Akul Goyal
PhD candidate, cybersecurity researcher, and co-founder of Provenance Security
Urbana-Champaign, Illinois
Summary
Akul Goyal is a dedicated PhD candidate in Computer Science at the University of Illinois Urbana-Champaign, with a strong focus on cybersecurity research. His work bridges computer security, graph analysis, and machine learning, particularly in developing provenance-based systems for anomaly-based intrusion detection. He is advised by Professor Adam Bates and his research aims to tackle real-world security challenges by understanding the complete context surrounding telemetric events. akulgoyal+1
Akul is recognized for his innovative contributions to cybersecurity, evident through his co-founding of Provenance Security and his recognition as an Illinois Innovation Award finalist in 2024. His innovation focuses on developing a next-generation Endpoint Protection and Response (EDR) system that significantly reduces false positives, automates alert investigation, and enhances resilience against advanced evasion techniques. akulgoyal+1
His practical experience includes multiple internships, notably as a year-round Research Intern at Sandia National Laboratories in the Center for Cyber Defenders. Here, he contributed to the Tracer FIRE cybersecurity training scenario by developing data parsers and labeling events, gaining insights into national security applications of his academic research. sandia
Akul is a prolific author of academic papers, with publications in top-tier security conferences such as IEEE Symposium on Security and Privacy (S&P) and Network and Distributed System Security Symposium (NDSS). His research includes topics like embedding root cause analysis in intrusion detection, streaming threat detection over provenance graphs, and mimicry attacks against host intrusion detection systems. akulgoyal+1
Work
Education
Writing
R-CAID: Embedding Root Cause Analysis within Provenance-based Intrusion Detection
January 1, 2024ORCHID: Streaming Threat Detection over Versioned Provenance Graphs
January 1, 2024Class-based Subset Selection for Transfer Learning under Extreme Label Shift
January 1, 2024Sometimes, you aren't what you do: Mimicry attacks against provenance graph host intrusion detection systems
January 1, 2023Explores a new threat model where zero-permission motion sensors can be used to steal permission-protected private information from smartphone voice assistants, demonstrating high accuracy and proposing defense mechanisms.
SoK: History is a vast early warning system: Auditing the provenance of system intrusions
January 1, 2023FAuST: Striking a bargain between forensic auditing's security and throughput
January 1, 2022Semi-Supervised Boosting Via Self Labeling
January 1, 2019Master's thesis on noise-resistant machine learning.