2019 IEEE 25th International Symposium on On-Line Testing and Robust System Design (IOLTS)最新文献_第8页

3D Integration: Another Dimension Toward Hardware Security 3D集成:硬件安全的另一个维度

2019 IEEE 25th International Symposium on On-Line Testing and Robust System Design (IOLTS) Pub Date : 2019-06-06 DOI: 10.1109/IOLTS.2019.8854395

J. Knechtel, Satwik Patnaik, O. Sinanoglu

引用次数: 7

An Efficient SAT-Attack Algorithm Against Logic Encryption 一种针对逻辑加密的高效sat攻击算法

2019 IEEE 25th International Symposium on On-Line Testing and Robust System Design (IOLTS) Pub Date : 2018-11-28 DOI: 10.1109/IOLTS.2019.8854466

Y. Matsunaga, Masayoshi Yoshimura

引用次数: 0

QuSecNets: Quantization-based Defense Mechanism for Securing Deep Neural Network against Adversarial Attacks 基于量化的保护深度神经网络免受对抗性攻击的防御机制

2019 IEEE 25th International Symposium on On-Line Testing and Robust System Design (IOLTS) Pub Date : 2018-11-04 DOI: 10.1109/IOLTS.2019.8854377

Hassan Ali, Hammad Tariq, Muhammad Abdullah Hanif, Faiq Khalid, Semeen Rehman, Rehan Ahmed, M. Shafique

{"title":"QuSecNets: Quantization-based Defense Mechanism for Securing Deep Neural Network against Adversarial Attacks","authors":"Hassan Ali, Hammad Tariq, Muhammad Abdullah Hanif, Faiq Khalid, Semeen Rehman, Rehan Ahmed, M. Shafique","doi":"10.1109/IOLTS.2019.8854377","DOIUrl":"https://doi.org/10.1109/IOLTS.2019.8854377","url":null,"abstract":"Adversarial examples have emerged as a significant threat to machine learning algorithms, especially to the convolutional neural networks (CNNs). In this paper, we propose two quantization-based defense mechanisms, Constant Quantization (CQ) and Trainable Quantization (TQ), to increase the robustness of CNNs against adversarial examples. CQ quantizes input pixel intensities based on a “fixed” number of quantization levels, while in TQ, the quantization levels are “iteratively learned during the training phase”, thereby providing a stronger defense mechanism. We apply the proposed techniques on undefended CNNs against different state-of-the-art adversarial attacks from the open-source Cleverhans library. The experimental results demonstrate 50%–96% and 10%–50% increase in the classification accuracy of the perturbed images generated from the MNIST and the CIFAR-10 datasets, respectively, on commonly used CNN (Conv2D(64, 8×8)-Conv2D(128, 6×6)-Conv2D(128, 5×5) - Dense(10) - Softmax()) available in Cleverhans library.","PeriodicalId":383056,"journal":{"name":"2019 IEEE 25th International Symposium on On-Line Testing and Robust System Design (IOLTS)","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114155057","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: 29

TrISec: Training Data-Unaware Imperceptible Security Attacks on Deep Neural Networks TrISec:对深度神经网络的训练数据无意识的难以察觉的安全攻击

2019 IEEE 25th International Symposium on On-Line Testing and Robust System Design (IOLTS) Pub Date : 2018-11-02 DOI: 10.1109/IOLTS.2019.8854425

Faiq Khalid, Muhammad Abdullah Hanif, Semeen Rehman, Rehan Ahmed, M. Shafique

{"title":"TrISec: Training Data-Unaware Imperceptible Security Attacks on Deep Neural Networks","authors":"Faiq Khalid, Muhammad Abdullah Hanif, Semeen Rehman, Rehan Ahmed, M. Shafique","doi":"10.1109/IOLTS.2019.8854425","DOIUrl":"https://doi.org/10.1109/IOLTS.2019.8854425","url":null,"abstract":"Most of the data manipulation attacks on deep neural networks (DNNs) during the training stage introduce a perceptible noise that can be catered by preprocessing during inference, or can be identified during the validation phase. There-fore, data poisoning attacks during inference (e.g., adversarial attacks) are becoming more popular. However, many of them do not consider the imperceptibility factor in their optimization algorithms, and can be detected by correlation and structural similarity analysis, or noticeable (e.g., by humans) in multi-level security system. Moreover, majority of the inference attack rely on some knowledge about the training dataset. In this paper, we propose a novel methodology which automatically generates imperceptible attack images by using the back-propagation algorithm on pre-trained DNNs, without requiring any information about the training dataset (i.e., completely training data-unaware). We present a case study on traffic sign detection using the VGGNet trained on the German Traffic Sign Recognition Benchmarks dataset in an autonomous driving use case. Our results demonstrate that the generated attack images successfully perform misclassification while remaining imperceptible in both “subjective” and “objective” quality tests.","PeriodicalId":383056,"journal":{"name":"2019 IEEE 25th International Symposium on On-Line Testing and Robust System Design (IOLTS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129505662","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: 21

A Vulnerability Factor for ECC-protected Memory ecc保护内存的漏洞因子

2019 IEEE 25th International Symposium on On-Line Testing and Robust System Design (IOLTS) Pub Date : 2018-10-15 DOI: 10.1109/IOLTS.2019.8854397

Luc Jaulmes, Miquel Moretó, M. Valero, Marc Casas

引用次数: 4

A Test Generation Method Based on k-Cycle Testing for Finite State Machines 基于k循环测试的有限状态机测试生成方法

2019 IEEE 25th International Symposium on On-Line Testing and Robust System Design (IOLTS) Pub Date : 2018-02-13 DOI: 10.1109/IOLTS.2019.8854426

Yuya Kinoshita, Toshinori Hosokawa, H. Fujiwara

引用次数: 0