Proceedings of the 2023 Secure and Trustworthy Deep Learning Systems Workshop最新文献

Toward Evaluating the Robustness of Deep Learning Based Rain Removal Algorithm in Autonomous Driving 基于深度学习的自动驾驶除雨算法鲁棒性评估

Proceedings of the 2023 Secure and Trustworthy Deep Learning Systems Workshop Pub Date : 2023-07-10 DOI: 10.1145/3591197.3591309

Yiming Qin, Jincheng Hu, Bang Wu

{"title":"Toward Evaluating the Robustness of Deep Learning Based Rain Removal Algorithm in Autonomous Driving","authors":"Yiming Qin, Jincheng Hu, Bang Wu","doi":"10.1145/3591197.3591309","DOIUrl":"https://doi.org/10.1145/3591197.3591309","url":null,"abstract":"Autonomous driving systems have been widely adopted by automobile manufacturers, ushering in a new era of intelligent transportation. While adverse weather conditions continue to pose a significant challenge to its commercial application, as they can impact sensor data, degrade the quality of image transmission, and pose safety risks. Using neural network models to remove rain has shown significant promise in addressing this problem. The learning-based rain-removal algorithm discovers the deep connection between rainy pictures and non-rainy pictures by mining the information on raindrops and rain patterns. Nevertheless, the robustness of these rain removal algorithms was not considered, which poses a threat to autonomous vehicles. In this paper, we propose an optimized CW adversarial sample attack to explore the robustness of the rain removal algorithm. In our attacks, we generate a perturbation index of structural similarity that is difficult to detect through human vision and image pixel analysis, causing the similarity and image quality of the restored scene to be significantly degraded. To validate the realistic attack potential of the proposed method, a pre-trained State-of-the-art rain removal attack algorithm, RainCCN, is used as a potential victim of the proposed attack method. We demonstrate the effectiveness of our approach against a state-of-the-art rain removal algorithm, RainCCN, and show that we can reduce PSNR by 39.5 and SSIM by 26.4.","PeriodicalId":128846,"journal":{"name":"Proceedings of the 2023 Secure and Trustworthy Deep Learning Systems Workshop","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132046290","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

A First Look at the Security of EEG-based Systems and Intelligent Algorithms under Physical Signal Injections 物理信号注入下基于脑电图的系统和智能算法的安全性初探

Proceedings of the 2023 Secure and Trustworthy Deep Learning Systems Workshop Pub Date : 2023-07-10 DOI: 10.1145/3591197.3591304

Md Imran Hossen, Yazhou Tu, X. Hei

引用次数: 2

Membership Inference Vulnerabilities in Peer-to-Peer Federated Learning 点对点联邦学习中的成员推理漏洞

Proceedings of the 2023 Secure and Trustworthy Deep Learning Systems Workshop Pub Date : 2023-07-10 DOI: 10.1145/3591197.3593638

Alka Luqman, A. Chattopadhyay, Kwok-Yan Lam

引用次数: 0

Privacy-Enhanced Knowledge Transfer with Collaborative Split Learning over Teacher Ensembles 基于教师团队的协作式分割学习的隐私增强知识转移

Proceedings of the 2023 Secure and Trustworthy Deep Learning Systems Workshop Pub Date : 2023-07-10 DOI: 10.1145/3591197.3591303

Ziyao Liu, Jiale Guo, Mengmeng Yang, Wenzhuo Yang, Jiani Fan, Kwok-Yan Lam

{"title":"Privacy-Enhanced Knowledge Transfer with Collaborative Split Learning over Teacher Ensembles","authors":"Ziyao Liu, Jiale Guo, Mengmeng Yang, Wenzhuo Yang, Jiani Fan, Kwok-Yan Lam","doi":"10.1145/3591197.3591303","DOIUrl":"https://doi.org/10.1145/3591197.3591303","url":null,"abstract":"Knowledge Transfer has received much attention for its ability to transfer knowledge, rather than data, from one application task to another. In order to comply with the stringent data privacy regulations, privacy-preserving knowledge transfer is highly desirable. The Private Aggregation of Teacher Ensembles (PATE) scheme is one promising approach to address this privacy concern while supporting knowledge transfer from an ensemble of \"teacher\" models to a \"student\" model under the coordination of an aggregator. To further protect the data privacy of the student node, the privacy-enhanced version of PATE makes use of cryptographic techniques at the expense of heavy computation overheads at the teacher nodes. However, this inevitably hinders the adoption of knowledge transfer due to the highly disparate computational capability of teachers. Besides, in real-life systems, participating teachers may drop out of the system at any time, which causes new security risks for adopted cryptographic building blocks. Thus, it is desirable to devise privacy-enhanced knowledge transfer that can run on teacher nodes with relatively fewer computational resources and can preserve privacy with dropped teacher nodes. In this connection, we propose a dropout-resilient and privacy-enhanced knowledge transfer scheme, Collaborative Split learning over Teacher Ensembles (CSTE), that supports the participating teacher nodes to train and infer their local models using split learning. CSTE not only allows the compute-intensive processing to be performed at a split learning server, but also protects the data privacy of teacher nodes from collusion between the student node and aggregator. Experimental results showed that CSTE achieves significant efficiency improvement from existing schemes.","PeriodicalId":128846,"journal":{"name":"Proceedings of the 2023 Secure and Trustworthy Deep Learning Systems Workshop","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131420988","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

Multi-class Detection for Off The Shelf transfer-based Black Box Attacks 基于传输的黑盒攻击多类检测

Proceedings of the 2023 Secure and Trustworthy Deep Learning Systems Workshop Pub Date : 2023-07-10 DOI: 10.1145/3591197.3591305

Niklas Bunzel, Dominic Böringer

引用次数: 0

Energy-Latency Attacks to On-Device Neural Networks via Sponge Poisoning 通过海绵中毒对设备上神经网络的能量延迟攻击

Proceedings of the 2023 Secure and Trustworthy Deep Learning Systems Workshop Pub Date : 2023-05-06 DOI: 10.1145/3591197.3591307

Zijian Wang, Shuo Huang, Yu-Jen Huang, Helei Cui

{"title":"Energy-Latency Attacks to On-Device Neural Networks via Sponge Poisoning","authors":"Zijian Wang, Shuo Huang, Yu-Jen Huang, Helei Cui","doi":"10.1145/3591197.3591307","DOIUrl":"https://doi.org/10.1145/3591197.3591307","url":null,"abstract":"In recent years, on-device deep learning has gained attention as a means of developing affordable deep learning applications for mobile devices. However, on-device models are constrained by limited energy and computation resources. In the mean time, a poisoning attack known as sponge poisoning has been developed.This attack involves feeding the model with poisoned examples to increase the energy consumption during inference. As previous work is focusing on server hardware accelerators, in this work, we extend the sponge poisoning attack to an on-device scenario to evaluate the vulnerability of mobile device processors. We present an on-device sponge poisoning attack pipeline to simulate the streaming and consistent inference scenario to bridge the knowledge gap in the on-device setting. Our exclusive experimental analysis with processors and on-device networks shows that sponge poisoning attacks can effectively pollute the modern processor with its built-in accelerator. We analyze the impact of different factors in the sponge poisoning algorithm and highlight the need for improved defense mechanisms to prevent such attacks on on-device deep learning applications.","PeriodicalId":128846,"journal":{"name":"Proceedings of the 2023 Secure and Trustworthy Deep Learning Systems Workshop","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128332516","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

Privacy-Preserving Distributed Machine Learning Made Faster 保护隐私的分布式机器学习变得更快

Proceedings of the 2023 Secure and Trustworthy Deep Learning Systems Workshop Pub Date : 2022-05-12 DOI: 10.1145/3591197.3591306

Z. L. Jiang, Jiajing Gu, Hongxiao Wang, Yulin Wu, Jun-bin Fang, S. Yiu, Wenjian Luo, Xuan Wang

{"title":"Privacy-Preserving Distributed Machine Learning Made Faster","authors":"Z. L. Jiang, Jiajing Gu, Hongxiao Wang, Yulin Wu, Jun-bin Fang, S. Yiu, Wenjian Luo, Xuan Wang","doi":"10.1145/3591197.3591306","DOIUrl":"https://doi.org/10.1145/3591197.3591306","url":null,"abstract":"With the development of machine learning, it is difficult for a single server to process all the data. So machine learning tasks need to be spread across multiple servers, turning the centralized machine learning into a distributed one. Multi-key homomorphic encryption is one of the suitable candidates to solve the problem. However, the most recent result of the Multi-key homomorphic encryption scheme (MKTFHE) only supports the NAND gate. Although it is Turing complete, it requires efficient encapsulation of the NAND gate to further support mathematical calculation. This paper designs and implements a series of operations on positive and negative integers accurately. First, we design basic bootstrapped gates, the efficiency of which is times that the number of using NAND to build. Second, we construct practical k-bit complement mathematical operators based on our basic binary bootstrapped gates. The constructed created can perform addition, subtraction, multiplication, and division on both positive and negative integers. Finally, we demonstrated the generality of the designed operators by achieving a distributed privacy-preserving machine learning algorithm, i.e. linear regression with two different solutions. Experiments show that the consumption time of the operators built with our gate is about 50 ∼ 70% shorter than built directly with NAND gate and the iteration time of linear regression with our gates is 66.7% shorter than with NAND gate directly.","PeriodicalId":128846,"journal":{"name":"Proceedings of the 2023 Secure and Trustworthy Deep Learning Systems Workshop","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128513933","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

Proceedings of the 2023 Secure and Trustworthy Deep Learning Systems Workshop 2023安全与可信赖深度学习系统研讨会论文集

Proceedings of the 2023 Secure and Trustworthy Deep Learning Systems Workshop Pub Date : 1900-01-01 DOI: 10.1145/3591197

引用次数: 0