Welcome to the 1996 IEEE Second International Workshop on Systems Management. Since the first Systems Management Workshop in 1993, the world of systems and application management has grown and moved simultaneously in different directions: the growing acceptance of objectoriented technology to model and implement management activities and computing environments; more concern about end-to-end quality of service, especially with the emergence of ATM technology; the further blurring of the boundaries between telecommunications and computer communications; the growing reality of distributed computing environments with personal computers, workstations, servers and mainframes; the growth of the Internet as the means for distributed operations and services.
{"title":"Message from the Workshop General Chair","authors":"","doi":"10.1109/spw.2019.00005","DOIUrl":"https://doi.org/10.1109/spw.2019.00005","url":null,"abstract":"Welcome to the 1996 IEEE Second International Workshop on Systems Management. Since the first Systems Management Workshop in 1993, the world of systems and application management has grown and moved simultaneously in different directions: the growing acceptance of objectoriented technology to model and implement management activities and computing environments; more concern about end-to-end quality of service, especially with the emergence of ATM technology; the further blurring of the boundaries between telecommunications and computer communications; the growing reality of distributed computing environments with personal computers, workstations, servers and mainframes; the growth of the Internet as the means for distributed operations and services.","PeriodicalId":125351,"journal":{"name":"2019 IEEE Security and Privacy Workshops (SPW)","volume":"1994 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125549787","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}
Abhishta Abhishta, M. Junger, R. Joosten, L. Nieuwenhuis
We study the influence of daily routines of Dutch academic institutions on the number of DDoS attacks targeting their infrastructures. We hypothesise that the attacks are motivated and harness the postulates of Routine Activity Theory (RAT) from criminology to analyse the data. We define routine periods in order to group days with similar activities and use 2.5 years of NetFlow alerts data measured by SURFnet to compare the number of alerts generated during each of these periods. Our analysis shows clear correlation between academic schedules and attack patterns on academic institutions. This leads us to believe that most of these attacks are not random and are initiated by someone who might benefit by disrupting scheduled educational activities.
{"title":"Victim Routine Influences the Number of DDoS Attacks: Evidence from Dutch Educational Network","authors":"Abhishta Abhishta, M. Junger, R. Joosten, L. Nieuwenhuis","doi":"10.1109/SPW.2019.00052","DOIUrl":"https://doi.org/10.1109/SPW.2019.00052","url":null,"abstract":"We study the influence of daily routines of Dutch academic institutions on the number of DDoS attacks targeting their infrastructures. We hypothesise that the attacks are motivated and harness the postulates of Routine Activity Theory (RAT) from criminology to analyse the data. We define routine periods in order to group days with similar activities and use 2.5 years of NetFlow alerts data measured by SURFnet to compare the number of alerts generated during each of these periods. Our analysis shows clear correlation between academic schedules and attack patterns on academic institutions. This leads us to believe that most of these attacks are not random and are initiated by someone who might benefit by disrupting scheduled educational activities.","PeriodicalId":125351,"journal":{"name":"2019 IEEE Security and Privacy Workshops (SPW)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126696241","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}
Alesia Chernikova, Alina Oprea, C. Nita-Rotaru, Baekgyu Kim
Deep Neural Networks (DNNs) have tremendous potential in advancing the vision for self-driving cars. However, the security of DNN models in this context leads to major safety implications and needs to be better understood. We consider the case study of steering angle prediction from camera images, using the dataset from the 2014 Udacity challenge. We demonstrate for the first time adversarial testing-time attacks for this application for both classification and regression settings. We show that minor modifications to the camera image (an L_2 distance of 0.82 for one of the considered models) result in mis-classification of an image to any class of attacker's choice. Furthermore, our regression attack results in a significant increase in Mean Square Error (MSE) – by a factor of 69 in the worst case.
{"title":"Are Self-Driving Cars Secure? Evasion Attacks Against Deep Neural Networks for Steering Angle Prediction","authors":"Alesia Chernikova, Alina Oprea, C. Nita-Rotaru, Baekgyu Kim","doi":"10.1109/SPW.2019.00033","DOIUrl":"https://doi.org/10.1109/SPW.2019.00033","url":null,"abstract":"Deep Neural Networks (DNNs) have tremendous potential in advancing the vision for self-driving cars. However, the security of DNN models in this context leads to major safety implications and needs to be better understood. We consider the case study of steering angle prediction from camera images, using the dataset from the 2014 Udacity challenge. We demonstrate for the first time adversarial testing-time attacks for this application for both classification and regression settings. We show that minor modifications to the camera image (an L_2 distance of 0.82 for one of the considered models) result in mis-classification of an image to any class of attacker's choice. Furthermore, our regression attack results in a significant increase in Mean Square Error (MSE) – by a factor of 69 in the worst case.","PeriodicalId":125351,"journal":{"name":"2019 IEEE Security and Privacy Workshops (SPW)","volume":"61 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133878452","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}
Despite a large amount of attention on adversarial examples, very few works have demonstrated an effective defense against this threat. We examine Deep k-Nearest Neighbor (DkNN), a proposed defense that combines k-Nearest Neighbor (kNN) and deep learning to improve the model's robustness to adversarial examples. It is challenging to evaluate the robustness of this scheme due to a lack of efficient algorithm for attacking kNN classifiers with large k and high-dimensional data. We propose a heuristic attack that allows us to use gradient descent to find adversarial examples for kNN classifiers, and then apply it to attack the DkNN defense as well. Results suggest that our attack is moderately stronger than any naive attack on kNN and significantly outperforms other attacks on DkNN.
{"title":"On the Robustness of Deep K-Nearest Neighbors","authors":"Chawin Sitawarin, David A. Wagner","doi":"10.1109/SPW.2019.00014","DOIUrl":"https://doi.org/10.1109/SPW.2019.00014","url":null,"abstract":"Despite a large amount of attention on adversarial examples, very few works have demonstrated an effective defense against this threat. We examine Deep k-Nearest Neighbor (DkNN), a proposed defense that combines k-Nearest Neighbor (kNN) and deep learning to improve the model's robustness to adversarial examples. It is challenging to evaluate the robustness of this scheme due to a lack of efficient algorithm for attacking kNN classifiers with large k and high-dimensional data. We propose a heuristic attack that allows us to use gradient descent to find adversarial examples for kNN classifiers, and then apply it to attack the DkNN defense as well. Results suggest that our attack is moderately stronger than any naive attack on kNN and significantly outperforms other attacks on DkNN.","PeriodicalId":125351,"journal":{"name":"2019 IEEE Security and Privacy Workshops (SPW)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115445591","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}
Feature engineering is one of the most costly aspects of developing effective machine learning models, and that cost is even greater in specialized problem domains, like malware classification, where expert skills are necessary to identify useful features. Recent work, however, has shown that deep learning models can be used to automatically learn feature representations directly from the raw, unstructured bytes of the binaries themselves. In this paper, we explore what these models are learning about malware. To do so, we examine the learned features at multiple levels of resolution, from individual byte embeddings to end-to-end analysis of the model. At each step, we connect these byte-oriented activations to their original semantics through parsing and disassembly of the binary to arrive at human-understandable features. Through our results, we identify several interesting features learned by the model and their connection to manually-derived features typically used by traditional machine learning models. Additionally, we explore the impact of training data volume and regularization on the quality of the learned features and the efficacy of the classifiers, revealing the somewhat paradoxical insight that better generalization does not necessarily result in better performance for byte-based malware classifiers.
{"title":"Activation Analysis of a Byte-Based Deep Neural Network for Malware Classification","authors":"Scott E. Coull, Christopher Gardner","doi":"10.1109/SPW.2019.00017","DOIUrl":"https://doi.org/10.1109/SPW.2019.00017","url":null,"abstract":"Feature engineering is one of the most costly aspects of developing effective machine learning models, and that cost is even greater in specialized problem domains, like malware classification, where expert skills are necessary to identify useful features. Recent work, however, has shown that deep learning models can be used to automatically learn feature representations directly from the raw, unstructured bytes of the binaries themselves. In this paper, we explore what these models are learning about malware. To do so, we examine the learned features at multiple levels of resolution, from individual byte embeddings to end-to-end analysis of the model. At each step, we connect these byte-oriented activations to their original semantics through parsing and disassembly of the binary to arrive at human-understandable features. Through our results, we identify several interesting features learned by the model and their connection to manually-derived features typically used by traditional machine learning models. Additionally, we explore the impact of training data volume and regularization on the quality of the learned features and the efficacy of the classifiers, revealing the somewhat paradoxical insight that better generalization does not necessarily result in better performance for byte-based malware classifiers.","PeriodicalId":125351,"journal":{"name":"2019 IEEE Security and Privacy Workshops (SPW)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-03-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129814680","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}
The convolutional neural network (CNN) architecture is increasingly being applied to new domains, such as malware detection, where it is able to learn malicious behavior from raw bytes extracted from executables. These architectures reach impressive performance with no feature engineering effort involved, but their robustness against active attackers is yet to be understood. Such malware detectors could face a new attack vector in the form of adversarial interference with the classification model. Existing evasion attacks intended to cause misclassification on test-time instances, which have been extensively studied for image classifiers, are not applicable because of the input semantics that prevents arbitrary changes to the binaries. This paper explores the area of adversarial examples for malware detection. By training an existing model on a production-scale dataset, we show that some previous attacks are less effective than initially reported, while simultaneously highlighting architectural weaknesses that facilitate new attack strategies for malware classification. Finally, we explore how generalizable different attack strategies are, the trade-offs when aiming to increase their effectiveness, and the transferability of single-step attacks.
{"title":"Exploring Adversarial Examples in Malware Detection","authors":"Octavian Suciu, Scott E. Coull, Jeffrey Johns","doi":"10.1109/SPW.2019.00015","DOIUrl":"https://doi.org/10.1109/SPW.2019.00015","url":null,"abstract":"The convolutional neural network (CNN) architecture is increasingly being applied to new domains, such as malware detection, where it is able to learn malicious behavior from raw bytes extracted from executables. These architectures reach impressive performance with no feature engineering effort involved, but their robustness against active attackers is yet to be understood. Such malware detectors could face a new attack vector in the form of adversarial interference with the classification model. Existing evasion attacks intended to cause misclassification on test-time instances, which have been extensively studied for image classifiers, are not applicable because of the input semantics that prevents arbitrary changes to the binaries. This paper explores the area of adversarial examples for malware detection. By training an existing model on a production-scale dataset, we show that some previous attacks are less effective than initially reported, while simultaneously highlighting architectural weaknesses that facilitate new attack strategies for malware classification. Finally, we explore how generalizable different attack strategies are, the trade-offs when aiming to increase their effectiveness, and the transferability of single-step attacks.","PeriodicalId":125351,"journal":{"name":"2019 IEEE Security and Privacy Workshops (SPW)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125807024","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}
Rohan Taori, Amog Kamsetty, Brenton Chu, N. Vemuri
The application of deep recurrent networks to audio transcription has led to impressive gains in automatic speech recognition (ASR) systems. Many have demonstrated that small adversarial perturbations can fool deep neural networks into incorrectly predicting a specified target with high confidence. Current work on fooling ASR systems have focused on white-box attacks, in which the model architecture and parameters are known. In this paper, we adopt a black-box approach to adversarial generation, combining the approaches of both genetic algorithms and gradient estimation to solve the task. We achieve a 89.25% targeted attack similarity, with 35% targeted attack success rate, after 3000 generations while maintaining 94.6% audio file similarity.
{"title":"Targeted Adversarial Examples for Black Box Audio Systems","authors":"Rohan Taori, Amog Kamsetty, Brenton Chu, N. Vemuri","doi":"10.1109/SPW.2019.00016","DOIUrl":"https://doi.org/10.1109/SPW.2019.00016","url":null,"abstract":"The application of deep recurrent networks to audio transcription has led to impressive gains in automatic speech recognition (ASR) systems. Many have demonstrated that small adversarial perturbations can fool deep neural networks into incorrectly predicting a specified target with high confidence. Current work on fooling ASR systems have focused on white-box attacks, in which the model architecture and parameters are known. In this paper, we adopt a black-box approach to adversarial generation, combining the approaches of both genetic algorithms and gradient estimation to solve the task. We achieve a 89.25% targeted attack similarity, with 35% targeted attack success rate, after 3000 generations while maintaining 94.6% audio file similarity.","PeriodicalId":125351,"journal":{"name":"2019 IEEE Security and Privacy Workshops (SPW)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131318177","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：