[{"data":1,"prerenderedAt":126},["ShallowReactive",2],{"content-query-LmZxaXDgmL":3},{"_path":4,"_dir":5,"_draft":6,"_partial":6,"_locale":7,"title":8,"description":9,"date":10,"cover":11,"type":12,"state":13,"body":14,"_type":120,"_id":121,"_source":122,"_file":123,"_stem":124,"_extension":125},"/activities/zh/3540","zh",false,"","倒计时2天！AI安全论坛与创新技术研讨会启幕，共探AI安全前沿！","AI安全论坛与创新技术研讨会即将开启！","2024-12-18","https://obs-mindspore-file.obs.cn-north-4.myhuaweicloud.com/file/2024/12/20/bc3b045461af4a538596e95269d9e34e.png","activities",1,{"type":15,"children":16,"toc":117},"root",[17,25,34,51,59,67,72,77,82,90,97,105,110],{"type":18,"tag":19,"props":20,"children":22},"element","h1",{"id":21},"倒计时2天ai安全论坛与创新技术研讨会启幕共探ai安全前沿",[23],{"type":24,"value":8},"text",{"type":18,"tag":26,"props":27,"children":28},"p",{},[29],{"type":18,"tag":30,"props":31,"children":32},"strong",{},[33],{"type":24,"value":9},{"type":18,"tag":26,"props":35,"children":36},{},[37,42,44,49],{"type":18,"tag":30,"props":38,"children":39},{},[40],{"type":24,"value":41},"AI安全论坛与创新技术研讨会",{"type":24,"value":43},"，将于本周五",{"type":18,"tag":30,"props":45,"children":46},{},[47],{"type":24,"value":48},"12月20日",{"type":24,"value":50},"正式开启。本次会议邀请了数十位来自学界、业界AI安全领域的重量级嘉宾，从AI安全技术发展、SIG发展方向、生态发展共创等角度展开技术分享和研讨。我们希望更多的开发者一起加入社区，共同开发、共同探索开源科学的未来。",{"type":18,"tag":26,"props":52,"children":53},{},[54],{"type":18,"tag":55,"props":56,"children":58},"img",{"alt":7,"src":57},"https://obs-mindspore-file.obs.cn-north-4.myhuaweicloud.com/file/2024/12/20/7ac37e992eec4534b0625d3922dce515.png",[],{"type":18,"tag":26,"props":60,"children":61},{},[62],{"type":18,"tag":30,"props":63,"children":64},{},[65],{"type":24,"value":66},"MindSpore Trusted AI",{"type":18,"tag":26,"props":68,"children":69},{},[70],{"type":24,"value":71},"MindSpore Trusted AI通过对抗鲁棒性、模型安全测试、差分隐私训练、隐私泄露风险评估、数据漂移检测等一系列先进的技术手段，为MindSpore的安全与隐私保护提供了全方位的保障。",{"type":18,"tag":26,"props":73,"children":74},{},[75],{"type":24,"value":76},"在对抗样本方面，MindSpore Trusted AI能够帮助安全工作人员快速高效地生成对抗样本，评测AI模型的鲁棒性，从而确保模型在面对恶意攻击时能够保持稳定和可靠。在隐私泄漏风险评估方面，通过成员推理攻击、模型逆向攻击等算法，我们能够对模型的隐私泄漏风险进行准确评估，为模型的隐私保护提供有力支持。",{"type":18,"tag":26,"props":78,"children":79},{},[80],{"type":24,"value":81},"在模型保护方面，MindSpore Trusted AI提供高性能并行加解密以及模型动态混淆能力，保障模型在传输、存储和运行过程中的安全性，防止模型被恶意窃取或篡改。",{"type":18,"tag":26,"props":83,"children":84},{},[85],{"type":18,"tag":30,"props":86,"children":87},{},[88],{"type":24,"value":89},"本次议程",{"type":18,"tag":26,"props":91,"children":92},{},[93],{"type":18,"tag":55,"props":94,"children":96},{"alt":7,"src":95},"https://obs-mindspore-file.obs.cn-north-4.myhuaweicloud.com/file/2024/12/20/ac34b7d137e14fffac346327aa8fce0b.png",[],{"type":18,"tag":26,"props":98,"children":99},{},[100],{"type":18,"tag":30,"props":101,"children":102},{},[103],{"type":24,"value":104},"活动亮点",{"type":18,"tag":26,"props":106,"children":107},{},[108],{"type":24,"value":109},"本次活动不仅有硬核干货分享，对话大咖机会，我们还为参与活动的同学准备了签到礼品和抽奖礼品，为开发者打造交流切磋、碰撞思想火花、共同携手进阶的绝佳平台。",{"type":18,"tag":26,"props":111,"children":112},{},[113],{"type":18,"tag":55,"props":114,"children":116},{"alt":7,"src":115},"https://obs-mindspore-file.obs.cn-north-4.myhuaweicloud.com/file/2024/12/20/c526101414524600bc06e9b56b28e164.png",[],{"title":7,"searchDepth":118,"depth":118,"links":119},4,[],"markdown","content:activities:zh:3540.md","content","activities/zh/3540.md","activities/zh/3540","md",1776506026709]