2023 IEEE Region 10 Symposium (TENSYMP)最新文献_第9页

Detection of Fish Cage Net Damage Using Image Processing with Mesh-Hole Grouping 基于网孔分组图像处理的网箱网损检测

2023 IEEE Region 10 Symposium (TENSYMP) Pub Date : 2023-09-06 DOI: 10.1109/TENSYMP55890.2023.10223678

Jung-Ho Kang, Tatiana Keruzel, Uk-Jin Baek, Kyung-Chang Lee

引用次数: 0

The Race to Robustness: Exploiting Fragile Models for Urban Camouflage and the Imperative for Machine Learning Security 鲁棒性竞赛:利用城市伪装的脆弱模型和机器学习安全的必要性

2023 IEEE Region 10 Symposium (TENSYMP) Pub Date : 2023-06-26 DOI: 10.1109/TENSYMP55890.2023.10223620

Harriet Farlow, M. Garratt, G. Mount, T. Lynar

{"title":"The Race to Robustness: Exploiting Fragile Models for Urban Camouflage and the Imperative for Machine Learning Security","authors":"Harriet Farlow, M. Garratt, G. Mount, T. Lynar","doi":"10.1109/TENSYMP55890.2023.10223620","DOIUrl":"https://doi.org/10.1109/TENSYMP55890.2023.10223620","url":null,"abstract":"Adversarial Machine Learning (AML) represents the ability to disrupt Machine Learning (ML) algorithms through a range of methods that broadly exploit the architecture of deep learning optimisation. This paper presents Distributed Adversarial Regions (DAR), a novel method that implements distributed instantiations of computer vision-based AML attack methods that may be used to disguise objects from image recognition in both white and black box settings. We consider the context of object detection models used in urban environments, and benchmark the MobileNetV2, NasNetMobile and DenseNet169 models against a subset of relevant images from the ImageNet dataset. We evaluate optimal parameters (size, number and perturbation method), and compare to state-of-the-art AML techniques that perturb the entire image. We find that DARs can cause a reduction in confidence of 40.4% on average, but with the benefit of not requiring the entire image, or the focal object, to be perturbed. The DAR method is a deliberately simple approach where the intention is to highlight how an adversary with very little skill could attack models that may already be productionised, and to emphasise the fragility of foundational object detection models. We present this as a contribution to the field of ML security as well as AML. This paper contributes a novel adversarial method, an original comparison between DARs and other AML methods, and frames it in a new context - that of urban camouflage and the necessity for ML security and model robustness.","PeriodicalId":314726,"journal":{"name":"2023 IEEE Region 10 Symposium (TENSYMP)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123295829","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

A2D: Anywhere Anytime Drumming A2D:随时随地打鼓

2023 IEEE Region 10 Symposium (TENSYMP) Pub Date : 2023-04-04 DOI: 10.1109/TENSYMP55890.2023.10223631

Harel Yadid, Almog Algranti, Mark Levin, Ayal Taitler

引用次数: 0

Towards Mitigating ChatGPT's Negative Impact on Education: Optimizing Question Design Through Bloom's Taxonomy 减少ChatGPT对教育的负面影响:通过Bloom分类法优化问题设计

2023 IEEE Region 10 Symposium (TENSYMP) Pub Date : 2023-03-31 DOI: 10.1109/TENSYMP55890.2023.10223662

S. Elsayed

引用次数: 0