Get started
Author

Saad Ullah

Observed name: Ullah, Saad
Institution: Boston University
Observed institution: Boston University
OpenAlex ID: A5111098550
LLMs Cannot Reliably Identify and Reason About Security Vulnerabilities (Yet?): A Comprehensive Evaluation, Framework, and Benchmarks
2024 · Saad Ullah, Mingji Han, et al. · IEEE Symposium on Security and Privacy (S&P) · 208
PDF
From CVE Entries to Verifiable Exploits: An Automated Multi-Agent Framework for Reproducing CVEs
2025 · Ullah, Saad, Balasubramanian, Praneeth, et al. · arXiv (Cornell University) · 32
PDF
Multi-Agent Taint Specification Extraction for Vulnerability Detection
2026 · Ghebremichael, Jonah, Vasan, Saastha, et al. · arXiv (Cornell University) · 8
PDF
SelfOp: An Optimization Algorithm for Self-Improving Security Agents
2026 · Ullah, Saad, Kaya, Yigitcan, et al. · arXiv (Cornell University)
PDF
From Documentation to Zero-day Vulnerabilities: LLM-Driven Fuzzing of JavaScript Engines in PDF Readers
2026 · Guo, Suyue, Pletinckx, Stijn, et al. · arXiv (Cornell University)
PDF
Works count: 5
Citation count: 248
H-index: 3
I10-index: 2
Year
Topic
Type