Translation in progress Some entries still include text in the original language.

腾讯 · News

AI Safety HOTOct 13 · Tuesday

arXivY

腾讯 · News

Latest publications and developments

Latest publications and developments

Search titles, summaries and full text/

腾讯

Research topics

Prompt injectionAgent safetyDeception and schemingReward hackingChain-of-thought monitoringInterpretabilityAI controlBackdoors and poisoning隐私与数据泄露Supply-chain securityDangerous capabilitiesAI 与网络攻防开源模型安全Red teaming

Companies and institutions

OpenAIAnthropicGoogle DeepMindGoogle ResearchGoogle 安全MetaxAIMicrosoftNVIDIADeepSeek阿里巴巴 · Qwen智谱 · GLM月之暗面 · Kimi字节跳动腾讯蚂蚁集团上海人工智能实验室UK AISIUS CAISIMETRApollo ResearchRedwood ResearchFAR.AIPalisade Research

Reports and frameworks

System CardFrontier safety frameworks

TimelineTrendingTodaySelected

腾讯 · News

Latest publications and developments

TimelineTrendingTodaySelected

腾讯

Research topics

Prompt injectionAgent safetyDeception and schemingReward hackingChain-of-thought monitoringInterpretabilityAI controlBackdoors and poisoning隐私与数据泄露Supply-chain securityDangerous capabilitiesAI 与网络攻防开源模型安全Red teaming

Companies and institutions

OpenAIAnthropicGoogle DeepMindGoogle ResearchGoogle 安全MetaxAIMicrosoftNVIDIADeepSeek阿里巴巴 · Qwen智谱 · GLM月之暗面 · Kimi字节跳动腾讯蚂蚁集团上海人工智能实验室UK AISIUS CAISIMETRApollo ResearchRedwood ResearchFAR.AIPalisade Research

Reports and frameworks

System CardFrontier safety frameworks

Jun 16, 2023Fri

Jun 16, 2023Friday · 1 items

1. 11:42
   雷峰网安全频道 · Jun 16, 2023 11:42Attention66

   AGI 大时代，企业安全为什么需要“新进化”？

   面对 AGI 时代攻击面扩大与生成式人工智能被用于编写攻击脚本、恶意软件和钓鱼邮件，雷峰网提出企业安全需从单点防御转向“数字安全免疫力”。腾讯安全与 IDC 于 6 月 13 日“数字安全免疫力研讨论坛”联合发布数据安全免疫力模型及《加强数字安全免疫力，促进数字化时代下的韧性发展》白皮书，强调前置投入、动态轻量实时响应，把安全融入战略、管理与运营流程。

Mar 26, 2023Sun

Mar 26, 2023Sunday · 1 items

1. 16:11
   雷峰网安全频道 · Mar 26, 2023 16:11Attention88

   专家解读《2023产业互联网安全十大趋势》：警惕 ChatGPT 隐形危机、数据泄露与勒索攻击风险

   腾讯安全、腾讯研究院等机构联合推出《2023产业互联网安全十大趋势》，将 ChatGPT 大模型带来的隐形危机列为趋势之一。编

You have reached the end