Proceedings of the 2022 ACM Workshop on Information Hiding and Multimedia Security最新文献_第2页

Covert Channels in Network Time Security 网络时间安全中的隐蔽通道

Proceedings of the 2022 ACM Workshop on Information Hiding and Multimedia Security Pub Date : 2022-06-23 DOI: 10.1145/3531536.3532947

Kevin Lamshöft, J. Dittmann

引用次数: 0

Session details: Session 4: Steganography I 会议详情:第四部分:隐写术1

Proceedings of the 2022 ACM Workshop on Information Hiding and Multimedia Security Pub Date : 2022-06-23 DOI: 10.1145/3545214

J. Fridrich

引用次数: 0

Hiding Needles in a Haystack: Towards Constructing Neural Networks that Evade Verification 大海捞针:构建逃避验证的神经网络

Proceedings of the 2022 ACM Workshop on Information Hiding and Multimedia Security Pub Date : 2022-06-23 DOI: 10.1145/3531536.3532966

Árpád Berta, Gábor Danner, István Hegedüs, Márk Jelasity

{"title":"Hiding Needles in a Haystack: Towards Constructing Neural Networks that Evade Verification","authors":"Árpád Berta, Gábor Danner, István Hegedüs, Márk Jelasity","doi":"10.1145/3531536.3532966","DOIUrl":"https://doi.org/10.1145/3531536.3532966","url":null,"abstract":"Machine learning models are vulnerable to adversarial attacks, where a small, invisible, malicious perturbation of the input changes the predicted label. A large area of research is concerned with verification techniques that attempt to decide whether a given model has adversarial inputs close to a given benign input. Here, we show that current approaches to verification have a key vulnerability: we construct a model that is not robust but passes current verifiers. The idea is to insert artificial adversarial perturbations by adding a backdoor to a robust neural network model. In our construction, the adversarial input subspace that triggers the backdoor has a very small volume, and outside this subspace the gradient of the model is identical to that of the clean model. In other words, we seek to create a \"needle in a haystack\" search problem. For practical purposes, we also require that the adversarial samples be robust to JPEG compression. Large \"needle in the haystack\" problems are practically impossible to solve with any search algorithm. Formal verifiers can handle this in principle, but they do not scale up to real-world networks at the moment, and achieving this is a challenge because the verification problem is NP-complete. Our construction is based on training a hiding and a revealing network using deep steganography. Using the revealing network, we create a separate backdoor network and integrate it into the target network. We train our deep steganography networks over the CIFAR-10 dataset. We then evaluate our construction using state-of-the-art adversarial attacks and backdoor detectors over the CIFAR-10 and the ImageNet datasets. We made the code and models publicly available at https://github.com/szegedai/hiding-needles-in-a-haystack.","PeriodicalId":164949,"journal":{"name":"Proceedings of the 2022 ACM Workshop on Information Hiding and Multimedia Security","volume":"223 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114600573","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

Sparse Trigger Pattern Guided Deep Learning Model Watermarking 稀疏触发模式引导深度学习模型水印

Proceedings of the 2022 ACM Workshop on Information Hiding and Multimedia Security Pub Date : 2022-06-23 DOI: 10.1145/3531536.3532961

Chun-Shien Lu

引用次数: 2

AMR Steganalysis based on Adversarial Bi-GRU and Data Distillation 基于对抗性Bi-GRU和数据蒸馏的AMR隐写分析

Proceedings of the 2022 ACM Workshop on Information Hiding and Multimedia Security Pub Date : 2022-06-23 DOI: 10.1145/3531536.3532958

Z. Wu, Junjun Guo

{"title":"AMR Steganalysis based on Adversarial Bi-GRU and Data Distillation","authors":"Z. Wu, Junjun Guo","doi":"10.1145/3531536.3532958","DOIUrl":"https://doi.org/10.1145/3531536.3532958","url":null,"abstract":"Existing AMR (Adaptive Multi-Rate) steganalysis algorithms based on pitch delay have low detection accuracy on samples with short time or low embedding rate, and the model shows fragility under the attack of adversarial samples. To solve this problem, we design an advanced AMR steganalysis method based on adversarial Bi-GRU (Bi-directional Gated Recurrent Unit) and data distillation. First, Gaussian white noise is randomly added to part of the original speech to form adversarial data set, then artificially annotate a small amount of voice to train the model. Second, perform three transformations of 1.5 times speed, 0.5 times speed, and mirror flip on the remaining original voice data, then put them into Bi-GRU for classification, and the final predicted label obtained by the decision fusion corresponds to the original data. All data with the label is put back into the Bi-GRU model for final training at last. What needs to be pointed out is that each batch of final training data includes normal and adversarial samples. This method adopts a semi-supervised learning method, which greatly saves the resources consumed by manual labeling, and introduces adversarial Bi-GRU, which can realize the two-direction analysis of samples for a long time. Based on improving the detection accuracy, the safety and robustness of the model are greatly improved. The experimental results show that for normal and adversarial samples, the algorithm can achieve accuracy of 96.73% and 95.6% respectively.","PeriodicalId":164949,"journal":{"name":"Proceedings of the 2022 ACM Workshop on Information Hiding and Multimedia Security","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133941457","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

A Nearest Neighbor Under-sampling Strategy for Vertical Federated Learning in Financial Domain 金融领域垂直联邦学习的最近邻欠采样策略

Proceedings of the 2022 ACM Workshop on Information Hiding and Multimedia Security Pub Date : 2022-06-23 DOI: 10.1145/3531536.3532960

Denghao Li, Jianzong Wang, Lingwei Kong, Shijing Si, Zhangcheng Huang, Chenyu Huang, Jing Xiao

{"title":"A Nearest Neighbor Under-sampling Strategy for Vertical Federated Learning in Financial Domain","authors":"Denghao Li, Jianzong Wang, Lingwei Kong, Shijing Si, Zhangcheng Huang, Chenyu Huang, Jing Xiao","doi":"10.1145/3531536.3532960","DOIUrl":"https://doi.org/10.1145/3531536.3532960","url":null,"abstract":"Machine learning techniques have been widely applied in modern financial activities. Participants in the field are aware of the importance of data privacy. Vertical federated learning (VFL) was proposed as a solution to multi-party secure computation for machine learning to obtain the huge data required by the models as well as keep the privacy of the data holders. However, previous research majorly analyzed the algorithms under ideal conditions. Data imbalance in VFL is still an open problem. In this paper, we propose a privacy-preserving sampling strategy for imbalanced VFL based on federated graph embedding of the samples, without leaking any distribution information. The participants of the federation provide partial neighbor information for each sample during the intersection stage and the controversial negative sample will be filtered out. Experiments were conducted on commonly used financial datasets and one real-world dataset. Our proposed approach obtained the leading F1 score on all tested datasets on comparing with the baseline under sampling strategies for VFL.","PeriodicalId":164949,"journal":{"name":"Proceedings of the 2022 ACM Workshop on Information Hiding and Multimedia Security","volume":"63 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131156312","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

Domain Adaptational Text Steganalysis Based on Transductive Learning 基于转换学习的领域自适应文本隐写分析

Proceedings of the 2022 ACM Workshop on Information Hiding and Multimedia Security Pub Date : 2022-06-23 DOI: 10.1145/3531536.3532963

Yiming Xue, Boya Yang, Yaqian Deng, Wanli Peng, Juan Wen

引用次数: 6

Session details: Session 2: Security of Machine Learning 会议详情:会议2:机器学习的安全性

Proceedings of the 2022 ACM Workshop on Information Hiding and Multimedia Security Pub Date : 2022-06-23 DOI: 10.1145/3545212

Yassine Yousfi

引用次数: 0

Fighting the Reverse JPEG Compatibility Attack: Pick your Side 对抗反向JPEG兼容性攻击:选择你的立场

Proceedings of the 2022 ACM Workshop on Information Hiding and Multimedia Security Pub Date : 2022-06-23 DOI: 10.1145/3531536.3532955

Jan Butora, P. Bas

{"title":"Fighting the Reverse JPEG Compatibility Attack: Pick your Side","authors":"Jan Butora, P. Bas","doi":"10.1145/3531536.3532955","DOIUrl":"https://doi.org/10.1145/3531536.3532955","url":null,"abstract":"In this work we aim to design a steganographic scheme undetectable by the Reverse JPEG Compatibility Attack (RJCA). The RJCA, while only effective for JPEG images compressed with quality factors 99 and 100, was shown to work mainly due to change in variance of the rounding errors after decompression of the DCT coefficients, which is induced by embedding changes incompatible with the JPEG format. One remedy to preserve the aforementioned format is utilizing during the embedding the rounding errors created during the JPEG compression, but no steganographic method is known to be resilient to RJCA without this knowledge. Inspecting the effect of embedding changes on variance and also mean of decompression rounding errors, we propose a steganographic method allowing resistance against RJCA without any side-information. To resist RJCA, we propose a distortion metric making all embedding changes within a DCT block dependent, resulting in a lattice-based embedding. Then it turns out it is enough to cleverly pick the side of the (binary) embedding changes through inspection of their effect on the variance of decompression rounding errors and simply use uniform costs in order to enforce their sparsity across DCT blocks. To increase security against detectors in the spatial (pixel) domain, we show an easy way of combining the proposed methodology with steganography designed for spatial domain security, further improving the undetectability for quality factor 99. The improvements over existing non-informed steganography are up to 40% in terms of detector's accuracy.","PeriodicalId":164949,"journal":{"name":"Proceedings of the 2022 ACM Workshop on Information Hiding and Multimedia Security","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133766318","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

Looking for Signals: A Systems Security Perspective 寻找信号:系统安全视角

Proceedings of the 2022 ACM Workshop on Information Hiding and Multimedia Security Pub Date : 2022-06-23 DOI: 10.1145/3531536.3533774

Christopher Kruegel

{"title":"Looking for Signals: A Systems Security Perspective","authors":"Christopher Kruegel","doi":"10.1145/3531536.3533774","DOIUrl":"https://doi.org/10.1145/3531536.3533774","url":null,"abstract":"Over the last 20 years, my students and I have built systems that look for signals of malice in large datasets. These datasets include network traffic, program code, web transactions, and social media posts. For many of our detection systems, we used feature engineering to model properties of the data and then leveraged different types of machine learning to find outliers or to build classifiers that could recognize unwanted inputs. In this presentation, I will cover three recent works that go beyond that basic approach. First, I will talk about cross-dataset analysis. The key idea is that we look at the same data from different vantage points. Instead of directly detecting malicious instances, the analysis compares the views across multiple angles and finds those cases where these views meaningfully differ. Second, I will cover an approach to perform meta-analysis of the outputs (events) that a detection model might produce. Sometimes, looking at a single event is insufficient to determine whether it is malicious. In such cases, it is necessary to correlate multiple events. We have built a semi-supervised analysis that leverages the context of an event to determine whether it should be treated as malicious or not. Third, I will discuss ways in which attackers might attempt to thwart our efforts to build detectors. Specifically, I will talk about a fast and efficient clean-label dataset poisoning attack. In this attack, correctly labeled poison samples are injected into the training dataset. While these poison samples look legitimate to a human observer, they contain malicious characteristics that trigger a targeted misclassification during detection (inference).","PeriodicalId":164949,"journal":{"name":"Proceedings of the 2022 ACM Workshop on Information Hiding and Multimedia Security","volume":"65 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123606230","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