2021 IEEE International Conference on Cyber Security and Resilience (CSR)最新文献

Defending Against Model Inversion Attack by Adversarial Examples 用对抗性示例防御模型反转攻击

2021 IEEE International Conference on Cyber Security and Resilience (CSR) Pub Date : 2021-07-26 DOI: 10.1109/CSR51186.2021.9527945

Jing Wen, S. Yiu, L. Hui

{"title":"Defending Against Model Inversion Attack by Adversarial Examples","authors":"Jing Wen, S. Yiu, L. Hui","doi":"10.1109/CSR51186.2021.9527945","DOIUrl":"https://doi.org/10.1109/CSR51186.2021.9527945","url":null,"abstract":"Model inversion (MI) attacks aim to infer and reconstruct the input data from the output of a neural network, which poses a severe threat to the privacy of input data. Inspired by adversarial examples, we propose defending against MI attacks by adding adversarial noise to the output. The critical challenge is finding a noise vector that maximizes the inversion error and introduces negligible utility loss to the target model. We propose an algorithm to craft such noise vectors, which also incorporates utility-loss constraints. Specifically, our algorithm takes advantage of the gradient of an inversion model we train to mimic the adversary and compute a noise vector to turn the output into an adversarial example that can maximize the reconstruction error of the inversion model. Then we apply a label modifier that keeps the label unchanged to achieve zero accuracy loss of the target model. Our defense does not tamper with the training process or need the private training dataset. Thus it can be easily applied to any current neural networks or APIs. We evaluate our method under both standard and adaptive attack settings. Our empirical results show our approach is effective against state-of-the-art MI attacks due to the transferability of adversarial examples and outperforms existing defenses. Furthermore, it causes more reconstruction errors while introducing zero accuracy loss and less distortion than existing defenses.","PeriodicalId":253300,"journal":{"name":"2021 IEEE International Conference on Cyber Security and Resilience (CSR)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115492660","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 5

Clustering Analysis of Email Malware Campaigns 电子邮件恶意软件活动的聚类分析

2021 IEEE International Conference on Cyber Security and Resilience (CSR) Pub Date : 2021-07-26 DOI: 10.1109/CSR51186.2021.9527902

Ruichao Zhang, Shang Wang, Renée Burton, Minh Hoang, Juhua Hu, A. Nascimento

引用次数: 0

Modelling Cyber-Risk in an Economic Perspective 经济视角下的网络风险建模

2021 IEEE International Conference on Cyber Security and Resilience (CSR) Pub Date : 2021-07-26 DOI: 10.1109/CSR51186.2021.9527994

Ioannis Bothos, Vasileios Vlachos, D. Kyriazanos, I. Stamatiou, K. Thanos, Pantelis Tzamalis, Sotirios E. Nikoletseas, S. Thomopoulos

引用次数: 0

Mapping Cyber Threat Intelligence to Probabilistic Attack Graphs 将网络威胁情报映射到概率攻击图

2021 IEEE International Conference on Cyber Security and Resilience (CSR) Pub Date : 2021-07-26 DOI: 10.1109/CSR51186.2021.9527970

A. Gylling, M. Ekstedt, Zeeshan Afzal, Per Eliasson

引用次数: 4

ECHO Federated Cyber Range: Towards Next-Generation Scalable Cyber Ranges ECHO联合网络范围:迈向下一代可扩展网络范围

2021 IEEE International Conference on Cyber Security and Resilience (CSR) Pub Date : 2021-07-26 DOI: 10.1109/CSR51186.2021.9527985

Nikos Oikonomou, Notis Mengidis, Minas Spanopoulos-Karalexidis, A. Voulgaridis, Matteo Merialdo, Ivo Raisr, Kaarel Hanson, Paloma de La Vallée, T. Tsikrika, S. Vrochidis, K. Votis

引用次数: 2

Detecting Adversarial DDoS Attacks in Software- Defined Networking Using Deep Learning Techniques and Adversarial Training 使用深度学习技术和对抗性训练检测软件定义网络中的对抗性DDoS攻击

2021 IEEE International Conference on Cyber Security and Resilience (CSR) Pub Date : 2021-07-26 DOI: 10.1109/CSR51186.2021.9527967

Beny Nugraha, Naina Kulkarni, Akash Gopikrishnan

引用次数: 11

A tree-based machine learning methodology to automatically classify software vulnerabilities 一种基于树的自动分类软件漏洞的机器学习方法

2021 IEEE International Conference on Cyber Security and Resilience (CSR) Pub Date : 2021-07-26 DOI: 10.1109/CSR51186.2021.9527965

Georgios Aivatoglou, Mike Anastasiadis, Georgios Spanos, A. Voulgaridis, K. Votis, D. Tzovaras

引用次数: 4

ERAMO: Effective Remote Attestation through Memory Offloading ERAMO:通过内存卸载有效的远程认证

2021 IEEE International Conference on Cyber Security and Resilience (CSR) Pub Date : 2021-07-26 DOI: 10.1109/CSR51186.2021.9527978

J. Østergaard, Edlira Dushku, N. Dragoni

{"title":"ERAMO: Effective Remote Attestation through Memory Offloading","authors":"J. Østergaard, Edlira Dushku, N. Dragoni","doi":"10.1109/CSR51186.2021.9527978","DOIUrl":"https://doi.org/10.1109/CSR51186.2021.9527978","url":null,"abstract":"Remote Attestation (RA) has gained a broad attention over recent years as an essential security mechanism that enables integrity verification of remote IoT devices. Typically, existing RA protocols aim at detecting malware presence in program memory. Recent RA schemes work towards attesting also data memory and focus mainly on detecting runtime attacks that manipulate stack pointers to hijack the execution flow of a running program. Despite different RA approaches, some data memory attacks still remain undetected. This paper proposes ERAMO, a novel RA protocol that investigates memory offloading technique in attesting broad memory regions of IoT devices. Instead of running a complex RA protocol on a resource-constrained IoT device, ERAMO leverages the emerging paradigm of Fog Computing to securely offload memory contents of IoT devices to nearby powerful devices. This approach aims at increasing the effectiveness of RA protocols by attesting larger data memory regions and allowing powerful devices to perform complex analysis of IoT devices’ state. We validate and evaluate ERAMO with a hardware proof-of-concept implementation using an ARM Cortex-M33 based microcontroller that provides ARM TrustZone to support secure isolation of the RA procedure. The conducted experiments confirm the feasibility of ERAMO and demonstrate that offloading technique increases the RA effectiveness in attesting dynamic memory regions.","PeriodicalId":253300,"journal":{"name":"2021 IEEE International Conference on Cyber Security and Resilience (CSR)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121711930","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 4

Enabling Cyber-attack Mitigation Techniques in a Software Defined Network 在软件定义网络中启用网络攻击缓解技术

2021 IEEE International Conference on Cyber Security and Resilience (CSR) Pub Date : 2021-07-26 DOI: 10.1109/CSR51186.2021.9527932

Achilleas Pasias, Thanasis Kotsiopoulos, G. Lazaridis, A. Drosou, D. Tzovaras, P. Sarigiannidis

引用次数: 3

A Stream Clustering Algorithm for Classifying Network IDS Alerts 一种网络IDS告警分类的流聚类算法

2021 IEEE International Conference on Cyber Security and Resilience (CSR) Pub Date : 2021-07-26 DOI: 10.1109/CSR51186.2021.9527926

Risto Vaarandi

引用次数: 2