Agentic biological AI systems like Biomni and K-Dense assist with dual-use tasks blocked by safeguards and gain performance uplift on WMDP proxies; BioVeil MATRIX is introduced as a 10-category taxonomy with 22 techniques to categorize and red-team AI-enabled biosecurity risks.
Sok: The mitre att&ck framework in research and practice
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 3roles
background 1polarities
background 1representative citing papers
NetSecBed delivers a declarative, container-native framework that automates generation of reproducible network traffic evidence including attacks and benign flows for cybersecurity research.
Systematic review of 80 papers shows TTP extraction shifting to transformer and LLM methods but limited by narrow datasets, single-label focus, and low reproducibility.
citing papers explorer
-
BioVeil MATRIX: Uncovering and categorizing vulnerabilities of agentic biological AI scientists
Agentic biological AI systems like Biomni and K-Dense assist with dual-use tasks blocked by safeguards and gain performance uplift on WMDP proxies; BioVeil MATRIX is introduced as a 10-category taxonomy with 22 techniques to categorize and red-team AI-enabled biosecurity risks.
-
NetSecBed: A Container-Native Testbed for Reproducible Cybersecurity Experimentation
NetSecBed delivers a declarative, container-native framework that automates generation of reproducible network traffic evidence including attacks and benign flows for cybersecurity research.
-
What Are Adversaries Doing? Automating Tactics, Techniques, and Procedures Extraction: A Systematic Review
Systematic review of 80 papers shows TTP extraction shifting to transformer and LLM methods but limited by narrow datasets, single-label focus, and low reproducibility.