DeepChronos: Temporal Neuro-Symbolic Reasoning for Multi-Step Attack Detection
arXiv cs.AI · 10 Nov 2026, 03:37 AEST
DeepChronos is a neuro-symbolic network intrusion detection system designed to improve multi-step attack detection. It shifts the paradigm from a detect-first approach to detection through logical progression.
Key facts
- Modern cyber threats commonly unfold as multi-step attacks comprising temporally and causally related phases.
- We present DEEPCHRONOS, a neuro-symbolic network intrusion detection system that shifts the paradigm from detect first and correlate later to detection through logical progression.
- Evaluations on DARPA 2000 and AIT-LDS V2 show that DEEPCHRONOS improves macro F1 over purely neural baselines by up to 11.3%, eliminates causal violations under strict temporal constraints, and maintains millisecond-scale inference latency.
Read aloud
DeepChronos is a neuro-symbolic network intrusion detection system designed to improve multi-step attack detection. It shifts the paradigm from a detect-first approach to detection through logical progression. Modern cyber threats commonly unfold as multi-step attacks comprising temporally and causally related phases. We present DEEPCHRONOS, a neuro-symbolic network intrusion detection system that shifts the paradigm from detect first and correlate later to detection through logical progression. Evaluations on DARPA two thousand and AIT-LDS V2 show that DEEPCHRONOS improves macro F1 over purely neural baselines by up to eleven point three percent, eliminates causal violations under strict temporal constraints, and maintains millisecond-scale inference latency.
Sources in this cluster
- DeepChronos: Temporal Neuro-Symbolic Reasoning for Multi-Step Attack Detection
arXiv cs.AI · 10 Nov 2026, 03:37 AEST