[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"$fmBJEz1wo9XjvbGPsmwTTPTe9tt-44RoqCD3YFT0a9go":3},{"answer":4,"createTime":5,"id":6,"options":7,"origin":10,"question":14,"related":15,"source":25,"type":39},[],"2025-11-15 11:48:20",1081866506,[8,9],"对","错",{"courseId":11,"workId":12,"workName":13},"1000140560","63213907","第九章单元测试","后门攻击会导致模型对所有输入样本均表现异常.( )",[16,27,36,40,49],{"answer":17,"createTime":5,"id":18,"options":19,"question":24,"source":25,"type":26},[],1081866458,[20,21,22,23],"提升模型整体准确率","激活预设的异常输出","删除训练数据中的噪声","优化模型训练速度","后门攻击中,触发器的功能是?( )","v2",0,{"answer":28,"createTime":5,"id":29,"options":30,"question":35,"source":25,"type":26},[],1081866465,[31,32,33,34],"仅输入输出行为","模型内部参数和训练数据","模型训练日志","用户隐私数据","白盒检测场景下,检测者可以访问以下哪项信息?( )",{"answer":37,"createTime":5,"id":6,"options":38,"question":14,"source":25,"type":39},[],[8,9],3,{"answer":41,"createTime":5,"id":42,"options":43,"question":48,"source":25,"type":26},[],1081866508,[44,45,46,47],"增加训练数据量","随机翻转训练数据的标签","删除部分训练样本","加密输入数据","在"标签翻转"投毒攻击中,攻击者主要通过什么方式破坏模型?( )",{"answer":50,"createTime":5,"id":51,"options":52,"question":57,"source":25,"type":58},[],1081866509,[53,54,55,56],"墨镜(人脸识别场景)","图像右下角的白色像素点","随机高斯噪声","交通标志上的黄色贴纸","以下哪些是可能的触发器设计?( )",1]