Saastha Vasan

Saastha Vasan

AI Security Researcher

University of California, Santa Barbara

Biography

I am a PhD candidate at University of California, Santa Barbara, advised by Prof. Giovanni Vigna and Prof. Christopher Kruegel (expected graduation July 2026). My research sits at the intersection of machine learning and computer security, with a focus on malware analysis, reverse engineering, and ML-driven threat detection. I build systems that translate security research into practical tools for malware investigation, cyber threat intelligence, and vulnerability analysis.

Interests
  • Malware Analysis
  • Machine Learning
  • Artificial Intelligence (AI)
  • Program Analysis
  • Threat Intelligence
  • Vulnerability Assessment
Education
  • Doctor of Philosophy(Ph.D), Computer Science, 2021 - present

    University of California, Santa Barbara

  • Bachelor of Technology, Computer Science, 2016 - 2020

    Amrita Vishwa Vidyapeetham, Kerala, India

Publications

Experience

 
 
 
 
 
Ph.D. Intern
July 2025 – September 2025 Irvine, California
* Developed a large-scale .NET malware detection pipeline over 5M+ malicious and benign samples, achieving a 10% relative F1 improvement over prior academic baselines.
* Designed cross-platform XDR anomaly detection using Markov-chain process models and ancestry trees to identify anomalous execution patterns across macOS and Windows.
 
 
 
 
 
University of California Santa Barbara
Graduate Researcher
October 2021 – Present Santa Barbara, California
* Led research on MalwarePT, a binary-level foundation model for malware analysis, covering pretraining, downstream evaluation, and robustness analysis.
* Built ML/LLM pipelines that map malware behavior to malicious capabilities, convert attack evidence into CTI, and support automated vulnerability root-cause analysis.
* Participating in Capture The Flag (CTF) competitions as a member of team Shellphish.
 
 
 
 
 
Aspirify Enterprises Pvt
Infosec Engineer
December 2020 – July 2021 New Delhi, India
* Built red-team assessment modules for RCE, lateral movement, and N-day vulnerability simulation using C, C++, C#, and Python.
* Built modular exploit payloads and post-exploitation scripts that expanded the red-team framework's coverage for enterprise assessments.
 
 
 
 
 
University of California Santa Barbara
Research Intern
March 2020 – September 2020 Santa Barbara, California
* Designed and developed a novel malware post-detection framework that identifies potentially malicious capabilities in Windows malware, outperforming existing solutions by 20% in precision and 80% in recall.
* Reverse-engineered malware executables and mapped their attack implementations to the MITRE ATT&CK Framework.
 
 
 
 
 
Amrita Vishwa Vidyapeetham
Student Researcher
December 2016 – February 2020 Kerala, India
* Conducted malware analysis, documented results, and developed proof-of-concept attack methods.
* Fostered collaborative learning by teaching reverse engineering and malware analysis, promoting ongoing education.
* Participated actively in Capture The Flag (CTF) competitions as part of team bi0s

Achievements

DARPA AI Cyber Challenge (AIxCC) — Team Shellphish, Top-7 Semi-Final Finish, $2M Award
Core member of Team Shellphish during the DARPA AIxCC effort; contributed to automated root-cause analysis and vulnerability patching systems. The team secured a top-7 semi-final finish, won $2 million, and advanced to the finals.
Co-Chair, NSF-funded ACTION Institute Student Executive Council
Lead internship recruitment, coordinate guest speaker sessions, foster research collaborations across 11 universities, and drive outreach programs introducing AI and security to high school students.
Uiversity of California, Santa Barbara
Academic Excellence Fellowship
Amrita Vishwa Vidyapeetham
Magna Cum Laude: Bachelors Degree in Computer Science with first class distinction
Amrita Vishwa Vidyapeetham
Student Excellence Award for achievements in computer science
Amrita Vishwa Vidyapeetham
Student Excellence Award for achievements in computer science

Recent Posts