Negative-One-Day Malware Detection with Generative AI: A Stable Diffusion-Based Proactive Defense Framework

The detection of zero-day malware represents one of the most significant challenges in contemporary cybersecurity. In this paper, we introduce a novel concept called “Negative-One-Day Malware Detection”, which aims to identify potentially malicious software before it is actually created by threat actors. Our approach leverages recent advancements in generative AI, specifically diffusion-based generative models, to generate and analyze potential future malware variants. By doing so, we can train detection systems to recognize these variants before they emerge in the wild, thereby closing the critical protection gap that currently exists between malware creation and detection. We demonstrate the effectiveness of our approach through extensive experimentation, showing that our framework can generate executable malware samples that combine characteristics from different families while exhibiting novel behaviors. These synthetically generated samples significantly improve the detection capabilities of security systems when incorporated into training data, providing a proactive rather than reactive approach to cybersecurity.