盛锦辰(幻猫)
Employers on the program
- 2026蚂蚁安全非攻实验室1 talk
Events1
Conferences1
Talks1
Years active2026
The year around now
Talks in the past 12 months and announced talks ahead, one row per conference, January to December. Hover a mark for the talk.
Appearances by year
- AICon 全球人工智能开发与应用大会 (AICon Global AI Development and Application Conference)
Talks
| Date | Event | Conference | Role | Title | Links |
|---|---|---|---|---|---|
| Jun 26, 2026 | AICon 全球人工智能开发与应用大会 | 上海 | AICon 全球人工智能开发与应用大会 (AICon Global AI Development and Application Conference) | speaker | 以模治模——支付宝 Agent 安全漏洞智能化检测实践 as 蚂蚁安全非攻实验室 2026 年,Agent 框架(OpenClaw 等)大规模走入企业生产,攻击面横跨模型、框架、运行环境三层——记忆投毒、工具滥用、身份越权、沙箱逃逸接踵而至,单层切片的传统检测工具已无法覆盖。支付宝的解法是用 Agent 检测 Agent。本演讲分享从「人工审计」走向「智能化自主检测」的生产实践:如何构建 Agent…Show less2026 年,Agent 框架(OpenClaw 等)大规模走入企业生产,攻击面横跨模型、框架、运行环境三层——记忆投毒、工具滥用、身份越权、沙箱逃逸接踵而至,单层切片的传统检测工具已无法覆盖。支付宝的解法是用 Agent 检测 Agent。本演讲分享从「人工审计」走向「智能化自主检测」的生产实践:如何构建 Agent 风险大图、如何构建漏洞检测 harness、如何让领域记忆驱动自进化、如何进行评测。 演讲提纲: 问题:Agent 攻击面横跨全栈,旧地图失灵 复合风险: 模型、框架、运行环境三层叠加,跨层级联放大攻击面 旧地图失灵: 从攻击路径系统性建… |
Frequent co-speakers
No one else spoke at two or more of the same events.
Speakers with the same name are merged into one entry, so this page may combine more than one person. Affiliations are shown as each conference listed them.