CyberFactory Scales Cybersecurity with Real‑World Instances
open-source
| Source: HF Papers | Original article
Researchers aim to scale cybersecurity using open‑source LLMs, building on advances seen in closed‑source models like Mythos, though open tools remain limited.
A new open‑source framework called **CyberFactory** has been released, aiming to boost the cybersecurity capabilities of large language models (LLMs) by turning real‑world vulnerability data into training material. The system, described in a recent paper by Jian Yang and colleagues, ingests public artifacts such as CVEs, ARVO entries and OSS‑Fuzz findings, reconstructs both the vulnerable and patched program states, and generates a self‑contained task description. By stripping away privileged verification signals before synthesising execution trajectories, CyberFactory creates “agentic” training instances that can be fed to LLMs.
The framework is used to train an open‑weight model named **Aegis**, which the authors say outperforms existing open‑source baselines on three core security tasks: generating proof‑of‑concept exploits, suggesting patches, and answering vulnerability‑related questions. This development arrives at a time when closed‑source LLMs such as Mythos are already demonstrating advanced coding and security functions, while the open‑source community has struggled to match them.
If the claims hold up, CyberFactory could narrow the gap between proprietary and community‑driven AI security tools, making sophisticated automated analysis more accessible to researchers, defenders and smaller organisations that lack commercial licences. By grounding training on authentic, “wild” vulnerabilities, the approach also promises more realistic evaluation and reduced reliance on synthetic benchmarks.
The next steps to watch include broader adoption of the CyberFactory pipeline, independent benchmarking of Aegis against both open and closed models, and potential integration into existing security workflows. Community feedback on the framework’s usability and any emerging concerns about releasing powerful exploit‑generation capabilities in an open format will also shape its impact on the evolving AI‑security landscape.
Sources
Back to AIPULSEN