Cited By
View all- Zhang RLi HQian XJiang WChen H(2025)On large language models safety, security, and privacy: A surveyJournal of Electronic Science and Technology10.1016/j.jnlest.2025.100301(100301)Online publication date: Jan-2025
TransLinkGuard: Safeguarding Transformer Models Against Model Stealing in Edge Deployment
Authors: 
Qinfeng Li, Zhiqiang Shen, Zhenghan Qin, Yangfan Xie, Xuhong Zhang, Tianyu Du, Sheng Cheng, Xun Wang, Jianwei YinAuthors Info & Claims
Pages 3479 - 3488
Abstract
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 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, which can freshly authorize each request based on its input. Extensive experiments show that TransLinkGuard achieves the same security as the black-box guarantees with negligible overhead.
References
[1]
Yossi Adi, Carsten Baum, Moustapha Cisse, Benny Pinkas, and Joseph Keshet. 2018. Turning your weakness into a strength: Watermarking deep neural networks by backdooring. In 27th USENIX Security Symposium (USENIX Security 18). 1615--1631.
[2]
Tiago Alves. 2004. Trustzone: Integrated hardware and software security. Information Quarterly, Vol. 3 (2004), 18--24.
[3]
Anthropic. 2023. Claude. https://www.anthropic.com/. Accessed: [2024.02.24].
[4]
Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, et al. 2020. Language models are few-shot learners. Advances in neural information processing systems, Vol. 33 (2020), 1877--1901.
[5]
Ying Cao, Ruigang Liang, Kai Chen, and Peiwei Hu. 2022. Boosting Neural Networks to Decompile Optimized Binaries. In Proceedings of the 38th Annual Computer Security Applications Conference. 508--518.
[6]
Abhishek Chakraborty, Ankit Mondai, and Ankur Srivastava. 2020. Hardware-assisted intellectual property protection of deep learning models. In 2020 57th ACM/IEEE Design Automation Conference (DAC). IEEE, 1--6.
[7]
Jialuo Chen, Jingyi Wang, Tinglan Peng, Youcheng Sun, Peng Cheng, Shouling Ji, Xingjun Ma, Bo Li, and Dawn Song. 2022. Copy, right? a testing framework for copyright protection of deep learning models. In 2022 IEEE symposium on security and privacy (SP). IEEE, 824--841.
[8]
Yufei Chen, Chao Shen, Cong Wang, and Yang Zhang. 2022. Teacher model fingerprinting attacks against transfer learning. In 31st USENIX Security Symposium (USENIX Security 22). 3593--3610.
[9]
Karl Cobbe, Vineet Kosaraju, Mohammad Bavarian, Mark Chen, Heewoo Jun, Lukasz Kaiser, Matthias Plappert, Jerry Tworek, Jacob Hilton, Reiichiro Nakano, et al. 2021. Training verifiers to solve math word problems. arXiv preprint arXiv:2110.14168 (2021).
[10]
Zhengxiao Du, Yujie Qian, Xiao Liu, Ming Ding, Jiezhong Qiu, Zhilin Yang, and Jie Tang. 2021. Glm: General language model pretraining with autoregressive blank infilling. arXiv preprint arXiv:2103.10360 (2021).
[11]
Tarek Elgamal and Klara Nahrstedt. 2020. Serdab: An IoT framework for partitioning neural networks computation across multiple enclaves. In 2020 20th IEEE/ACM International Symposium on Cluster, Cloud and Internet Computing (CCGRID). IEEE, 519--528.
[12]
Lixin Fan, Kam Woh Ng, and Chee Seng Chan. 2019. Rethinking deep neural network ownership verification: Embedding passports to defeat ambiguity attacks. Advances in neural information processing systems, Vol. 32 (2019).
[13]
Ran Gilad-Bachrach, Nathan Dowlin, Kim Laine, Kristin Lauter, Michael Naehrig, and John Wernsing. 2016. Cryptonets: Applying neural networks to encrypted data with high throughput and accuracy. In International conference on machine learning. PMLR, 201--210.
[14]
Google. 2023. Gemini. https://blog.google/technology/ai/google-gemini-ai/. Accessed: [2024.03.12].
[15]
Lucjan Hanzlik, Yang Zhang, Kathrin Grosse, Ahmed Salem, Maximilian Augustin, Michael Backes, and Mario Fritz. 2021. Mlcapsule: Guarded offline deployment of machine learning as a service. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 3300--3309.
[16]
Hanieh Hashemi, Yongqin Wang, and Murali Annavaram. 2021. DarKnight: An accelerated framework for privacy and integrity preserving deep learning using trusted hardware. In MICRO-54: 54th Annual IEEE/ACM International Symposium on Microarchitecture. 212--224.
[17]
Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2016. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition. 770--778.
[18]
Weizhe Hua, Muhammad Umar, Zhiru Zhang, and G Edward Suh. 2022. Guardnn: secure accelerator architecture for privacy-preserving deep learning. In Proceedings of the 59th ACM/IEEE Design Automation Conference. 349--354.
[19]
Weizhe Hua, Zhiru Zhang, and G Edward Suh. 2018. Reverse engineering convolutional neural networks through side-channel information leaks. In Proceedings of the 55th Annual Design Automation Conference. 1--6.
[20]
Wei Huang, Yinggui Wang, Anda Cheng, Aihui Zhou, Chaofan Yu, and Lei Wang. 2024. A Fast, Performant, Secure Distributed Training Framework For LLM. In ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). 4800--4804. https://doi.org/10.1109/ICASSP48485.2024.10446717
[21]
Matthew Jagielski, Nicholas Carlini, David Berthelot, Alex Kurakin, and Nicolas Papernot. 2020. High accuracy and high fidelity extraction of neural networks. In 29th USENIX security symposium (USENIX Security 20). 1345--1362.
[22]
Hengrui Jia, Christopher A Choquette-Choo, Varun Chandrasekaran, and Nicolas Papernot. 2021. Entangled watermarks as a defense against model extraction. In 30th USENIX Security Symposium (USENIX Security 21). 1937--1954.
[23]
Qiao Jin, Bhuwan Dhingra, Zhengping Liu, William W Cohen, and Xinghua Lu. 2019.qa: A dataset for biomedical research question answering. arXiv preprint arXiv:1909.06146 (2019).
[24]
Chiraag Juvekar, Vinod Vaikuntanathan, and Anantha Chandrakasan. 2018. {GAZELLE}: A low latency framework for secure neural network inference. In 27th USENIX security symposium (USENIX security 18). 1651--1669.
[25]
David Kaplan, Jeremy Powell, and Tom Woller. 2016. AMD memory encryption. White paper, Vol. 13 (2016).
[26]
Kyungtae Kim, Chung Hwan Kim, Junghwan "John" Rhee, Xiao Yu, Haifeng Chen, Dave Tian, and Byoungyoung Lee. 2020. Vessels: Efficient and scalable deep learning prediction on trusted processors. In Proceedings of the 11th ACM Symposium on Cloud Computing. 462--476.
[27]
Taegyeong Lee, Zhiqi Lin, Saumay Pushp, Caihua Li, Yunxin Liu, Youngki Lee, Fengyuan Xu, Chenren Xu, Lintao Zhang, and Junehwa Song. 2019. Occlumency: Privacy-preserving remote deep-learning inference using SGX. In The 25th Annual International Conference on Mobile Computing and Networking. 1--17.
[28]
Mike Lewis, Yinhan Liu, Naman Goyal, Marjan Ghazvininejad, Abdelrahman Mohamed, Omer Levy, Ves Stoyanov, and Luke Zettlemoyer. 2019. Bart: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. arXiv preprint arXiv:1910.13461 (2019).
[29]
Yuepeng Li, Deze Zeng, Lin Gu, Quan Chen, Song Guo, Albert Zomaya, and Minyi Guo. 2021. Lasagna: Accelerating secure deep learning inference in sgx-enabled edge cloud. In Proceedings of the ACM Symposium on Cloud Computing. 533--545.
[30]
Zheng Lin, Guanqiao Qu, Qiyuan Chen, Xianhao Chen, Zhe Chen, and Kaibin Huang. 2023. Pushing large language models to the 6g edge: Vision, challenges, and opportunities. arXiv preprint arXiv:2309.16739 (2023).
[31]
Gang Liu, Ruotong Xiang, Jing Liu, Rong Pan, and Ziyi Zhang. 2022. An invisible and robust watermarking scheme using convolutional neural networks. Expert Systems with Applications, Vol. 210 (2022), 118529.
[32]
Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692 (2019).
[33]
Chun Shien Lu. 2005. Steganography and digital watermarking techniques for protection of intellectual property. Multimedia Security, Idea Group Publishing, Singapore (2005), 75--157.
[34]
Frank McKeen, Ilya Alexandrovich, Alex Berenzon, Carlos V Rozas, Hisham Shafi, Vedvyas Shanbhogue, and Uday R Savagaonkar. 2013. Innovative instructions and software model for isolated execution. Hasp@ isca, Vol. 10, 1 (2013).
[35]
Fan Mo, Hamed Haddadi, Kleomenis Katevas, Eduard Marin, Diego Perino, and Nicolas Kourtellis. 2021. PPFL: privacy-preserving federated learning with trusted execution environments. In Proceedings of the 19th annual international conference on mobile systems, applications, and services. 94--108.
[36]
Fan Mo, Ali Shahin Shamsabadi, Kleomenis Katevas, Soteris Demetriou, Ilias Leontiadis, Andrea Cavallaro, and Hamed Haddadi. 2020. Darknetz: towards model privacy at the edge using trusted execution environments. In Proceedings of the 18th International Conference on Mobile Systems, Applications, and Services. 161--174.
[37]
Tsunato Nakai, Daisuke Suzuki, and Takeshi Fujino. 2021. Towards trained model confidentiality and integrity using trusted execution environments. In Applied Cryptography and Network Security Workshops: ACNS 2021 Satellite Workshops, AIBlock, AIHWS, AIoTS, CIMSS, Cloud S&P, SCI, SecMT, and SiMLA, Kamakura, Japan, June 21-24, 2021, Proceedings. Springer, 151--168.
[38]
NVIDIA. 2024. NVIDIA H100 Tensor Core GPU. https://www.nvidia.com/en-us/data-center/h100/. Accessed: [2024.3.18].
[39]
OpenAI. 2023. GPT-4. https://openai.com/gpt-4. Accessed: [2023.11.17].
[40]
OpenAI. 2023. Text-generation. https://platform.openai.com/docs/guides/text-generation. Accessed: [2023.11.17].
[41]
Tribhuvanesh Orekondy, Bernt Schiele, and Mario Fritz. 2019. Knockoff nets: Stealing functionality of black-box models. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 4954--4963.
[42]
Nicolas Papernot, Patrick McDaniel, Arunesh Sinha, and Michael Wellman. 2016. Towards the science of security and privacy in machine learning. arXiv preprint arXiv:1611.03814 (2016).
[43]
Alec Radford, Jeffrey Wu, Rewon Child, David Luan, Dario Amodei, Ilya Sutskever, et al. 2019. Language models are unsupervised multitask learners. OpenAI blog, Vol. 1, 8 (2019), 9.
[44]
Pranav Rajpurkar, Jian Zhang, Konstantin Lopyrev, and Percy Liang. 2016. Squad: 100,000 questions for machine comprehension of text. arXiv preprint arXiv:1606.05250 (2016).
[45]
Adnan Siraj Rakin, Md Hafizul Islam Chowdhuryy, Fan Yao, and Deliang Fan. 2022. Deepsteal: Advanced model extractions leveraging efficient weight stealing in memories. In 2022 IEEE symposium on security and privacy (SP). IEEE, 1157--1174.
[46]
M Sadegh Riazi, Christian Weinert, Oleksandr Tkachenko, Ebrahim M Songhori, Thomas Schneider, and Farinaz Koushanfar. 2018. Chameleon: A hybrid secure computation framework for machine learning applications. In Proceedings of the 2018 on Asia conference on computer and communications security. 707--721.
[47]
Frank Rubin. 1996. One-time pad cryptography. Cryptologia, Vol. 20, 4 (1996), 359--364.
[48]
Claude E Shannon. 1949. Communication theory of secrecy systems. The Bell system technical journal, Vol. 28, 4 (1949), 656--715.
[49]
Tianxiang Shen, Ji Qi, Jianyu Jiang, Xian Wang, Siyuan Wen, Xusheng Chen, Shixiong Zhao, Sen Wang, Li Chen, Xiapu Luo, et al. 2022. {SOTER}: Guarding Black-box Inference for General Neural Networks at the Edge. In 2022 USENIX Annual Technical Conference (USENIX ATC 22). 723--738.
[50]
Youren Shen, Hongliang Tian, Yu Chen, Kang Chen, Runji Wang, Yi Xu, Yubin Xia, and Shoumeng Yan. 2020. Occlum: Secure and efficient multitasking inside a single enclave of intel sgx. In Proceedings of the Twenty-Fifth International Conference on Architectural Support for Programming Languages and Operating Systems. 955--970.
[51]
Zhichuang Sun, Ruimin Sun, Changming Liu, Amrita Roy Chowdhury, Long Lu, and Somesh Jha. 2023. Shadownet: A secure and efficient on-device model inference system for convolutional neural networks. In 2023 IEEE Symposium on Security and Privacy (SP). IEEE, 1596--1612.
[52]
Mingxing Tan and Quoc Le. 2019. Efficientnet: Rethinking model scaling for convolutional neural networks. In International conference on machine learning. PMLR, 6105--6114.
[53]
Timothy Prickett Morgan. 2022. Counting The Cost Of Training Large Language Models. https://www.nextplatform.com/2022/12/01/counting-the-cost-of-training-large-language-models/. Accessed: [2024.02.24].
[54]
Hugo Touvron, Louis Martin, Kevin Stone, Peter Albert, Amjad Almahairi, Yasmine Babaei, Nikolay Bashlykov, Soumya Batra, Prajjwal Bhargava, Shruti Bhosale, et al. 2023. Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023).
[55]
Florian Tramer and Dan Boneh. 2018. Slalom: Fast, verifiable and private execution of neural networks in trusted hardware. arXiv preprint arXiv:1806.03287 (2018).
[56]
Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems, Vol. 30 (2017).
[57]
Stavros Volos, Kapil Vaswani, and Rodrigo Bruno. 2018. Graviton: Trusted execution environments on {GPUs}. In 13th USENIX Symposium on Operating Systems Design and Implementation (OSDI 18). 681--696.
[58]
Alex Wang, Amanpreet Singh, Julian Michael, Felix Hill, Omer Levy, and Samuel R Bowman. 2018. GLUE: A multi-task benchmark and analysis platform for natural language understanding. arXiv preprint arXiv:1804.07461 (2018).
[59]
Ruoyu Wu, Taegyu Kim, Dave Jing Tian, Antonio Bianchi, and Dongyan Xu. 2022. {DnD}: A {Cross-Architecture} deep neural network decompiler. In 31st USENIX Security Symposium (USENIX Security 22). 2135--2152.
[60]
Mengjia Yan, Christopher W Fletcher, and Josep Torrellas. 2020. Cache telepathy: Leveraging shared resource attacks to learn {DNN} architectures. In 29th USENIX Security Symposium (USENIX Security 20). 2003--2020.
[61]
Baosong Yang, Longyue Wang, Derek F Wong, Lidia S Chao, and Zhaopeng Tu. 2019. Assessing the ability of self-attention networks to learn word order. arXiv preprint arXiv:1906.00592 (2019).
[62]
Tao Yu, Rui Zhang, Kai Yang, Michihiro Yasunaga, Dongxu Wang, Zifan Li, James Ma, Irene Li, Qingning Yao, Shanelle Roman, et al. 2018. Spider: A large-scale human-labeled dataset for complex and cross-domain semantic parsing and text-to-sql task. arXiv preprint arXiv:1809.08887 (2018).
[63]
Mu Yuan, Lan Zhang, and Xiang-Yang Li. 2023. Secure Transformer Inference. arXiv preprint arXiv:2312.00025 (2023).
[64]
Ziqi Zhang, Chen Gong, Yifeng Cai, Yuanyuan Yuan, Bingyan Liu, Ding Li, Yao Guo, and Xiangqun Chen. 2023. No Privacy Left Outside: On the (In-) Security of TEE-Shielded DNN Partition for On-Device ML. In 2024 IEEE Symposium on Security and Privacy (SP). IEEE Computer Society, 52--52.
[65]
Tong Zhou, Yukui Luo, Shaolei Ren, and Xiaolin Xu. 2023. NNSplitter: an active defense solution for DNN model via automated weight obfuscation. In International Conference on Machine Learning. PMLR, 42614--42624.
Index Terms
- TransLinkGuard: Safeguarding Transformer Models Against Model Stealing in Edge Deployment
Recommendations
Delegation in role-based access control
User delegation is a mechanism for assigning access rights available to one user to another user. A delegation can either be a grant or transfer operation. Existing work on delegation in the context of role-based access control models has extensively ...
Self-Adaptive Authorization Framework for Policy Based RBAC/ABAC Models
DASC '11: Proceedings of the 2011 IEEE Ninth International Conference on Dependable, Autonomic and Secure ComputingAuthorization systems are an integral part of any network where resources need to be protected. They act as the gateway for providing (or denying) subjects (users) access to resources. As networks expand and organisations start to federate access to ...
An Effective Usage and Access Control Scheme for Preventing Permission Leak in a Trusted Execution Environment
ICCNS '16: Proceedings of the 6th International Conference on Communication and Network SecurityIn the universal Android system, each application runs in its own sandbox, and the permission mechanism is used to enforce access control to the system APIs and applications. However, permission leak could happen when an application without certain ...
Comments
Please enable JavaScript to view thecomments powered by Disqus.Information & Contributors
Information
Published In
October 2024
11719 pages
ISBN:9798400706868
DOI:10.1145/3664647
- General Chairs:
- Jianfei Cai,
- Mohan Kankanhalli,
- Balakrishnan Prabhakaran,
- Susanne Boll,
- Program Chairs:
- Ramanathan Subramanian,
- Liang Zheng,
- Vivek K. Singh,
- Pablo Cesar,
- Lexing Xie,
- Dong Xu
Copyright © 2024 ACM.
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].
Sponsors
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 28 October 2024
Check for updates
Author Tags
Qualifiers
- Research-article
Conference
MM '24
Sponsor:
MM '24: The 32nd ACM International Conference on Multimedia
October 28 - November 1, 2024
Melbourne VIC, Australia
Acceptance Rates
MM '24 Paper Acceptance Rate 1,150 of 4,385 submissions, 26%;
Overall Acceptance Rate 2,145 of 8,556 submissions, 25%
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- View Citations1Total Citations
- 200Total Downloads
- Downloads (Last 12 months)200
- Downloads (Last 6 weeks)86
Reflects downloads up to 01 Mar 2025
Other Metrics
Citations
Cited By
View all- Zhang RLi HQian XJiang WChen H(2025)On large language models safety, security, and privacy: A surveyJournal of Electronic Science and Technology10.1016/j.jnlest.2025.100301(100301)Online publication date: Jan-2025
View Options
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in