云南高校图书馆联盟文献共享服务平台- ATTACKS

ATTACKS: 作品数：470被引量：519H指数：9; 导出分析报告; 相关领域：自动化与计算机技术更多>>; 相关作者：张颖李彦辉王新生更多>>; 相关机构：华南理工大学湖南大学中南大学重庆大学更多>>; 相关期刊：更多>>; 相关基金：国家自然科学基金国家重点基础研究发展计划中国博士后科学基金北京市自然科学基金更多>>

Efficient Untargeted White-Box Adversarial Attacks Based on Simple Initialization: 《Chinese Journal of Electronics》2024年第4期979-988,共10页Yunyi ZHOU Haichang GAO Jianping HE Shudong ZHANG Zihui WU; National Natural Science Foundation of China (Grant No. 61972306);Song Shan Laboratory (Grant No. YYJC012022005);Zhejiang Laboratory (Grant No. 2021KD0AB03)。; Adversarial examples(AEs) are an additive amalgamation of clean examples and artificially malicious perturbations. Attackers often leverage random noise and multiple random restarts to initialize perturbation starting...; 关键词：Adversarial examples White-box attacks Image classification

BAD-FM:Backdoor Attacks Against Factorization-Machine Based Neural Network for Tabular Data Prediction: 《Chinese Journal of Electronics》2024年第4期1077-1092,共16页Lingshuo MENG Xueluan GONG Yanjiao CHEN; Backdoor attacks pose great threats to deep neural network models. All existing backdoor attacks are designed for unstructured data(image, voice, and text), but not structured tabular data, which has wide real-world a...; 关键词：Backdoor attacks Tabular data Click-through rate prediction Deep neural network

New Related-Tweakey Boomerang Attacks and Distinguishers on Deoxys-BC: 《Chinese Journal of Electronics》2024年第3期683-693,共11页Jiamei LIU Lin TAN Hong XU; supported by the National Cryptography Development Fund of China (Grant Nos.MMJJ20170103 and MMJJ20180204)。; Deoxys-BC is the primitive tweakable block cipher of the Deoxys family of authenticated encryption schemes.Based on existing related-tweakey boomerang distinguishers,this paper improves the boomerang attacks on 11-rou...; 关键词：Block cipher Tweakable block cipher Boomerang attack Related-tweakey

Robust Regularization Design of Graph Neural Networks Against Adversarial Attacks Based on Lyapunov Theory被引量：1: 《Chinese Journal of Electronics》2024年第3期732-741,共10页Wenjie YAN Ziqi LI Yongjun QI; supported by the National Natural Science Foundation of China (Grant No.61702157);the Doctoral Fund of North China Institute of Aerospace Engineering (Grant No.BKY-2022-09)。; The robustness of graph neural networks(GNNs)is a critical research topic in deep learning.Many researchers have designed regularization methods to enhance the robustness of neural networks,but there is a lack of theo...; 关键词：Deep learning Graph neural network ROBUSTNESS LYAPUNOV REGULARIZATION

SwiftTheft:A Time-Efficient Model Extraction Attack Framework Against Cloud-Based Deep Neural Networks: 《Chinese Journal of Electronics》2024年第1期90-100,共11页Wenbin YANG Xueluan GONG Yanjiao CHEN Qian WANG Jianshuo DONG; partially supported by the National Key R&D Program of China(Grant No.2020AAA0107701);the NSFC(Grant No.U20B2049 and U21B2018)。; With the rise of artificial intelligence and cloud computing,machine-learning-as-a-service platforms,such as Google,Amazon,and IBM,have emerged to provide sophisticated tasks for cloud applications.These proprietary m...; 关键词：Artificial intelligence security Model extraction attacks Deep neural networks

Quantum Attacks on Type-3 Generalized Feistel Scheme and Unbalanced Feistel Scheme with Expanding Functions被引量：1: 《Chinese Journal of Electronics》2023年第2期209-216,共8页ZHANG Zhongya WU Wenling SUI Han WANG Bolin; supported by the National Natural Science Foundation of China(62072445);the National Key Research and Development Program of China(2021YFB3100100).; Quantum algorithms are raising concerns in the field of cryptography all over the world.A growing number of symmetric cryptography algorithms have been attacked in the quantum setting.Type-3 generalized Feistel scheme...; 关键词：Quantum attacks Block ciphers Unbalanced Feistel scheme with expanding functions Type-3 generalized Feistel scheme

Towards Evaluating the Robustness of Adversarial Attacks Against Image Scaling Transformation被引量：1: 《Chinese Journal of Electronics》2023年第1期151-158,共8页ZHENG Jiamin ZHANG Yaoyuan LI Yuanzhang WU Shangbo YU Xiao; supported by the National Natural Science Foundation of China(61876019,U1936218,62072037)。; The robustness of adversarial examples to image scaling transformation is usually ignored when most existing adversarial attacks are proposed.In contrast,image scaling is often the first step of the model to transfer ...; 关键词：Adversarial examples Image scaling Image classification Deep learning

Statistical Model on CRAFT: 《Chinese Journal of Electronics》2022年第4期698-712,共15页WANG Caibing GUO Hao YE Dingfeng WANG Ping; supported by the National Key R&D Program of China(2018YFA0704704);Natural Science Foundation of China(NSFC)(61772519);the Chinese Major Program of National Cryptography Development Foundation(MMJJ20180102).; Many cryptanalytic techniques for symmetric-key primitives rely on specific statistical analysis to extract some secrete key information from a large number of known or chosen plaintext-ciphertext pairs.For example,th...; 关键词：Differential cryptanalysis Statistical models Success probability Data complexity Bimodal behavior CRAFT Differential fault analysis(DFA)attacks

Backdoor Attacks on Image Classification Models in Deep Neural Networks被引量：1: 《Chinese Journal of Electronics》2022年第2期199-212,共14页ZHANG Quanxin MA Wencong WANG Yajie ZHANG Yaoyuan SHI Zhiwei LI Yuanzhang; supported by the National Natural Science Foundation of China(61876019)。; Deep neural network(DNN)is applied widely in many applications and achieves state-of-the-art performance.However,DNN lacks transparency and interpretability for users in structure.Attackers can use this feature to emb...; 关键词：Backdoor attack Poisoning-based attacks Non-poisoning-based attacks Security Review

Joint Spectrum Sensing and Spectrum Access for Defending Massive SSDF Attacks:A Novel Defense Framework被引量：1: 《Chinese Journal of Electronics》2022年第2期240-254,共15页XU Zhenyu SUN Zhiguo GUO Lili Muhammad Zahid Hammad Chintha Tellambura; supported in part by the Fundamental Research Funds for the Central Universities(3072021CF0809);National Natural Science Foundation of China(62001138)。; Multiple secondary users(SUs)perform collaborative spectrum sensing(CSS)in cognitive radio networks to improve the sensing performance.However,this system severely degrades with spectrum sensing data falsification(SSD...; 关键词：Collaborative spectrum sensing Spectrum sensing data falsification Spectrum access Generalized likelihood ratio test

ATTACKS