Ransomware 3.0: Self-Composing and LLM-Orchestrated

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Raz, Md, Udeshi, Meet, Charan, P. V. Sai, Krishnamurthy, Prashanth, Khorrami, Farshad, Karri, Ramesh
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866912557662470144
author Raz, Md
Udeshi, Meet
Charan, P. V. Sai
Krishnamurthy, Prashanth
Khorrami, Farshad
Karri, Ramesh
author_facet Raz, Md
Udeshi, Meet
Charan, P. V. Sai
Krishnamurthy, Prashanth
Khorrami, Farshad
Karri, Ramesh
contents Using automated reasoning, code synthesis, and contextual decision-making, we introduce a new threat that exploits large language models (LLMs) to autonomously plan, adapt, and execute the ransomware attack lifecycle. Ransomware 3.0 represents the first threat model and research prototype of LLM-orchestrated ransomware. Unlike conventional malware, the prototype only requires natural language prompts embedded in the binary; malicious code is synthesized dynamically by the LLM at runtime, yielding polymorphic variants that adapt to the execution environment. The system performs reconnaissance, payload generation, and personalized extortion, in a closed-loop attack campaign without human involvement. We evaluate this threat across personal, enterprise, and embedded environments using a phase-centric methodology that measures quantitative fidelity and qualitative coherence in each attack phase. We show that open source LLMs can generate functional ransomware components and sustain closed-loop execution across diverse environments. Finally, we present behavioral signals and multi-level telemetry of Ransomware 3.0 through a case study to motivate future development of better defenses and policy enforcements to address novel AI-enabled ransomware attacks.
format Preprint
id arxiv_https___arxiv_org_abs_2508_20444
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Ransomware 3.0: Self-Composing and LLM-Orchestrated
Raz, Md
Udeshi, Meet
Charan, P. V. Sai
Krishnamurthy, Prashanth
Khorrami, Farshad
Karri, Ramesh
Cryptography and Security
Using automated reasoning, code synthesis, and contextual decision-making, we introduce a new threat that exploits large language models (LLMs) to autonomously plan, adapt, and execute the ransomware attack lifecycle. Ransomware 3.0 represents the first threat model and research prototype of LLM-orchestrated ransomware. Unlike conventional malware, the prototype only requires natural language prompts embedded in the binary; malicious code is synthesized dynamically by the LLM at runtime, yielding polymorphic variants that adapt to the execution environment. The system performs reconnaissance, payload generation, and personalized extortion, in a closed-loop attack campaign without human involvement. We evaluate this threat across personal, enterprise, and embedded environments using a phase-centric methodology that measures quantitative fidelity and qualitative coherence in each attack phase. We show that open source LLMs can generate functional ransomware components and sustain closed-loop execution across diverse environments. Finally, we present behavioral signals and multi-level telemetry of Ransomware 3.0 through a case study to motivate future development of better defenses and policy enforcements to address novel AI-enabled ransomware attacks.
title Ransomware 3.0: Self-Composing and LLM-Orchestrated
topic Cryptography and Security
url https://arxiv.org/abs/2508.20444