AREOD:对抗性鲁棒性评估,用于目标检测

上传者: 42116585 | 上传时间: 2022-05-05 14:56:50 | 文件大小: 49KB | 文件类型: ZIP
AREOD 该存储库包含AREOD (用于对象检测的对抗鲁棒性评估)的代码,这是一个Python的库,用于进行对抗性机器学习研究,以正确地对标目标检测中的对抗性鲁棒性。 该存储库仍在开发中,我们使用3种针对对象检测模型的攻击来对逆向鲁棒性进行基准测试。 功能概述: 建立在tensorFlow上,并通过给定的接口支持TensorFlow和Kerasa模型 支持各种威胁模型中的多种攻击 提供现成的预训练基线模型(faster-rcnn-inception-v2-coco,多尺度GTRSB) 为bencmark模型提供方便的工具,并使用printor打印生成的对抗性样本 攻击方法清单 我们使用3种攻击方法生成对抗示例,下面的论文对此进行了介绍 , , ,。 稍后,我们使用连接的打印机将对抗性示例打印出来,以提供更高的性能基准。 安装 git clone https://github.c

文件下载

资源详情

[{"title":"( 42 个子文件 49KB ) AREOD:对抗性鲁棒性评估,用于目标检测","children":[{"title":"AREOD-master","children":[{"title":"setup.py <span style='color:#111;'> 684B </span>","children":null,"spread":false},{"title":".gitignore <span style='color:#111;'> 1.85KB </span>","children":null,"spread":false},{"title":"patches","children":[{"title":"object_detection_api.diff <span style='color:#111;'> 822B </span>","children":null,"spread":false},{"title":"lucid.diff <span style='color:#111;'> 5.59KB </span>","children":null,"spread":false}],"spread":true},{"title":"requirements.txt <span style='color:#111;'> 960B </span>","children":null,"spread":false},{"title":"LICENSE <span style='color:#111;'> 1.04KB </span>","children":null,"spread":false},{"title":"README.md <span style='color:#111;'> 3.14KB </span>","children":null,"spread":false},{"title":"example","children":[{"title":"faster_rcnn_inception_v2_coco.py <span style='color:#111;'> 14.79KB </span>","children":null,"spread":false},{"title":"multiscale.py <span style='color:#111;'> 3.99KB </span>","children":null,"spread":false}],"spread":true},{"title":"build.sh <span style='color:#111;'> 576B </span>","children":null,"spread":false},{"title":"areod","children":[{"title":"loss","children":[{"title":"__init__.py <span style='color:#111;'> 398B </span>","children":null,"spread":false},{"title":"base.py <span style='color:#111;'> 490B </span>","children":null,"spread":false},{"title":"cw.py <span style='color:#111;'> 4.09KB </span>","children":null,"spread":false},{"title":"cross_entropy.py <span style='color:#111;'> 3.48KB </span>","children":null,"spread":false}],"spread":true},{"title":"model","children":[{"title":"loader.py <span style='color:#111;'> 847B </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 75B </span>","children":null,"spread":false},{"title":"base.py <span style='color:#111;'> 10.06KB </span>","children":null,"spread":false}],"spread":true},{"title":"dataset","children":[{"title":"utils.py <span style='color:#111;'> 347B </span>","children":null,"spread":false},{"title":"GTSRB.py <span style='color:#111;'> 906B </span>","children":null,"spread":false}],"spread":true},{"title":"__init__.py <span style='color:#111;'> 133B </span>","children":null,"spread":false},{"title":"samples","children":[{"title":"loader.py <span style='color:#111;'> 527B </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 51B </span>","children":null,"spread":false},{"title":"shapeshifter_loader.py <span style='color:#111;'> 457B </span>","children":null,"spread":false},{"title":"darts_loader.py <span style='color:#111;'> 3.93KB </span>","children":null,"spread":false},{"title":"utils.py <span style='color:#111;'> 676B </span>","children":null,"spread":false}],"spread":false},{"title":"utils.py <span style='color:#111;'> 1.26KB </span>","children":null,"spread":false},{"title":"attack","children":[{"title":"__init__.py <span style='color:#111;'> 0B </span>","children":null,"spread":false},{"title":"darts_worker.py <span style='color:#111;'> 19.16KB </span>","children":null,"spread":false},{"title":"base.py <span style='color:#111;'> 3.88KB </span>","children":null,"spread":false},{"title":"shapeshifter2d.py <span style='color:#111;'> 423B </span>","children":null,"spread":false},{"title":"shapeshifter.py <span style='color:#111;'> 20.96KB </span>","children":null,"spread":false},{"title":"utils.py <span style='color:#111;'> 2.71KB </span>","children":null,"spread":false},{"title":"darts.py <span style='color:#111;'> 5.58KB </span>","children":null,"spread":false},{"title":"shapeshifter3d.py <span style='color:#111;'> 423B </span>","children":null,"spread":false}],"spread":false},{"title":"print","children":[{"title":"__init__.py <span style='color:#111;'> 0B </span>","children":null,"spread":false},{"title":"print_cli.py <span style='color:#111;'> 1.29KB </span>","children":null,"spread":false},{"title":"print.py <span style='color:#111;'> 2.92KB </span>","children":null,"spread":false}],"spread":false},{"title":"generator","children":[{"title":"__init__.py <span style='color:#111;'> 0B </span>","children":null,"spread":false},{"title":"utils.py <span style='color:#111;'> 5.50KB </span>","children":null,"spread":false},{"title":"benchmark_cli.py <span style='color:#111;'> 4.47KB </span>","children":null,"spread":false},{"title":"attack_cli.py <span style='color:#111;'> 5.41KB </span>","children":null,"spread":false},{"title":"attack.py <span style='color:#111;'> 4.60KB </span>","children":null,"spread":false}],"spread":false}],"spread":true}],"spread":true}],"spread":true}]

评论信息

免责申明

【只为小站】的资源来自网友分享,仅供学习研究,请务必在下载后24小时内给予删除,不得用于其他任何用途,否则后果自负。基于互联网的特殊性,【只为小站】 无法对用户传输的作品、信息、内容的权属或合法性、合规性、真实性、科学性、完整权、有效性等进行实质审查;无论 【只为小站】 经营者是否已进行审查,用户均应自行承担因其传输的作品、信息、内容而可能或已经产生的侵权或权属纠纷等法律责任。
本站所有资源不代表本站的观点或立场,基于网友分享,根据中国法律《信息网络传播权保护条例》第二十二条之规定,若资源存在侵权或相关问题请联系本站客服人员,zhiweidada#qq.com,请把#换成@,本站将给予最大的支持与配合,做到及时反馈和处理。关于更多版权及免责申明参见 版权及免责申明