mlsanityData to 14 Oct 2026

TransLinkGuard: Safeguarding Transformer Models Against Model Stealing in Edge Deployment

arXiv 2404.11121 ↗First posted 17 Apr 2024cs.CR cs.AIcited by 11

Not on the map. Why?

Abstract (arXiv)

Proprietary large language models (LLMs) have been widely applied in various scenarios. Additionally, deploying LLMs on edge devices is trending for efficiency and privacy reasons. However, edge deployment of proprietary LLMs introduces new security challenges: edge-deployed models are exposed as white-box accessible to users, enabling adversaries to conduct effective model stealing (MS) attacks. Unfortunately, existing defense mechanisms fail to provide effective protection. Specifically, we identify four critical protection properties that existing methods fail to simultaneously satisfy: (1) maintaining protection after a model is physically copied; (2) authorizing model access at request level; (3) safeguarding runtime reverse engineering; (4) achieving high security with negligible runtime overhead. To address the above issues, we propose TransLinkGuard, a plug-and-play model protection approach against model stealing on edge devices. The core part of TransLinkGuard is a lightweight authorization module residing in a secure environment, e.g., TEE. The authorization module can freshly authorize each request based on its input. Extensive experiments show that TransLinkGuard achieves the same security protection as the black-box security guarantees with negligible overhead.

Key facts. Cited by 11 papers in the map (data through 14 Oct 2026). Builds on 30 of its 63 references that are in the map. First posted on arXiv 17 Apr 2024.

Builds on

30 of 63 references.

References · 30

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2020Language Models are Few-Shot Learnerscited by 32,419
  4. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  5. 2021Training Verifiers to Solve Math Word Problemscited by 10,109
  6. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,442
  7. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,893
  8. 2016SQuAD: 100,000+ Questions for Machine Comprehension of Textcited by 4,148
  9. 2019PubMedQA: A Dataset for Biomedical Research Question Answeringcited by 1,288
  10. 2018Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Taskcited by 1,139
  11. 2021GLM: General Language Model Pretraining with Autoregressive Blank Infillingcited by 1,031
  12. 2018Turning Your Weakness Into a Strength: Watermarking Deep Neural Networks by Backdooringcited by 357
18 more
  1. 2018Knockoff Nets: Stealing Functionality of Black-Box Modelscited by 292
  2. 2019High Accuracy and High Fidelity Extraction of Neural Networkscited by 214
  3. 2018Gazelle: A Low Latency Framework for Secure Neural Network Inferencecited by 193
  4. 2018Slalom: Fast, Verifiable and Private Execution of Neural Networks in Trusted Hardwarecited by 102
  5. 2021PPFL: Privacy-preserving Federated Learning with Trusted Execution Environmentscited by 93
  6. 2016Towards the Science of Security and Privacy in Machine Learningcited by 89
  7. 2018Chameleon: A Hybrid Secure Computation Framework for Machine Learning Applicationscited by 67
  8. 2020DarkneTZ: Towards Model Privacy at the Edge using Trusted Execution Environmentscited by 58
  9. 2023No Privacy Left Outside: On the (In-)Security of TEE-Shielded DNN Partition for On-Device MLcited by 21
  10. 2021Teacher Model Fingerprinting Attacks Against Transfer Learningcited by 16
  11. 2023NNSplitter: An Active Defense Solution for DNN Model via Automated Weight Obfuscationcited by 16
  12. 2022DarKnight: An Accelerated Framework for Privacy and Integrity Preserving Deep Learning Using Trusted Hardwarecited by 14
  13. 2020Occlum: Secure and Efficient Multitasking Inside a Single Enclave of Intel SGXcited by 11
  14. 2020Serdab: An IoT Framework for Partitioning Neural Networks Computation across Multiple Enclavescited by 11
  15. 2023Boosting Neural Networks to Decompile Optimized Binariescited by 11
  16. 2019Assessing the Ability of Self-Attention Networks to Learn Word Ordercited by 9
  17. 2020GuardNN: Secure Accelerator Architecture for Privacy-Preserving Deep Learningcited by 9
  18. 2024A Fast, Performant, Secure Distributed Training Framework For Large Language Modelcited by 8

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 5; 2025: 4; 2026: 2.

11 papers.

  1. 2025A Survey on Model Extraction Attacks and Defenses for Large Language Modelscited by 19
  2. 2024SLIP: Securing LLMs IP Using Weights Decompositioncited by 14
  3. 2024A First Look At Efficient And Secure On-Device LLM Inference Against KV Leakagecited by 8
  4. 2024CoreGuard: Safeguarding Foundational Capabilities of LLMs Against Model Stealing in Edge Deploymentcited by 5
  5. 2024TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Modelscited by 3
  6. 2024Taylor Unswift: Secured Weight Release for Large Language Models via Taylor Expansioncited by 2
  7. 2025Do Not Merge My Model! Safeguarding Open-Source LLMs Against Unauthorized Model Mergingcited by 2
  8. 2025PC-MoE: Memory-Efficient and Privacy-Preserving Collaborative Training for Mixture-of-Experts LLMscited by 1
  9. 2026FlexServe: A Fast and Secure LLM Serving System for Mobile Devices with Flexible Resource Isolationcited by 1
  10. 2025DistilLock: Safeguarding LLMs from Unauthorized Knowledge Distillation on the Edgecited by 0
  11. 2026FlexServe: A Fast and Secure LLM Serving System for Mobile Devices with Flexible Resource Isolationcited by 0