an extended abstract about the work, which has been accepted by HotSoS 2020. We have started to refine our detection scheme to improve on those mis-detections by adding system call arguments into our analysis. We continued our work on an aggregated learning framework to further improve anomaly detection accuracy for microservices system consisting of many ephemeral containers.

COMMUNITY ENGAGEMENTS

None.

EDUCATIONAL ADVANCES:

One PhD students Fogo (Olufogorehan Tunde-Onadele) is currently supported by the grant.