CyberMaskQA is a new privacy-aware QA benchmark for cybersecurity that annotates private entities in realistic organizational scenarios with causal dependencies to jointly evaluate reasoning accuracy and masking performance.
AttackQA: Development and adoption of a dataset for assisting cybersecurity operations using fine-tuned and open-source LLMs.arXiv:2411.01073, 2024
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CR 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Controlled experiments across 96 LoRA adapters show that reduced optimizer updates explain nearly all observed memorization drops in DP-SGD fine-tuning, HMAC pseudonymization cuts exposure 40-61% without creating new targets, and 1-3B models achieve only 0.19-0.28 F1 under the tested budget.
citing papers explorer
-
CyberMaskQA: A Privacy-Aware Benchmark for Evaluating Large Language Models in Cybersecurity Question Answering
CyberMaskQA is a new privacy-aware QA benchmark for cybersecurity that annotates private entities in realistic organizational scenarios with causal dependencies to jointly evaluate reasoning accuracy and masking performance.
-
Decomposing Memorization Reduction in Privacy-Preserving Fine-Tuning of SLMs for CSIRTs
Controlled experiments across 96 LoRA adapters show that reduced optimizer updates explain nearly all observed memorization drops in DP-SGD fine-tuning, HMAC pseudonymization cuts exposure 40-61% without creating new targets, and 1-3B models achieve only 0.19-0.28 F1 under the tested budget.