Streamlining DNN obfuscation to defend against model stealing attacks

Streamlining DNN obfuscation to defend against model stealing attacks

Side-channel-based Deep Neural Network (DNN) model stealing has become a major concern with the advent of learning-based attacks. In respond to this threat, defence mechanisms have been presented to obfuscate the DNN execution, making it difficult to infer the correlation between side-channel inform...

Disgrifiad llawn

Manylion Llyfryddiaeth
Prif Awduron:	Sun, Yidan, Lam, Siew-Kei, Jiang, Guiyuan, He, Peilan
Awduron Eraill:	College of Computing and Data Science
Fformat:	Conference Paper
Iaith:	English
Cyhoeddwyd:	2024
Pynciau:	Computer and Information Science Deep nerual network Defense side-channel attack Model extraction
Mynediad Ar-lein:	https://hdl.handle.net/10356/178547 https://ieee-cas.org/event/conference/2024-ieee-international-symposium-circuits-and-systems

Eitemau Tebyg

Layer sequence extraction of optimized DNNs using side-channel information leaks
gan: Sun, Yidan, et al.
Cyhoeddwyd: (2024)

Strategic safeguarding: A game theoretic approach for analyzing attacker-defender behavior in DNN backdoors
gan: Kassem Kallas, et al.
Cyhoeddwyd: (2024-10-01)

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

Using side-channel and quantization vulnerability to recover DNN weights
gan: Jinghai LI, et al.
Cyhoeddwyd: (2021-08-01)

Universal patching method for side-channel vulnerabilities based on atomic obfuscation
gan: Deqing ZOU, et al.
Cyhoeddwyd: (2022-04-01)

A Review of Attacker–Defender Games and Cyber Security
gan: Kjell Hausken, et al.
Cyhoeddwyd: (2024-08-01)

Defending Against Backdoor Attacks by Quarantine Training
gan: Chengxu Yu, et al.
Cyhoeddwyd: (2024-01-01)

Template attack of Crypto chip based on clustering
gan: Zhen WU, et al.
Cyhoeddwyd: (2018-08-01)

Template attack of Crypto chip based on clustering
gan: Zhen WU, et al.
Cyhoeddwyd: (2018-08-01)

VLSI implementation of AES algorithm against differential power attack and differential fault attack
gan: HAN Jun, et al.
Cyhoeddwyd: (2010-01-01)

VLSI implementation of AES algorithm against differential power attack and differential fault attack
gan: HAN Jun, et al.
Cyhoeddwyd: (2010-01-01)

A Low-Overhead and High-Security Scan Design Based on Scan Obfuscation
gan: Weizheng Wang, et al.
Cyhoeddwyd: (2024-01-01)

SAPA-based approach for defending DoS attacks in cloud computing
gan: Meng YUE, et al.
Cyhoeddwyd: (2017-04-01)

SAPA-based approach for defending DoS attacks in cloud computing
gan: Meng YUE, et al.
Cyhoeddwyd: (2017-04-01)

An Attacker–Defender Game Model with Constrained Strategies
gan: Jiaqi Ren, et al.
Cyhoeddwyd: (2024-07-01)

A survey of acoustic eavesdropping attacks: Principle, methods, and progress
gan: Yiwei Chen, et al.
Cyhoeddwyd: (2024-12-01)

Power model in power analysis attack
gan: Peng LUO, et al.
Cyhoeddwyd: (2012-09-01)

Research and simulation of timing attacks on ECC
gan: Hui-hui JIA, et al.
Cyhoeddwyd: (2016-04-01)

Power model in power analysis attack
gan: Peng LUO, et al.
Cyhoeddwyd: (2012-09-01)

Defending Deep Neural Networks Against Backdoor Attack by Using De-Trigger Autoencoder
gan: Hyun Kwon
Cyhoeddwyd: (2025-01-01)

FRNet: A Feature-Rich CNN Architecture to Defend Against Adversarial Attacks
gan: Neha A S, et al.
Cyhoeddwyd: (2024-01-01)

Blind mask template attacks on masked cryptographic algorithm
gan: Yi WANG, et al.
Cyhoeddwyd: (2019-01-01)

Blind mask template attacks on masked cryptographic algorithm
gan: Yi WANG, et al.
Cyhoeddwyd: (2019-01-01)

SAluMC: Thwarting Side-Channel Attacks via Random Number Injection in RISC-V
gan: Shibo Dang, et al.
Cyhoeddwyd: (2025-02-01)

Fault-injection attack on countermeasure algorithms of RSA-CRT cryptosystem
gan: Fanyu KONG, et al.
Cyhoeddwyd: (2019-02-01)

Improvement of equivalent power consumption coding secure against power analysis attacks
gan: WU Zhen, et al.
Cyhoeddwyd: (2010-01-01)

Post-Quantum Authenticated Encryption against Chosen-Ciphertext Side-Channel Attacks
gan: Melissa Azouaoui, et al.
Cyhoeddwyd: (2022-08-01)

Improvement of equivalent power consumption coding secure against power analysis attacks
gan: WU Zhen, et al.
Cyhoeddwyd: (2010-01-01)

Post-Quantum Authenticated Encryption against Chosen-Ciphertext Side-Channel Attacks
gan: Melissa Azouaoui, et al.
Cyhoeddwyd: (2022-08-01)

A divide-and-conquer reconstruction method for defending against adversarial example attacks
gan: Xiyao Liu, et al.
Cyhoeddwyd: (2024-10-01)

Feature selection methods for non-profiled side-channel attacks on ECC
gan: Bhasin, Shivam, et al.
Cyhoeddwyd: (2019)

A Survey of Security Strategies in Federated Learning: Defending Models, Data, and Privacy
gan: Habib Ullah Manzoor, et al.
Cyhoeddwyd: (2024-10-01)

A Not So Discrete Sampler: Power Analysis Attacks on HAWK signature scheme
gan: Morgane Guerreau, et al.
Cyhoeddwyd: (2024-09-01)

Survey on Byzantine attacks and defenses in federated learning
gan: ZHAO Xiaojie, et al.
Cyhoeddwyd: (2024-12-01)

Defeating low-cost countermeasures against side-channel attacks in lattice-based encryption
gan: Ravi, Prasanna, et al.
Cyhoeddwyd: (2024)

Creating from noise: trace generations using diffusion model for side-channel attack
gan: Yap, Trevor, et al.
Cyhoeddwyd: (2024)

Detection and defending the XSS attack using novel hybrid stacking ensemble learning-based DNN approach
gan: Muralitharan Krishnan, et al.
Cyhoeddwyd: (2024-06-01)

Survey of side channel attack on encrypted network traffic
gan: Ding LI, et al.
Cyhoeddwyd: (2021-08-01)

Exploring integrity of AEADs with faults: definitions and constructions
gan: Saha, Sayandeep, et al.
Cyhoeddwyd: (2023)

Highly secured arithmetic hiding based S-Box on AES-128 implementation
gan: Pammu, Ali Akbar, et al.
Cyhoeddwyd: (2017)