MemSecBench
Explore score history ↗Evaluates lifecycle security of agent memory systems with 310 cases across 48 contexts, using a Write-Execute-Forget protocol and evidence-based adjudication across seven checkpoints.
- Released
- 2026-07-29
- Institutions
- Zhejiang University of Technology
- Evaluates
- Agents, General AI, Language & Knowledge
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- unreviewed
MemSecBench paper
No reported scores are on record for this benchmark yet.