2019 IEEE Security and Privacy Workshops (SPW)最新文献_第2页

After GDPR, Still Tracking or Not? Understanding Opt-Out States for Online Behavioral Advertising GDPR后，是否还在追踪数据?了解在线行为广告的选择退出状态

2019 IEEE Security and Privacy Workshops (SPW) Pub Date : 2019-05-19 DOI: 10.1109/SPW.2019.00027

Takahito Sakamoto, Masahiro Matsunaga

引用次数: 17

Detecting Malicious Campaigns in Obfuscated JavaScript with Scalable Behavioral Analysis 使用可扩展行为分析检测混淆JavaScript中的恶意活动

2019 IEEE Security and Privacy Workshops (SPW) Pub Date : 2019-05-19 DOI: 10.1109/SPW.2019.00048

Oleksii Starov, Yuchen Zhou, Jun Wang

{"title":"Detecting Malicious Campaigns in Obfuscated JavaScript with Scalable Behavioral Analysis","authors":"Oleksii Starov, Yuchen Zhou, Jun Wang","doi":"10.1109/SPW.2019.00048","DOIUrl":"https://doi.org/10.1109/SPW.2019.00048","url":null,"abstract":"Modern security crawlers and firewall solutions have to analyze millions of websites on a daily basis, and significantly more JavaScript samples. At the same time, fast static approaches, such as file signatures and hash matching, often are not enough to detect advanced malicious campaigns, i.e., obfuscated, packed, or randomized scripts. As such, low-overhead yet efficient dynamic analysis is required. In the current paper we describe behavioral analysis after executing all the scripts on web pages, similarly to how real browsers do. Then, we apply light \"behavioral signatures\" to the collected dynamic indicators, such as global variables declared during runtime, popup messages shown to the user, established WebSocket connections. Using this scalable method for a month, we enhanced the coverage of a commercial URL filtering product by detecting 8,712 URLs with intrusive coin miners. We evaluated the impact of increased coverage through telemetry data and discovered that customers attempted to visit these abusive sites more than a million times. Moreover, we captured 4,633 additional distinct URLs that lead to scam, clickjacking, phishing, and other kinds of malicious JavaScript. Our findings provide insight into recent trends in unauthorized cryptographic coin-mining and show that various scam kits are currently active on the Web.","PeriodicalId":125351,"journal":{"name":"2019 IEEE Security and Privacy Workshops (SPW)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131103464","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

You Talk Too Much: Limiting Privacy Exposure Via Voice Input 你说话太多:通过语音输入限制隐私暴露

2019 IEEE Security and Privacy Workshops (SPW) Pub Date : 2019-05-19 DOI: 10.1109/SPW.2019.00026

Tavish Vaidya, M. Sherr

{"title":"You Talk Too Much: Limiting Privacy Exposure Via Voice Input","authors":"Tavish Vaidya, M. Sherr","doi":"10.1109/SPW.2019.00026","DOIUrl":"https://doi.org/10.1109/SPW.2019.00026","url":null,"abstract":"Voice synthesis uses a voice model to synthesize arbitrary phrases. Advances in voice synthesis have made it possible to create an accurate voice model of a targeted individual, which can then in turn be used to generate spoofed audio in his or her voice. Generating an accurate voice model of target's voice requires the availability of a corpus of the target's speech. This paper makes the observation that the increasing popularity of voice interfaces that use cloud-backed speech recognition (e.g., Siri, Google Assistant, Amazon Alexa) increases the public's vulnerability to voice synthesis attacks. That is, our growing dependence on voice interfaces fosters the collection of our voices. As our main contribution, we show that voice recognition and voice accumulation (that is, the accumulation of users' voices) are separable. This paper introduces techniques for locally sanitizing voice inputs before they are transmitted to the cloud for processing. In essence, such methods employ audio processing techniques to remove distinctive voice characteristics, leaving only the information that is necessary for the cloud-based services to perform speech recognition. Our preliminary experiments show that our defenses prevent state-of-the-art voice synthesis techniques from constructing convincing forgeries of a user's speech, while still permitting accurate voice recognition.","PeriodicalId":125351,"journal":{"name":"2019 IEEE Security and Privacy Workshops (SPW)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124015265","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: 26

IOTFLA : A Secured and Privacy-Preserving Smart Home Architecture Implementing Federated Learning IOTFLA:实现联邦学习的安全和隐私保护智能家居架构

2019 IEEE Security and Privacy Workshops (SPW) Pub Date : 2019-05-19 DOI: 10.1109/SPW.2019.00041

U. Aïvodji, S. Gambs, Alexandre Martin

引用次数: 41

Side Channel Attacks in Computation Offloading Systems with GPU Virtualization GPU虚拟化计算分流系统中的侧信道攻击

2019 IEEE Security and Privacy Workshops (SPW) Pub Date : 2019-05-19 DOI: 10.1109/SPW.2019.00037

Sihang Liu, Yizhou Wei, Jianfeng Chi, F. H. Shezan, Yuan Tian

引用次数: 7

MLSEC - Benchmarking Shallow and Deep Machine Learning Models for Network Security MLSEC -网络安全的浅层和深度机器学习模型的基准测试

2019 IEEE Security and Privacy Workshops (SPW) Pub Date : 2019-05-19 DOI: 10.1109/SPW.2019.00050

P. Casas, Gonzalo Marín, G. Capdehourat, Maciej Korczyński

{"title":"MLSEC - Benchmarking Shallow and Deep Machine Learning Models for Network Security","authors":"P. Casas, Gonzalo Marín, G. Capdehourat, Maciej Korczyński","doi":"10.1109/SPW.2019.00050","DOIUrl":"https://doi.org/10.1109/SPW.2019.00050","url":null,"abstract":"Network security represents a keystone to ISPs, who need to cope with an increasing number of network attacks that put the network's integrity at risk. The high-dimensionality of network data provided by current network monitoring systems opens the door to the massive application of Machine Learning (ML) approaches to improve the detection and classification of network attacks. In recent years, machine learning-based systems have gained popularity for network security applications, usually considering the application of shallow models, where a set of expert handcrafted features are needed to pre-process the data before training. Deep Learning (DL) models can alleviate the need of domain expert knowledge by relying on their ability to learn feature representations from input raw or basic, non-processed data. Still, it is not clear today which is the best model or best model-category to manage network security, as in general, only adhoc and tailored approaches have been proposed and evaluated so far. In this paper we train and benchmark different ML models for detection of network attacks in different real network data. We consider an extensive battery of supervised ML models, including both shallow and deep models, taking as input either pre-computed domain-knowledge based input features, or raw, byte-stream inputs. Proposed models are evaluated either using real, in the wild network measurements coming from the WIDE backbone network – the well-known MAWILab dataset, and through publicly available datasets. Results suggest that deep learning models can provide similar results to the best-performing shallow models, but without any sort of expert handcrafted inputs.","PeriodicalId":125351,"journal":{"name":"2019 IEEE Security and Privacy Workshops (SPW)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133415968","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: 3

Membership Inference Attacks Against Adversarially Robust Deep Learning Models 对抗鲁棒深度学习模型的成员推理攻击

2019 IEEE Security and Privacy Workshops (SPW) Pub Date : 2019-05-19 DOI: 10.1109/SPW.2019.00021

Liwei Song, R. Shokri, Prateek Mittal

{"title":"Membership Inference Attacks Against Adversarially Robust Deep Learning Models","authors":"Liwei Song, R. Shokri, Prateek Mittal","doi":"10.1109/SPW.2019.00021","DOIUrl":"https://doi.org/10.1109/SPW.2019.00021","url":null,"abstract":"In recent years, the research community has increasingly focused on understanding the security and privacy challenges posed by deep learning models. However, the security domain and the privacy domain have typically been considered separately. It is thus unclear whether the defense methods in one domain will have any unexpected impact on the other domain. In this paper, we take a step towards enhancing our understanding of deep learning models when the two domains are combined together. We do this by measuring the success of membership inference attacks against two state-of-the-art adversarial defense methods that mitigate evasion attacks: adversarial training and provable defense. On the one hand, membership inference attacks aim to infer an individual's participation in the target model's training dataset and are known to be correlated with target model's overfitting. On the other hand, adversarial defense methods aim to enhance the robustness of target models by ensuring that model predictions are unchanged for a small area around each sample in the training dataset. Intuitively, adversarial defenses may rely more on the training dataset and be more vulnerable to membership inference attacks. By performing empirical membership inference attacks on both adversarially robust models and corresponding undefended models, we find that the adversarial training method is indeed more susceptible to membership inference attacks, and the privacy leakage is directly correlated with model robustness. We also find that the provable defense approach does not lead to enhanced success of membership inference attacks. However, this is achieved by significantly sacrificing the accuracy of the model on benign data points, indicating that privacy, security, and prediction accuracy are not jointly achieved in these two approaches.","PeriodicalId":125351,"journal":{"name":"2019 IEEE Security and Privacy Workshops (SPW)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132707431","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: 65

Knowledge is Power: Systematic Reuse of Privacy Knowledge for Threat Elicitation 知识就是力量:隐私知识的系统重用用于威胁引出

2019 IEEE Security and Privacy Workshops (SPW) Pub Date : 2019-05-19 DOI: 10.1109/SPW.2019.00025

Kim Wuyts, Laurens Sion, D. Landuyt, W. Joosen

引用次数: 5

MaxNet: Neural Network Architecture for Continuous Detection of Malicious Activity 用于持续检测恶意活动的神经网络架构

2019 IEEE Security and Privacy Workshops (SPW) Pub Date : 2019-05-19 DOI: 10.1109/SPW.2019.00018

Petr Gronát, Javier Alejandro Aldana-Iuit, M. Bálek

引用次数: 6

Counting Outdated Honeypots: Legal and Useful 统计过时的蜜罐:合法和有用的

2019 IEEE Security and Privacy Workshops (SPW) Pub Date : 2019-05-19 DOI: 10.1109/SPW.2019.00049

Alexander Vetterl, R. Clayton, I. Walden

{"title":"Counting Outdated Honeypots: Legal and Useful","authors":"Alexander Vetterl, R. Clayton, I. Walden","doi":"10.1109/SPW.2019.00049","DOIUrl":"https://doi.org/10.1109/SPW.2019.00049","url":null,"abstract":"Honeypots are intended to be covert and so little is known about how many are deployed or who is using them. We used protocol deviations at the SSH transport layer to fingerprint Kippo and Cowrie, the two most popular medium interaction SSH honeypots. Several Internet-wide scans over a one year period revealed the presence of thousands of these honeypots. Sending specific commands revealed their patch status and showed that many systems were not up to date: a quarter or more were not fully updated and by the time of our last scan 20% of honeypots were still running Kippo, which had last been updated several years earlier. However, our paper reporting these results was rejected from a major conference on the basis that our interactions with the honeypots were illegal and hence the research was unethical. We later published a much redacted account of our research which described the fingerprinting but omitted the results we had gained from the issuing of commands to check the patch status. In the present work we provide the missing results, but start with an extended ethical justification for our research and a detailed legal analysis to show why we did not infringe cybersecurity laws.","PeriodicalId":125351,"journal":{"name":"2019 IEEE Security and Privacy Workshops (SPW)","volume":"251 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123027612","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: 10