Proceedings of the 2021 ACM Workshop on Information Hiding and Multimedia Security最新文献

FederatedReverse: A Detection and Defense Method Against Backdoor Attacks in Federated Learning 联邦学习中后门攻击的检测与防御方法

Proceedings of the 2021 ACM Workshop on Information Hiding and Multimedia Security Pub Date : 2021-06-17 DOI: 10.1145/3437880.3460403

Chen Zhao, Yu Wen, Shuailou Li, Fucheng Liu, Dan Meng

{"title":"FederatedReverse: A Detection and Defense Method Against Backdoor Attacks in Federated Learning","authors":"Chen Zhao, Yu Wen, Shuailou Li, Fucheng Liu, Dan Meng","doi":"10.1145/3437880.3460403","DOIUrl":"https://doi.org/10.1145/3437880.3460403","url":null,"abstract":"Federated learning is a secure machine learning technology proposed to protect data privacy and security in machine learning model training. However, recent studies show that federated learning is vulnerable to backdoor attacks, such as model replacement attacks and distributed backdoor attacks. Most backdoor defense techniques are not appropriate for federated learning since they are based on entire data samples that cannot be hold in federated learning scenarios. The newly proposed methods for federated learning sacrifice the accuracy of models and still fail once attacks persist in many training rounds. In this paper, we propose a novel and effective detection and defense technique called FederatedReverse for federated learning. We conduct extensive experimental evaluation of our solution. The experimental results show that, compared with the existing techniques, our solution can effectively detect and defend against various backdoor attacks in federated learning, where the success rate and duration of backdoor attacks can be greatly reduced and the accuracies of trained models are almost not reduced.","PeriodicalId":120300,"journal":{"name":"Proceedings of the 2021 ACM Workshop on Information Hiding and Multimedia Security","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130244660","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: 14

Towards Match-on-Card Finger Vein Recognition 基于匹配卡的手指静脉识别

Proceedings of the 2021 ACM Workshop on Information Hiding and Multimedia Security Pub Date : 2021-06-17 DOI: 10.1145/3437880.3460406

Michael Linortner, A. Uhl

引用次数: 8

Evaluating and Designing against Side-Channel Leakage: White Box or Black Box? 侧道泄漏评估与设计:白盒还是黑盒?

Proceedings of the 2021 ACM Workshop on Information Hiding and Multimedia Security Pub Date : 2021-06-17 DOI: 10.1145/3437880.3458441

François-Xavier Standaert

{"title":"Evaluating and Designing against Side-Channel Leakage: White Box or Black Box?","authors":"François-Xavier Standaert","doi":"10.1145/3437880.3458441","DOIUrl":"https://doi.org/10.1145/3437880.3458441","url":null,"abstract":"Side-channel analysis is an important concern for the security of cryptographic implementations, and may lead to powerful key recovery attacks if no countermeasures are deployed. Therefore, various types of protection mechanisms have been proposed over the last 20 years. In view of the cost and performance overheads caused by these protections, their fair evaluation and scarce use are a primary concern for hardware and software designers. Yet, the physical nature of side-channel analysis also renders the security evaluation of cryptographic implementations very different from the one of cryptographic algorithms against mathematical cryptanalysis. That is, while the latter can be quantified based on (well-defined) time, data and memory complexities, the evaluation of side-channel security additionally requires to quantify the informativeness and exploitability of the physical leakages. This implies that a part of these security evaluations is inherently heuristic and dependent on engineering expertise. It also raises the question of the capabilities given to the adversary/evaluator. For example, should she get full (unrestricted) access to the implementation to gain a precise understanding of its functioning (which I will denote as the white box approach) or should she be more restricted? In this talk, I will argue that a white box approach is not only desirable in order to avoid designing and evaluating implementations with a \"false sense of security\" but also that such designs become feasible in view of the research progresses made over the last two decades.","PeriodicalId":120300,"journal":{"name":"Proceedings of the 2021 ACM Workshop on Information Hiding and Multimedia Security","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122788419","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: 0

Information Hiding in Cyber Physical Systems: Challenges for Embedding, Retrieval and Detection using Sensor Data of the SWAT Dataset 网络物理系统中的信息隐藏:利用SWAT数据集传感器数据嵌入、检索和检测的挑战

Proceedings of the 2021 ACM Workshop on Information Hiding and Multimedia Security Pub Date : 2021-06-17 DOI: 10.1145/3437880.3460413

Kevin Lamshöft, T. Neubert, Christian Krätzer, C. Vielhauer, J. Dittmann

{"title":"Information Hiding in Cyber Physical Systems: Challenges for Embedding, Retrieval and Detection using Sensor Data of the SWAT Dataset","authors":"Kevin Lamshöft, T. Neubert, Christian Krätzer, C. Vielhauer, J. Dittmann","doi":"10.1145/3437880.3460413","DOIUrl":"https://doi.org/10.1145/3437880.3460413","url":null,"abstract":"In this paper, we present an Information Hiding approach that would be suitable for exfiltrating sensible information of Industrial Control Systems (ICS) by leveraging the long-term storage of process data in historian databases. We show how hidden messages can be embedded in sensor measurements as well as retrieved asynchronously by accessing the historian. We evaluate this approach at the example of water-flow and water-level sensors of the Secure Water Treatment (SWAT) dataset from iTrust. To generalize from specific cover channels (sensors and their transmitted data), we reflect upon general challenges that arise in such Information Hiding scenarios creating network covert channels and discuss aspects of cover channel selection and and sender receiver synchronisation as well as temporal aspects such as the potential persistence of hidden messages in Cyber Physical Systems (CPS). For an empirical evaluation we design and implement a covert channel that makes use of different embedding strategies to perform an adaptive approach in regards to the noise in sensor measurements, resulting in dynamic capacity and bandwidth selection to reduce detection probability. The results of this evaluation show that, using such methods, the exfiltration of sensible information in long-term scaled attacks would indeed be possible. Additionally, we present two detection approaches for the introduced hidden channel and carry out an extensive evaluation of our detectors with multiple test data sets and different parameters. We determine a detection accuracy of up to 87.8% on test data at a false positive rate (FPR) of 0%.","PeriodicalId":120300,"journal":{"name":"Proceedings of the 2021 ACM Workshop on Information Hiding and Multimedia Security","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116055203","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: 8

Optimizing Additive Approximations of Non-additive Distortion Functions 非加性失真函数的加性逼近优化

Proceedings of the 2021 ACM Workshop on Information Hiding and Multimedia Security Pub Date : 2021-06-17 DOI: 10.1145/3437880.3460407

Solène Bernard, P. Bas, T. Pevný, John Klein

引用次数: 11

A Protocol for Secure Verification of Watermarks Embedded into Machine Learning Models 嵌入到机器学习模型中的水印安全验证协议

Proceedings of the 2021 ACM Workshop on Information Hiding and Multimedia Security Pub Date : 2021-06-17 DOI: 10.1145/3437880.3460409

K. Kapusta, V. Thouvenot, Olivier Bettan, Hugo Beguinet, Hugo Senet

{"title":"A Protocol for Secure Verification of Watermarks Embedded into Machine Learning Models","authors":"K. Kapusta, V. Thouvenot, Olivier Bettan, Hugo Beguinet, Hugo Senet","doi":"10.1145/3437880.3460409","DOIUrl":"https://doi.org/10.1145/3437880.3460409","url":null,"abstract":"Machine Learning is a well established tool used in a variety of applications. As training advanced models requires considerable amounts of meaningful data in addition to specific knowledge, a new business model separate models creators from model users. Pre-trained models are sold or made available as a service. This raises several security challenges, among others the one of intellectual property protection. Therefore, a new research track actively seeks to provide techniques for model watermarking that would enable model identification in case of suspicion of model theft or misuse. In this paper, we focus on the problem of secure watermarks verification, which affects all of the proposed techniques and until now was barely tackled. First, we revisit the existing threat model. In particular, we explain the possible threats related to a semi-honest or dishonest verification authority. Secondly, we show how to reduce trust requirements between participants by performing the watermarks verification on encrypted data. Finally, we describe a novel secure verification protocol as well as detail its possible implementation using Multi-Party Computation. The proposed solution does not only preserve the confidentiality of the watermarks but also helps detecting evasion attacks. It could be adopted to work with other authentication schemes based on watermarking, especially with image watermarking schemes.","PeriodicalId":120300,"journal":{"name":"Proceedings of the 2021 ACM Workshop on Information Hiding and Multimedia Security","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123593503","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: 8

Angular Margin Softmax Loss and Its Variants for Double Compressed AMR Audio Detection 角边际软最大损失及其变体双压缩AMR音频检测

Proceedings of the 2021 ACM Workshop on Information Hiding and Multimedia Security Pub Date : 2021-06-17 DOI: 10.1145/3437880.3460414

Aykut Büker, C. Hanilçi

{"title":"Angular Margin Softmax Loss and Its Variants for Double Compressed AMR Audio Detection","authors":"Aykut Büker, C. Hanilçi","doi":"10.1145/3437880.3460414","DOIUrl":"https://doi.org/10.1145/3437880.3460414","url":null,"abstract":"Double compressed (DC) adaptive multi-rate (AMR) audio detection is an important but challenging audio forensic task which has received great attention over the last decade. Although the majority of the existing studies extract hand-crafted features and classify these features using traditional pattern matching algorithms such as support vector machines (SVM), recently convolutional neural network (CNN) based DC AMR audio detection system was proposed which yields very promising detection performance. Similar to any traditional CNN based classification system, CNN based DC AMR recognition system uses standard softmax loss as the training criterion. In this paper, we propose to use angular margin softmax loss and its variants for DC AMR detection problem. Although using angular margin softmax was originally proposed for face recognition, we adapt it to the CNN based end-to-end DC audio detection system. The angular margin softmax basically introduces a margin between two classes so that the system can learn more discriminative embeddings for the problem. Experimental results show that adding angular margin penalty to the traditional softmax loss increases the average DC AMR audio detection from 95.83% to 100%. It is also found that the angular margin softmax loss functions boost the DC AMR audio detection performance when there is a mismatch between training and test datasets.","PeriodicalId":120300,"journal":{"name":"Proceedings of the 2021 ACM Workshop on Information Hiding and Multimedia Security","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128217234","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: 2

Tracing Data through Learning with Watermarking 通过水印学习跟踪数据

Proceedings of the 2021 ACM Workshop on Information Hiding and Multimedia Security Pub Date : 2021-06-17 DOI: 10.1145/3437880.3458442

Alexandre Sablayrolles

引用次数: 0

Banners: Binarized Neural Networks with Replicated Secret Sharing 横幅:具有复制秘密共享的二值化神经网络

Proceedings of the 2021 ACM Workshop on Information Hiding and Multimedia Security Pub Date : 2021-06-17 DOI: 10.1145/3437880.3460394

Alberto Ibarrondo, H. Chabanne, Melek Önen

{"title":"Banners: Binarized Neural Networks with Replicated Secret Sharing","authors":"Alberto Ibarrondo, H. Chabanne, Melek Önen","doi":"10.1145/3437880.3460394","DOIUrl":"https://doi.org/10.1145/3437880.3460394","url":null,"abstract":"Binarized Neural Networks (BNN) provide efficient implementations of Convolutional Neural Networks (CNN). This makes them particularly suitable to perform fast and memory-light inference of neural networks running on resource-constrained devices. Motivated by the growing interest in CNN-based biometric recognition on potentially insecure devices, or as part of strong multi-factor authentication for sensitive applications, the protection of BNN inference on edge devices is rendered imperative. We propose a new method to perform secure inference of BNN relying on secure multiparty computation. While preceding papers offered security in a semi-honest setting for BNN or malicious security for standard CNN, our work yields security with abort against one malicious adversary for BNN by leveraging on Replicated Secret Sharing (RSS) for an honest majority with three computing parties. Experimentally, we implement Banners on top of MP-SPDZ and compare it with prior work over binarized models trained for MNIST and CIFAR10 image classification datasets. Our results attest the efficiency of Banners as a privacy-preserving inference technique.","PeriodicalId":120300,"journal":{"name":"Proceedings of the 2021 ACM Workshop on Information Hiding and Multimedia Security","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117074995","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: 6

Fast Detection of Heterogeneous Parallel Steganography for Streaming Voice 流语音异构并行隐写的快速检测

Proceedings of the 2021 ACM Workshop on Information Hiding and Multimedia Security Pub Date : 2021-06-17 DOI: 10.1145/3437880.3460404

Huili Wang, Zhongliang Yang, Yuting Hu, Zhen Yang, Yongfeng Huang

{"title":"Fast Detection of Heterogeneous Parallel Steganography for Streaming Voice","authors":"Huili Wang, Zhongliang Yang, Yuting Hu, Zhen Yang, Yongfeng Huang","doi":"10.1145/3437880.3460404","DOIUrl":"https://doi.org/10.1145/3437880.3460404","url":null,"abstract":"Heterogeneous parallel steganography (HPS) has become a new trend of current streaming media voice steganography, which hides secret information in the frames of streaming media with multiple kinds of orthogonal steganography. Because of the complexity and imperceptibility of HPS, detecting its existence is a challenge for previous steganalysis methods, especially in the case of short sliding window length and low embedding rate. In order to improve the situation, we design a fast and efficient detection method named the key feature extraction and fusion network (KFEF) based on attention mechanism. The proposed model is able to effectively extract the key characteristic of the exceptions due to steganography and fuse the extracted features for different steganographic algorithms used in HPS. Experimental results show that the proposed method significantly improves the classification accuracy in detecting both low embedding rate samples and short segment samples. In addition, the detection time consumption is shorter than other methods and meets real-time requirements. Finally, with the help of attention we can predict the approximate locations of secret information which may bring new ideas to further steganalysis.","PeriodicalId":120300,"journal":{"name":"Proceedings of the 2021 ACM Workshop on Information Hiding and Multimedia Security","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130142335","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: 1