Prompt2Pwn 黑客大会两日后开幕:真实 AI 靶场 + 全场直播
rez0__ · x · 2026-11-19
Prompt2Pwn launches in two days in Oakland (Nov 20–21, 2026), where hackers work on real partner-supplied AI scopes with partner teams on site; talks stream worldwide.
The NahamCon lineup is heavily AI-security focused: Johann Rehberger on becoming an AI hacker and breaking frontier models, Ciarán Cotter on weird ways to hack Gemini, Zenity red teamer Mike Takahashi on a year of exfiltrating data from AI agents, plus talks on LLM-automated device hacking, hacking agents that don't get lost, and supply chain attacks in the AI era.
「安全」频道最新
- Palisade 的 AI 自我复制研究被指复现存在问题 — NathanpmYoung · 2026-11-19
- 今年最重要的可解释性成果,全靠开源模型才做成 — georgejrjrjr · 2026-11-19
- AI 安全研究者警告:圈层观点趋同快起飞论正在损害认知环境 — sayashk · 2026-11-19
- 英国 Turing 主权模型路线图曝光:可部署目标定在 2028 年末之后 — bclavie · 2026-11-19
- MIT 新方法让 AI 文本检测器在新模型与伪装文本面前保持鲁棒 — CurieuxExplorer · 2026-11-19
- Anthropic 内部现分歧:员工提议单方面暂停前沿训练,Dario 否决 — AndyMasley · 2026-11-19