Evidence · DiggingBeagle record
AIDA SOC agent independent challenger cuts benchmark missed attacks
Primary or indexed evidence for Radar finding DB-RADAR-CP2-CP3-013. Benchmark result, not validated production incident detection.
- Source role
- primary disclosure
Evidence record
Primary or indexed evidence for Radar finding DB-RADAR-CP2-CP3-013. Benchmark result, not validated production incident detection.
Claim-level citations (3)
- supportsIndependent challenge reduced missed alerts in an agentic SOC benchmark: Across 1,247 replayed alerts, the five baseline agent triage approaches each missed at least 40.4% of attack-related alerts according to the ALERT-BENCH authors.
Abstract, ALERT-BENCH baseline results
- supportsIndependent challenge reduced missed alerts in an agentic SOC benchmark: The authors report AIDA F1 of 0.958 and a false-negative rate of 3.1%, with 18.4% of alerts escalated to analysts on the same benchmark.
Abstract, AIDA evaluation results
- supportsIndependent challenge reduced missed alerts in an agentic SOC benchmark: AIDA uses an independent challenger and a separate judge to reassess provisional alert decisions against an append-only investigation ledger.
Abstract, AIDA architecture and evidence requirements