Chronohunt: Determining Optimal Pace for Automated Alert Analysis in Threat Hunting Using Reinforcement Learning
Bibliographic record
Abstract
Threat hunting stands out as a proactive practice applied to identify stealthy threats that evade traditional detection mechanisms. Although powerful, threat hunting demands significant investments in terms of knowledge, time, and resources to meticulously analyze massive amounts of logs, and formulate threat hypotheses. Particularly, real-time threat hunting necessitates substantial manpower and computational resources to identify threats and might lead to inefficiencies and overlooked threats. Conversely, while more economical in resource allocation, batch-mode hunting risks missing fast-moving threats. To address these pivotal challenges, we formulate the problem of pacing the threat hunting in security operational environments and design Chronohunt, a solution that automatically and adaptively adjusts the threat hunting pace in alignment with the security importance, volume of events, available resources, and the evolving threat landscape. Chronohunt integrates two optimizations: (i) an initial heuristic optimization using grid search to establish a baseline hunting pace, and (ii) a dynamic optimization using reinforcement learning to dynamically fine-tune the pace in response to changes in the environment (e.g., hunting performance, evolving threat landscape, event importance, etc.). Obtained results show the efficacy of Chronohunt in adaptively aligning the hunting pace based on changes in the environmental conditions while ensuring high accuracy in threat hunting and optimal resource utilization.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.005 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".