Dynamic Threat Intelligence Coalitions for Improved Cyber Defense Capabilities
Bibliographic record
Abstract
In the dynamic landscape of cybersecu-rity and cyber warfares, Cyber Threat Intelligence (CTI) is increasingly relied on for gathering and sharing the latest information about threats and their trends. Current CTI sharing methods (e.g., ISACs, automated STIX/TAXII platforms), face challenges in terms of scalability, trust, and data quality issues. This is because they often lack systematic metrics for evaluating the quality and relevance of the threat data that are being shared. Moreover, they do not offer any mechanism to enable participating organizations to autonomously make decisions as to what Threat Intelligence providers to request and share data from/to. To address these limitations, we propose a novel Threat Intelligence sharing approach based on coalitional game theory. We first propose a set of metrics that enable organizations to assess the effectiveness of the shared Threat Intelligence data. Based on these metrics, we propose a preference function and a coalition formation algorithm that enable organizations to autonomously join and leave Threat Intelligence coalitions until reaching a Nash-Stable situation wherein no organization has incentive to leave its current coalition and join another one. Experiments suggest that our solution significantly improves the Mean Time to Detect (MTTD), Mean Time to Respond (MTTR) and Containment Rate.
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 | 0.004 | 0.008 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.005 |
| Open science | 0.002 | 0.006 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.004 | 0.001 |
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".