arxiv
PublishedMay 16, 2026 at 4:00 AM
—neutral
ExploitBench: A Capability Ladder Benchmark for LLM Cybersecurity Agents
Publisher summary· verbatim
arXiv:2605.14153v1 Announce Type: cross Abstract: Exploitation is not a binary event. It is a ladder of acquiring progressive capabilities, from executing a single buggy line of code to taking full control of the target. However, existing LLM security benchmarks treat a crash as exploitation success
Stay posted· Newsletter
A 5-min weekly brief — top movers, price watch, story of the week.
Discussion
No replies yet. Be first.
Related coverage
More from ARXIV
arxivSvarna: An Open Corpus Workbench for Modern Greek14harxivWhen LLMs Agree, Are They Right? Auditing Self-Consistency and Cross-Model Agreement as Confidence Signals14harxivPLURAL: A Global Dataset for Value Alignment14harxivBiSCo-LLM: Lookup-Free Binary Spherical Coding for Extreme Low-Bit Large Language Model Compression14hThe Bubble Brief
WEEKLYRead AI insights every Tuesday — top movers, new releases, story of the week.
Originally published on arxiv ↗