I know what you trained last summer: A survey on stealing machine learning models and defences

D Oliynyk, R Mayer, A Rauber - ACM Computing Surveys, 2023 - dl.acm.org
Machine-Learning-as-a-Service (MLaaS) has become a widespread paradigm, making
even the most complex Machine Learning models available for clients via, eg, a pay-per …

AI/ML algorithms and applications in VLSI design and technology

D Amuru, A Zahra, HV Vudumula, PK Cherupally… - Integration, 2023 - Elsevier
An evident challenge ahead for the integrated circuit (IC) industry is the investigation and
development of methods to reduce the design complexity ensuing from growing process …

Guarding machine learning hardware against physical side-channel attacks

A Dubey, R Cammarota, V Suresh, A Aysu - ACM Journal on Emerging …, 2022 - dl.acm.org
Machine learning (ML) models can be trade secrets due to their development cost. Hence,
they need protection against malicious forms of reverse engineering (eg, in IP piracy). With a …

Compression-Encrypted Meta-Optics for Storage Efficiency and Security Enhancement

Z Wang, M Niu, W Zhao, Z Wang, S Wan, Y Shi… - ACS …, 2024 - ACS Publications
Information security is of vital importance in daily life, stimulating various cryptographic
strategies to protect data from leaking. Among them, metasurface-based optical encryption is …

Security for Machine Learning-based Software Systems: A Survey of Threats, Practices, and Challenges

H Chen, MA Babar - ACM Computing Surveys, 2024 - dl.acm.org
The rapid development of Machine Learning (ML) has demonstrated superior performance
in many areas, such as computer vision and video and speech recognition. It has now been …

Mitigation against DDoS attacks on an IoT-based production line using machine learning

L Huraj, T Horak, P Strelec, P Tanuska - Applied Sciences, 2021 - mdpi.com
Industry 4.0 collects, exchanges, and analyzes data during the production process to
increase production efficiency. Internet of Things (IoT) devices are among the basic …

Extraction of binarized neural network architecture and secret parameters using side-channel information

V Yli-Mäyry, A Ito, N Homma… - 2021 IEEE International …, 2021 - ieeexplore.ieee.org
In recent years, neural networks have been applied to various applications. To speed up the
evaluation, a method using binarized network weights has been introduced, facilitating …

[图书][B] CAD for hardware security

F Farahmandi, MS Rahman, SR Rajendran… - 2023 - Springer
Emerging hardware security vulnerabilities are menacing since it is almost impossible to
amend the design after fabrication. Recent studies reported vulnerabilities, including side …

Building Trust in Microelectronics: A Comprehensive Review of Current Techniques and Adoption Challenges

K Nyako, S Devkota, F Li, V Borra - Electronics, 2023 - mdpi.com
The field of microelectronics has experienced extensive integration into various aspects of
our everyday lives, evident via its utilization across a wide range of devices such as …

Towards ai-enabled hardware security: Challenges and opportunities

H Sayadi, M Aliasgari, F Aydin, S Potluri… - 2022 IEEE 28th …, 2022 - ieeexplore.ieee.org
Recent developments in Artificial Intelligence (AI) and Machine Learning (ML), driven by a
substantial increase in the size of data in emerging computing systems, have led into …