Forensic Implications of Localized AI: Artifact Analysis of Ollama, LM Studio, and llama.cpp

TL;DR

This study systematically analyzes artifacts left by local LLM applications like Ollama, LM Studio, and llama.cpp on Windows and Linux, revealing key forensic evidence and implications for privacy and legal proceedings.

Contribution

It provides the first comprehensive forensic artifact analysis of popular local LLM clients, detailing evidence persistence, detection methods, and implications for digital investigations.

Findings

Recovered plaintext prompt histories in JSON files

Identified unique file signatures for detection

Documented differences in evidence persistence across applications

Abstract

The proliferation of local Large Language Model (LLM) runners, such as Ollama, LM Studio and llama.cpp, presents a new challenge for digital forensics investigators. These tools enable users to deploy powerful AI models in an offline manner, creating a potential evidentiary blind spot for investigators. This work presents a systematic, cross platform forensic analysis of these popular local LLM clients. Through controlled experiments on Windows and Linux operating systems, we acquired and analyzed disk and memory artifacts, documenting installation footprints, configuration files, model caches, prompt histories and network activity. Our experiments uncovered a rich set of previously undocumented artifacts for each software, revealing significant differences in evidence persistence and location based on application architecture. Key findings include the recovery of plaintext prompt histories in structured JSON files, detailed model usage logs and unique file signatures suitable for forensic detection. This research provides a foundational corpus of digital evidence for local LLMs, offering forensic investigators reproducible methodologies, practical triage commands and analyse this new class of software. The findings have critical implications for user privacy, the admissibility of AI-related evidence and the development of anti-forensic techniques.