paper-with-me

Papers

Military AI Cyber Agents (MAICAs) Constitute a Global Threat to Critical Infrastructure

2025-06-12 · Timothy Dubber, Seth Lazar

This paper argues that autonomous AI cyber-weapons - Military-AI Cyber Agents (MAICAs) - create a credible pathway to catastrophic risk. It sets out the technical feasibility of MAICAs, explains why geopolitics and the nature of cyberspace make MAICAs a catastrophic risk, and proposes political, defensive-AI and analogue-resilience measures to blunt the threat.

📄 PDF Abstract BibTeX arXiv:2506.12094

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Exploring reinforcement learning for incident response in autonomous military vehicles

2024-10-28 · Henrik Madsen, Gudmund Grov, Federico Mancini, Magnus Baksaas 외

Unmanned vehicles able to conduct advanced operations without human intervention are being developed at a fast pace for many purposes. Not surprisingly, they are also expected to significantly change how military operati…

reinforcement-learningReinforcement Learning

EdgeRunner 20B: Military Task Parity with GPT-5 while Running on the Edge

2025-10-30 · Jack FitzGerald, Aristotelis Lazaridis, Dylan Bates, Aman Sharma 외 arxiv

We present EdgeRunner 20B, a fine-tuned version of gpt-oss-20b optimized for military tasks. EdgeRunner 20B was trained on 1.6M high-quality records curated from military documentation and websites. We also present four …

Red Lines and Grey Zones in the Fog of War: Benchmarking Legal Risk, Moral Harm, and Regional Bias in Large Language Model Military Decision-Making

2025-10-03 · Toby Drinkall arxiv

As military organisations consider integrating large language models (LLMs) into command and control (C2) systems for planning and decision support, understanding their behavioural tendencies is critical. This study deve…

Cybersecurity is the True Frontier for Generative AI Success or Failure

2026-06-27 · Edward Raff, Maor Ashkenazi, Sagar Samtani, David J. Elkind 외 arxiv

Cybersecurity is a real-life test-bed for many machine learning problems at once, especially when considering modern strides in using Large Language Models (LLMs) to automate processes as ``agents.'' Cybersecurity workfl…

Escalation Risks from Language Models in Military and Diplomatic Decision-Making

2024-01-07 · Juan-Pablo Rivera, Gabriel Mukobi, Anka Reuel, Max Lamparth 외

Governments are increasingly considering integrating autonomous AI agents in high-stakes military and foreign-policy decision-making, especially with the emergence of advanced generative AI models like GPT-4. Our work ai…

Decision MakingLanguage Modelling