MiST (Mid-trained Security Transformer) is a suite of 8B and 32B language models tailored for cybersecurity, achieving strong performance on public benchmarks. The approach uses a mid-training stage that adapts general pre-trained models to the domain by curating a compact, expert-vetted seed corpus and generating high-quality synthetic training data, rather than continual pre-training on large raw text. MiST checkpoints improve mean cybersecurity accuracy by +13.1 and +8.6 absolute percentage points over Qwen baselines for 8B and 32B models, respectively, and provide a stronger initialization for downstream task-specific fine-tuning and reinforcement learning.
arXiv:2507. 02964v2 Announce Type: replace-cross Abstract: The increasing scale of AI workloads demands High-Performance Computing (HPC) infrastructure and training methodologies that are both scalable and sustainable.
arXiv:2510. 14113v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are transforming everyday applications, yet deployment in cybersecurity lags due to a lack of high-quality, domain-specific models and training datasets.
The paper introduces a Teacher-Student framework that uses a large language model (LLM) to generate weak labels for unlabeled cybersecurity tweets, enabling the training of domain‑specific pre‑trained language models (PLMs) without extensive manual annotation. Experiments demonstrate that PLMs trained solely on these LLM‑generated labels achieve F1 scores above 0.92, within 3 percentage points of fully human‑supervised models across all evaluated architectures. This approach offers a practical alternative for creating cybersecurity‑specific training data when expert annotation resources are scarce.
arXiv:2606. 15123v1 Announce Type: cross Abstract: We study the task of CVE-conditioned exploit generation, where a model drafts proof-of-concept (PoC) exploits given software vulnerability context.
arXiv:2607. 09936v1 Announce Type: cross Abstract: Cybersecurity systems must adapt rapidly to emerging threats.
arXiv:2606. 18190v1 Announce Type: cross Abstract: Multi-stage cyberattacks span system, network, and browser logs.
arXiv:2607. 02072v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed in domains requiring guardrails to detect unsafe, off-topic, or adversarial prompts.
arXiv:2608.23181v1 Announce Type: cross Abstract: As large language models (LLMs) continue to advance in coding capabilities, their potential in cybersecurity has drawn increasing research attention,...
arXiv:2508.02312v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs), now a foundation in advancing natural language processing, power applications such as text generation, machine...
arXiv:2606. 18166v1 Announce Type: cross Abstract: Classifying Cyber Threat Intelligence (CTI) using MITRE Adversarial Tactics, Techniques, and Common Knowledge (ATT&CK) is essential for proactive defense, but historically required extensive human effort.
SecJev is a family of Jev-like decision models specialized for security, ranging from 0.8 B to 9 B parameters. Built on Kev’s single‑pass candidate scorer, it learns Boolean, choice, and ordered decisions from text, telemetry, and observation histories, and is trained on the SecJev‑Corpus that unifies source‑label prediction and explicit‑policy evaluation across 14 tasks and eight sources. The security specialization improves every model, with SecJev‑0.8B outperforming general Kev‑9B by 20.51 percentage points in task‑macro accuracy and matching generative fine‑tuning in accuracy and latency while using less peak inference memory.
arXiv:2512. 18542v3 Announce Type: replace-cross Abstract: AI coding assistants produce vulnerable code in 45\% of security-relevant scenarios~\cite{veracode2025}, yet no public training dataset teaches both traditional web security and AI/ML-specific defenses in a format suitable for instruction tuning.