Lambang Akbar Wijayadi
Titles as the sources gave them. In 1 entry, with 0 checked quotations.
In the Base
Every entry they appear in.
CyberBinGym: Can AI Agents Turn Binary Patches into Real Exploits?
According to the abstract, Lambang Akbar Wijayadi and colleagues introduce a 100-task benchmark built from real vulnerabilities in 53 projects, and report that the strongest agent recovers the vulnerability in 88% of tasks and exploits it in 20%.