The paper proposes a unified closed-loop threat taxonomy to systematically analyze and defend foundation models by explicitly framing the bidirectional security interactions between data and models.

The paper introduces a challenging benchmark for LLM agents to perform unsupervised threat hunting on raw Windows event logs, finding that current frontier models perform poorly and are not ready for…

This study longitudinally evaluates the adversarial robustness of Android malware detection systems over a decade, finding that temporal separation significantly degrades robustness due to concept dri…

The paper introduces an end-to-end framework that not only detects network intrusions using deep learning but also generates actionable, citation-grounded mitigation reports using a Retrieval-Augmente…

The paper introduces AgentCyberRange, an open, multi-range infrastructure for measuring autonomous cyber attack capability in realistic cyber ranges, and evaluates six frontier AI systems.

The paper investigates forecasting sparse and bursty vulnerability sightings, concluding that traditional time-series models like SARIMAX are inadequate, and count-based methods like Poisson regressio…

The paper introduces CyBiasBench, a comprehensive benchmark that quantifies the inherent, agent-specific bias in LLM agents' attack selection patterns in cybersecurity scenarios.

SentinelSphere is an AI platform that integrates advanced deep learning for real-time threat detection with an LLM-powered training system to holistically address both technical and human-factor cyber…

The paper introduces a comprehensive taxonomy and auditing framework to assess the collective coverage of existing LLM attack benchmarks, revealing significant and systematic gaps in current testing m…

ZERO-APT introduces a novel closed-loop adversarial framework for automated penetration testing that simulates attacks against an intelligent, real-time defending system, achieving a high attack succe…

The paper introduces the CAI Dataset, a massive, multi-terabyte corpus of real-world, hands-on cybersecurity LLM trajectories, designed to address the performance bottleneck caused by expert operator…

The paper argues that zero-day attacks primarily exploit undisclosed vulnerabilities rather than exhibiting novel behaviors, advocating for vulnerability-centric detection methods over purely behavior…

The paper introduces STRIDE-AI, a novel threat modeling framework that adapts classical STRIDE for generative AI, successfully reducing the attack success rate of a tested LLM chatbot from 80% to 15%.

The paper proposes a system that operationalizes cybersecurity governance frameworks by integrating them with attack-path modeling and Deep Reinforcement Learning to generate practical, resource-const…

The paper introduces GenTI, a novel LLM-driven benchmark and dataset, to automatically generate high-quality, deployable IDPS rules for detecting unseen and zero-day cyber attacks.

This study empirically measures the consistency and success rate of autonomous LLM penetration testing across multiple services, finding statistically significant differences in exploitation capabilit…

This study empirically measures the consistency and effectiveness of autonomous LLM penetration testing across multiple services, finding statistically significant differences in exploitation rates am…

This paper investigates the performance of orchestrated ensembles of small language models in analyzing malware detonation reports, surpassing the capabilities of single large language models and open…

The paper proposes a multi-modal contrastive learning framework to improve the generalization of machine learning models in cybersecurity by transferring knowledge from rich textual vulnerability desc…