mlsanityData to 7 Oct 2026

A Survey: Towards Privacy and Security in Mobile Large Language Models

arXiv 2509.02411 ↗First posted 2 Sep 2025cs.CR cs.AIcited by 1

Not on the map. Why?

Abstract (arXiv)

Mobile Large Language Models (LLMs) are revolutionizing diverse fields such as healthcare, finance, and education with their ability to perform advanced natural language processing tasks on-the-go. However, the deployment of these models in mobile and edge environments introduces significant challenges related to privacy and security due to their resource-intensive nature and the sensitivity of the data they process. This survey provides a comprehensive overview of privacy and security issues associated with mobile LLMs, systematically categorizing existing solutions such as differential privacy, federated learning, and prompt encryption. Furthermore, we analyze vulnerabilities unique to mobile LLMs, including adversarial attacks, membership inference, and side-channel attacks, offering an in-depth comparison of their effectiveness and limitations. Despite recent advancements, mobile LLMs face unique hurdles in achieving robust security while maintaining efficiency in resource-constrained environments. To bridge this gap, we propose potential applications, discuss open challenges, and suggest future research directions, paving the way for the development of trustworthy, privacy-compliant, and scalable mobile LLM systems.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 47 of its 91 references that are in the map. First posted on arXiv 2 Sep 2025.

Builds on

47 of 91 references.

References · 47

  1. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  2. 2023Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injectioncited by 1,339
  3. 2023LLM-Pruner: On the Structural Pruning of Large Language Modelscited by 643
  4. 2023Harnessing the Power of LLMs in Practice: A Survey on ChatGPT and Beyondcited by 409
  5. 2024Do Membership Inference Attacks Work on Large Language Models?cited by 188
  6. 2023Towards Building the Federated GPT: Federated Instruction Tuningcited by 184
  7. 2023FederatedScope-LLM: A Comprehensive Package for Fine-tuning Large Language Models in Federated Learningcited by 146
  8. 2024FLoRA: Federated Fine-Tuning Large Language Models with Heterogeneous Low-Rank Adaptationscited by 144
  9. 2024The Emerged Security and Privacy of LLM Agent: A Survey with Case Studiescited by 127
  10. 2024OpenFedLLM: Training Large Language Models on Decentralized Private Data via Federated Learningcited by 124
  11. 2024On-Device Language Models: A Comprehensive Reviewcited by 101
  12. 2024On Protecting the Data Privacy of Large Language Models (LLMs): A Surveycited by 91
35 more
  1. 2023Practical Membership Inference Attacks against Fine-tuned Large Language Models via Self-prompt Calibrationcited by 90
  2. 2024Revolutionizing Finance with LLMs: An Overview of Applications and Insightscited by 88
  3. 2024From LLMs to LLM-based Agents for Software Engineering: A Survey of Current, Challenges and Futurecited by 85
  4. 2022When Federated Learning Meets Pre-trained Language Models' Parameter-Efficient Tuning Methodscited by 74
  5. 2024Covert Malicious Finetuning: Challenges in Safeguarding LLM Adaptationcited by 74
  6. 2024FedBiOT: LLM Local Fine-tuning in Federated Learning without Full Modelcited by 73
  7. 2020Local and Central Differential Privacy for Robustness and Privacy in Federated Learningcited by 72
  8. 2024When LLMs Meet Cybersecurity: A Systematic Literature Reviewcited by 70
  9. 2024SliM-LLM: Salience-Driven Mixed-Precision Quantization for Large Language Modelscited by 61
  10. 2024SplitLoRA: A Split Parameter-Efficient Fine-Tuning Framework for Large Language Modelscited by 60
  11. 2024Understanding LLMs: A Comprehensive Overview from Training to Inferencecited by 58
  12. 2024Instruction Backdoor Attacks Against Customized LLMscited by 50
  13. 2022Privately Fine-Tuning Large Language Models with Differential Privacycited by 39
  14. 2024LLM-PBE: Assessing Data Privacy in Large Language Modelscited by 38
  15. 2024Fine-tuning and Utilization Methods of Domain-specific LLMscited by 35
  16. 2024Human-Imperceptible Retrieval Poisoning Attacks in LLM-Powered Applicationscited by 32
  17. 2024Recent Advances in Generative AI and Large Language Models: Current Status, Challenges, and Perspectivescited by 30
  18. 2024Text Embedding Inversion Security for Multilingual Language Modelscited by 26
  19. 2024FeDeRA:Efficient Fine-tuning of Language Models in Federated Learning Leveraging Weight Decompositioncited by 26
  20. 2024Federated LoRA with Sparse Communicationcited by 26
  21. 2024Transferable Embedding Inversion Attack: Uncovering Privacy Risks in Text Embeddings without Model Queriescited by 25
  22. 2024Towards Resilient and Efficient LLMs: A Comparative Study of Efficiency, Performance, and Adversarial Robustnesscited by 22
  23. 2024IncogniText: Privacy-enhancing Conditional Text Anonymization via LLM-based Private Attribute Randomizationcited by 21
  24. 2023LLMs Can Understand Encrypted Prompt: Towards Privacy-Computing Friendly Transformerscited by 20
  25. 2024Noisy Neighbors: Efficient membership inference attacks against LLMscited by 20
  26. 2024I-LLM: Efficient Integer-Only Inference for Fully-Quantized Low-Bit Large Language Modelscited by 19
  27. 2024LLMs and the Future of Chip Design: Unveiling Security Risks and Building Trustcited by 18
  28. 2021A novel time-frequency Transformer based on self-attention mechanism and its application in fault diagnosis of rolling bearingscited by 12
  29. 2024Why Does Differential Privacy with Large Epsilon Defend Against Practical Membership Inference Attacks?cited by 12
  30. 2024Enabling On-Device LLMs Personalization with Smartphone Sensingcited by 6
  31. 2024MaPPing Your Model: Assessing the Impact of Adversarial Attacks on LLM-based Programming Assistantscited by 5
  32. 2024MINI-LLM: Memory-Efficient Structured Pruning for Large Language Modelscited by 5
  33. 2024Adversarial Evasion Attack Efficiency against Large Language Modelscited by 4
  34. 2024Efficient LLM Context Distillationcited by 4
  35. 2024FEDSTR: Money-In AI-Out | A Decentralized Marketplace for Federated Learning and LLM Training on the NOSTR Protocolcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Thermo-FL: Thermal-Aware Robust Federated Fine-Tuning of Large Language Models for Edge AIcited by 0