段昊彤
Employers on the program
- 2026腾讯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 |
|---|---|---|---|---|---|
| Aug 21, 2026 | AICon 全球人工智能开发与应用大会 | 深圳 | AICon 全球人工智能开发与应用大会 (AICon Global AI Development and Application Conference) | speaker | 以 AI 对抗 AI:构建越用越强的 Agent Runtime 安全防线 as 腾讯 Agent 正加速进入企业核心场景,但其自主规划、工具调用与数据访问能力,也让提示词注入、意图偏离、工具滥用、数据泄露等运行时的风险浮出水面。传统规则安全在语义化攻击与非确定性行为面前逐渐失效。本次演讲将从第一性原理出发,分享一套面向智能体时代的 Agent Runtime 安全方案——以 AI 对抗…Show lessAgent 正加速进入企业核心场景,但其自主规划、工具调用与数据访问能力,也让提示词注入、意图偏离、工具滥用、数据泄露等运行时的风险浮出水面。传统规则安全在语义化攻击与非确定性行为面前逐渐失效。本次演讲将从第一性原理出发,分享一套面向智能体时代的 Agent Runtime 安全方案——以 AI 对抗 AI,覆盖事前、事中、事后全链路,并依托真实生产数据实现能力的持续自迭代,让 Agent 的安全,越用越强。 演讲大纲 1. Agent 时代,传统安全为何失效 一个真实攻击链回顾 传统规则安全的困境 AI 原生安全第一性原理 2. Agent Runti… |
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.