Recent advancements in AI for cybersecurity are focusing on enhancing the capabilities of language models and feature selection techniques to address the evolving threat landscape. New models like RedSage and Foundation-Sec-8B-Reasoning are being developed to provide domain-specific expertise while maintaining general reasoning abilities, enabling more effective responses to complex cyber threats. These models are particularly valuable for organizations seeking to automate cybersecurity operations without compromising sensitive data. Additionally, innovative frameworks such as CAFE-GB are improving malware detection by offering scalable and interpretable feature selection, which is crucial for managing high-dimensional datasets. The integration of AI in cybersecurity is also prompting a re-evaluation of how these systems govern decision-making under uncertainty, emphasizing the need for accountable autonomy. As cybercriminals increasingly leverage AI for malicious purposes, the demand for robust, adaptive defenses is more pressing than ever, driving research toward solutions that can keep pace with both offensive and defensive strategies.
The escalating frequency of cyber-attacks poses significant challenges for organisations, particularly small enterprises constrained by limited in-house expertise, insufficient knowledge, and financia...
We present a fine-tuned RoBERTa-base classifier (125M parameters) for mapping Common Vulnerabilities and Exposures (CVE) descriptions to Common Weakness Enumeration (CWE) categories. We construct a la...
DARPA's AI Cyber Challenge (AIxCC) showed that cyber reasoning systems (CRSs) can go beyond vulnerability discovery to autonomously confirm and patch bugs: seven teams built such systems and open-sour...
Cybersecurity operations demand assistant LLMs that support diverse workflows without exposing sensitive data. Existing solutions either rely on proprietary APIs with privacy risks or on open models l...
Is robot cybersecurity broken by AI? Consumer robots -- from autonomous lawnmowers to powered exoskeletons and window cleaners -- are rapidly entering homes and workplaces, yet their security remains ...
High-dimensional malware datasets often exhibit feature redundancy, instability, and scalability limitations, which hinder the effectiveness and interpretability of machine learning-based malware dete...
With frequently evolving Advanced Persistent Threats (APTs) in cyberspace, traditional security solutions approaches have become inadequate for threat hunting for organizations. Moreover, SOC (Securit...
The parallel evolution of Large Language Models (LLMs) with advanced code-understanding capabilities and the increasing sophistication of malware presents a new frontier for cybersecurity research. Th...
We present Foundation-Sec-8B-Reasoning, the first open-source native reasoning model for cybersecurity. Built upon our previously released Foundation-Sec-8B base model (derived from Llama-3.1-8B-Base)...
Android malware has become an increasingly critical threat to organizations, society and individuals, posing significant risks to privacy, data security and infrastructure. As malware continues to evo...