The Illusion of Local Privacy: Confidentiality Boundary Failures in Consumer LLM Serving Systems
cs.CR
Submitted: 2026-09-16
Updated: 2026-09-16
Comments: 20 pages, 1 figure, 12 tables. Code and experimental artifacts: https://github.com/0xzodiac/Local-LLMs-Forensics, Preprint under review for IEEE Transactions on Information Forensics and Security (T-IFS)
Code: https://github.com/0xzodiac/Local-LLMs-Forensics
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Quantifying Memorization Across Neural Language Models
- A Systematic Survey of Security Threats and Defenses in LLM-Based AI Agents: A Layered Attack Surface Framework
- Selective KV-Cache Sharing to Mitigate Timing Side-Channels in LLM Inference
- Local Is Not a Sufficient Privacy Boundary: Governing OS-Integrated On-Device AI
- Forensic Implications of Localized AI: Artifact Analysis of Ollama, LM Studio, and llama.cpp
- The Attack and Defense Landscape of Agentic AI: A Comprehensive Survey
- LLM Inference Serving: Survey of Recent Advances and Opportunities
- Ignore Previous Prompt: Attack Techniques For Language Models
Related papers
- SoK: AI-Augmented Binary Reversing
- Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
- Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
- Efficient Fuzzy PSI under One-Sided Assumptions
- Sealing the Audit-Runtime Gap for LLM Skills
- Token Composition: A Graph Based on EVM Logs