Ownership verification of DNN architectures via hardware cache side channels

Ownership verification of DNN architectures via hardware cache side channels

Deep Neural Networks (DNN) are gaining higher commercial values in computer vision applications, e.g., image classification, video analytics, etc. This calls for urgent demands of the intellectual property (IP) protection of DNN models. In this paper, we present a novel watermarking scheme to achiev...

Saved in:

書目詳細資料
Main Authors:	Lou, Xiaoxuan, Guo, Shangwei, Li, Jiwei, Zhang, Tianwei
其他作者:	School of Computer Science and Engineering
格式:	Article
語言:	English
出版:	2022
主題:	Engineering::Computer science and engineering Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence Deep Neural Network Watermarking Cache Side Channel
在線閱讀:	https://hdl.handle.net/10356/159773
標簽:	添加標簽沒有標簽, 成為第一個標記此記錄!
機構:	Nanyang Technological University
語言:	English

相似書籍

A formal methodology for verifying side-channel vulnerabilities in cache architectures
由: Jiang, Ke, et al.
出版: (2023)

Cache refinement type for side-channel detection of cryptographic software
由: Jiang, Ke, et al.
出版: (2023)

On use of deep learning for side channel evaluation of black box hardware AES engine
由: Won, Yoo-Seung, et al.
出版: (2021)

NASPY: automated extraction of automated machine learning models
由: Lou, Xiaoxuan, et al.
出版: (2023)

DNN model theft through trojan side-channel on edge FPGA accelerator
由: Chandrasekar, Srivatsan, et al.
出版: (2024)

Deep learning watermarking techniques
由: Lim, Jerick Kai Zheng
出版: (2025)

A deep learning framework supporting model ownership protection and traitor tracing
由: XU, Guowen, et al.
出版: (2020)

A survey of microarchitectural side-channel vulnerabilities, attacks, and defenses in cryptography
由: Lou, Xiaoxuan, et al.
出版: (2022)

Parameterized DNN design for identifying the resource limitations of edge deep learning hardware
由: Aung, Shin Thant
出版: (2024)

A systematic side-channel evaluation of black box AES in secure MCU : architecture recovery and retrieval of PUF based secret key
由: Won, Yoo-Seung, et al.
出版: (2021)

Conventional and deep-learning-based side-channel analysis on embedded devices
由: Gao, Diyan
出版: (2025)

Mercury: an automated remote side-channel attack to Nvidia deep learning accelerator
由: Yan, Xiaobei, et al.
出版: (2023)

Breaking redundancy-based countermeasures with random faults and power side channel
由: Saha, Sayandeep, et al.
出版: (2019)

Designing efficient DNNs via hardware-aware neural architecture search and beyond
由: Luo, Xiangzhong, et al.
出版: (2022)

An optical watermarking scheme with two-layer framework based on computational ghost imaging
由: Liansheng, Sui, et al.
出版: (2020)

A buyer-traceable DNN model IP protection method against piracy and misappropriation
由: Wang, Si, et al.
出版: (2022)

Fast media caching for geo-distributed data centers
由: Zhang, Wei, et al.
出版: (2020)

Intelligent Cache Farming Architecture for network management
由: Supawadee Hiranpongsin
出版: (2011)

Side channel attack on stream ciphers: a three-step approach to state/key recovery
由: Kumar, Satyam, et al.
出版: (2023)

The curse of class imbalance and conflicting metrics with machine learning for side-channel evaluations
由: Picek, Stjepan, et al.
出版: (2022)

HACScale : hardware-aware compound scaling for resource-efficient DNNs
由: Kong, Hao, et al.
出版: (2022)

Joint sponsored and edge caching content service market : a game-theoretic approach
由: Xiong, Zehui, et al.
出版: (2020)

Hysia : serving DNN-based video-to-retail applications in cloud
由: Zhang, Huaizheng, et al.
出版: (2021)

Security challenges in automotive hardware/software architecture design
由: Sagstetter, Florian, et al.
出版: (2013)

Predictability and performance aware replacement policy PVISAM for unified shared caches in real-time multicores
由: Mohammad Shihabul Haque, et al.
出版: (2020)

LKAW: a robust watermarking method based on large kernel convolution and adaptive weight assignment
由: Zhang, Xiaorui, et al.
出版: (2023)

Study of convergence using residual links in various or combinations of different DNN
由: Fang, Wen Jie
出版: (2020)

Towards optimal defences on adversarial examples for DNN-driven digital twinning
由: Lee, Michael Yew Chuan
出版: (2023)

Hardware-aware neural architecture search and compression towards embedded intelligence
由: Luo, Xiangzhong
出版: (2023)

Hardware architecture for real-time crossbar switching using genetic algorithm approach
由: Ding, Sheng Hua
出版: (2008)

Latency-constrained DNN architecture learning for edge systems using zerorized batch normalization
由: Huai, Shuo, et al.
出版: (2023)

On side channel vulnerabilities of bit permutations in cryptographic algorithms
由: Breier, Jakub, et al.
出版: (2020)

Caching efficiency enhancement at wireless edges with concerns on user’s quality of experience
由: Li, Feng, et al.
出版: (2019)

Practical side-channel based model extraction attack on tree-based machine learning algorithm
由: Jap, Dirmanto, et al.
出版: (2021)

On (in)security of edge-based machine learning against electromagnetic side-channels
由: Bhasin, Shivam, et al.
出版: (2023)

Design novel DNN models with neural architecture search
由: Lum, Ada Yueh Khay
出版: (2024)

Accelerating gustavson-based SpMM on embedded FPGAs with element-wise parallelism and access pattern-aware caches
由: Li, Shiqing, et al.
出版: (2023)

Toward rendering-latency reduction for composable web services via priority-based object caching
由: Hu, Han, et al.
出版: (2020)

DNN-FES & Fole : objective loss estimator for integrating deep neural-network into fuzzy systems
由: Dandapath, Soham
出版: (2021)

The performance evaluation and analysis of caching in data grid system
由: Teerayut Hiruntaraporn
出版: (2007)