What researchers learned about building an LLM security workflow
Oslo and FFI researchers show structured agentic workflows lift LLM alert-triage accuracy from 0% to about 93% on malicious cases.
55
Organization
University of Oslo
- Mentions · 7d0
- Mentions · 30d0
- All mentions1
- First seenAug 24, 2026
- Last mentionedAug 24, 2026
Timeline
1 articles · newest firstAppears with
- Gemma 3:27Bai model · 1
- AIT Log Data Set V1.1product · 1
- University of Oslovendor · 1
- Claude 3 Haikuai model · 1
- GPT-5-miniai model · 1
- Qwen3:30Bai model · 1
- Suricataproduct · 1
- Norwegian Defence Research Establishmentvendor · 1
- Norwegian Defence Research Establishmentorganization · 1
Entities are extracted by the model from each article. First seen , last mentioned . Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.