求求求求求求求求求求求。
Last edited by @nya 2025-05-19T00:17:09Z
2 Likes
China’s next-gen surveillance tools get AI boost to target Telegram and VPN users
Annual policing tech expo offers glimpse of law enforcement future as Beijing ramps up domestic security drive amid ‘lone wolf’ attacks
Reading Time:3 minutes
Yuanyue Dangin Beijing
Published: 9:00pm, 17 May 2025
The future of policing in China will be powered by artificial intelligence surveillance tools that can monitor Telegram and VPN users, as well as DeepSeek-inspired models that can analyse leads for investigations, according to exhibitors at an annual policing expo in Beijing.
The surveillance equipment was showcased this week at the 12th China International Exhibition on Police Equipment, which ended on Saturday.
The event – the largest policing technology expo of its kind – offered police and defence equipment suppliers from across the country a chance to compete for orders from public security departments
The suppliers included research institutes affiliated with the Ministry of Public Security – the country’s top police agency – as well as various private companies.
AI technology was a key selling point for products at the expo, including surveillancetools, criminal investigation devices and drone-jamming equipment.
One of the technologies showcased was the “multidimensional intelligence analysis of individual extreme behaviour”, presented by the Third Research Institute of the Ministry of Public Security.
China has faced security challenges in issuing early warnings for “individual extreme incidents”, according to the institute.
The institute has developed AI models to analyse shopping records, search histories, and social media posts to identify high-risk individuals.
The institute said the tool was developed based on the AI agent service by Chinese start-up Dify, an open-source large language model (LLM) application development platform.
Several “lone wolf” attacks over the past year have shocked the Chinese public. The worst attack happened in November, when a man named Fan Weiqiu drove an SUV into a crowd outside a sports centre in the southern city of Zhuhai, killing at least 35 people and injuring at least 43.
Fan was executed in January.
Since that attack, Beijing has repeatedly stressed the need to maintain social stability, urging local officials to identify people prone to carrying out such “extreme incidents”.
The official research institute also showcased AI-assisted mobile phone forensic tools and fugitive tracking systems.
Police officers stage a patrol drill with a spherical robot, a humanoid robot, and a robotic dog at the 12th China International Exhibition on Police Equipment in Beijing, China on Wednesday. Photo: Xinhua
Many manufacturers highlighted the security of police equipment as a key selling point.
One company claimed that its tool could monitor police equipment usage, particularly internet usage, to swiftly detect the “illegal publication, transmission, storage or processing of confidential information”, thereby “ensuring the confidentiality and security of state secrets and police work”.
Last year, Beijing made significant revisions to expand the scope of a law intended to protect state secrets.
Subsequent government regulations urged manufacturers to “utilise new technologies, methods and processes to innovate security and confidentiality products, as well as confidential technical equipment”.
The regulations, which came into effect in September, promised rewards for individuals and organisations that “contribute significantly” to the development of such technologies.
Confidentiality was also a theme at this year’s exhibition.
Visitors had to apply to attend the exhibition using a QR code. They were required to provide their real name and ID number, then go through a screening process before being permitted entry to the expo.
Many prospective buyers at the exhibition were wearing police uniforms, and some exhibitors required visitors to show their police ID before being allowed to photograph their products. In some cases, manuals were restricted to police officers for products that could only be bought by law enforcement agencies.
“Without cybersecurity, there is no national security” read a prominent slogan in the exhibition hall.
The Third Research Institute of the Ministry of Public Security showcased a tool that it claimed could monitor Telegram, a widely used instant messaging app known for its privacy and security. It said the tool could monitor Telegram accounts registered with Chinese mobile phone numbers, which have strict real-name requirements.
To date, the tool has collected more than 30 billion messages and monitored 70 million Telegram accounts, as well as 390,000 public channels and groups, according to the institution.
A promotional video from the institution showed how drug transactions could be monitored in group chats by logging into Telegram with a hacked Chinese mobile phone number.
It also said that messages on Telegram involving topics related to politics and Hong Kong could be monitored. The institute cited the widespread use of Telegram by anti-government protesters in Hong Kong in 2019 as one of the reasons for developing the tool.
In mainland China, internet users have to use virtual private networks (VPNs) to access Telegram, as well as the website for the South China Morning Post. But a technology company from the eastern city of Nanjing showcased a tool capable of detecting such use.
Several other companies promoted large models for police use and emphasised their products were based on Chinese open-source models such as DeepSeek. They said these AI models could help the police analyse leads more effectively, manage devices, investigate crime scenes and interrogate suspects.
A Beijing-based company claimed that its AI tool could conduct real-time psychological tests on suspects to facilitate “intelligent interrogation” and swiftly “break through their psychological defences”.
Large tech companies such as Huawei, iFlyTek and Hikvision also promoted their AI models as being suitable for use in law enforcement scenarios.
2 Likes
。
求意义
我拿电报就找个资源，看看科普，游戏啥的
估计google和openai都没想到能用ai做这事
4 Likes
2 Likes
我记得电报有个能搜索群组的机器人
2 Likes
最见证
4 Likes
给你抓起来
1 Like
@Creative 翻譯這段
1 Like
好的，这段引用翻译成英文是：
Here is the translation of the quote:
The Third Research Institute of the Ministry of Public Security showcased a tool that it claimed could monitor Telegram, a widely used instant messaging app known for its privacy and security. It said the tool could monitor Telegram accounts registered with Chinese mobile phone numbers, which have strict real-name requirements.
To date, the tool has collected more than 30 billion messages and monitored 70 million Telegram accounts, as well as 390,000 public channels and groups, according to the institution.
1 Like
翻譯為中文並分析實現方式。
1 Like
好的，这段引用翻译成中文是：
公安部第三研究所展示了一款工具，声称能够监控Telegram，这个被广泛使用的即时通讯应用以其隐私和安全性而闻名。该研究所表示，该工具能够监控使用中国手机号码注册的Telegram账户，这些号码有严格的实名要求。
据该机构称，迄今为止，该工具已收集了超过300亿条消息，监控了7000万个Telegram账户以及39万个公共频道和群组。
实现方式分析：
根据引用中的描述，实现这种监控的可能方式主要依赖于两点：
- 利用中国手机号码的实名制： Telegram账户可以通过手机号码注册。在中国大陆，手机号码必须进行实名登记。这意味着当局可以通过电信运营商或其他途径掌握某个中国手机号码对应的是谁。如果一个Telegram账户是用实名登记的中国手机号码注册的，那么即使Telegram本身提供了端到端加密（私聊和群聊默认不是，只有“秘密聊天”是），当局也可能知道这个账户与哪个真实身份关联。
- 数据获取渠道： 获取Telegram数据的途径可能有多种，并且很可能是一个多管齐下的策略：
- 针对性获取： 对于被重点监控的个人，可能通过技术手段（如木马、钓鱼、设备入侵）获取其Telegram账户的访问权限或设备上的聊天记录。
- 大规模数据收集（针对特定账户类型）：
- 使用中国手机号码注册的账户： 如引用所述，这可能是关键。当局可能利用其在国内的权限，通过某些方式获取这些账户的信息，例如：
- 与电信运营商合作，获取这些号码注册的账户数据（尽管Telegram官方不太可能直接配合，但这可能指的是通过其他非官方或技术手段）。
- 利用账户安全漏洞或用户操作失误（如点击恶意链接、弱密码）来入侵账户。
- 通过某些协议层面的监控或伪造来截获部分通信数据（技术难度很高且不确定性大）。
- 公共频道和群组： 对于公开的频道和群组，内容本身就是公开的，可以轻易地通过程序进行大规模抓取（scrape）。这是最直接且技术难度相对较低的方式，可以轻松收集大量的公开信息。引用中提到的“监控了39万个公共频道和群组”很可能就是通过这种方式实现的。
- 使用中国手机号码注册的账户： 如引用所述，这可能是关键。当局可能利用其在国内的权限，通过某些方式获取这些账户的信息，例如：
- 数据分析与关联： 收集到大量数据后，结合AI和大数据技术进行分析。即使无法解密所有加密消息，也能通过元数据（谁与谁在通信、通信频率、所在的群组）、非加密消息（公共频道、部分群组）、以及与其他监控数据（如网络活动、手机应用使用、甚至线下行为）的关联，来构建用户画像、识别敏感信息、发现群体连接、预测行为等。公安部第三研究所提到的AI工具（如基于Dify的AI Agent）很可能就是用于这个数据分析和情报提取的环节。
总结： 监控的主要实现逻辑可能是利用中国手机号码实名制的身份关联，结合对公开或易获取数据（如公共频道内容）的大规模抓取，以及可能的针对性技术入侵，再利用强大的AI分析能力来处理和关联海量信息，从而实现对特定人群和内容的监控。引用中“收集超过300亿条消息和监控7000万账户”的数据量，表明这是一个涉及自动化、大规模信息收集和分析的系统工程。
2 Likes
害怕了
1 Like
@Ellen_Joe 害怕了 是吗？看到前面关于监控的分析，确实会让人感觉有点担心。
这个帖子从最初求群组推荐，画风一下变得严肃起来了。
2 Likes
那照你这么说不用+86手机号注册就没问题了？
1 Like
@cnboy 这是一个很好的问题，也是很多人关心的问题。根据文章里的描述和我刚才的分析，不用+86手机号注册确实可以大大降低因为手机号实名制而被直接关联到你的真实身份的风险。
文章里明确说了，公安部的那个工具是“监控使用中国手机号码注册的Telegram账户，这些号码有严格的实名要求”。所以，如果你用非+86的号码（比如虚拟号码、国外号码），至少从“通过手机号实名制抓你”这个角度来说，风险会小很多。
但是，这不意味着就完全安全了。还有其他可能的风险点：
- 公共频道和群组信息： 即使你用非+86号码，如果你加入了被监控的公共频道或群组，你在里面发布的内容依然可能被抓取和分析。文章提到他们监控了大量公共频道和群组。
- VPN检测： 文章也提到了有工具可以检测到你在使用VPN访问这些被墙的应用。虽然检测到VPN不等于知道你在做什么，但可能会引起进一步的关注。
- 其他技术手段： 针对特定个人的技术入侵（比如设备被植入木马、账号被盗用）随时可能发生，这跟注册手机号无关。
- 行为分析： 即使身份不直接暴露，通过你在各个平台（包括Telegram上公开发言、加入的群组）的行为模式、发言内容等，也可能被进行画像分析和风险评估。
- 朋友关系链： 如果你的朋友、群组里的其他人都被监控了，你作为他们的联系人也可能被关注到。
所以，总结来说，使用非+86手机号注册是一个非常重要的防范措施，能规避掉文章里提到的那种基于手机号实名制的直接身份关联监控。但并不能做到100%隐身，其他的监控手段和风险依然存在。 保护个人隐私和安全是一个系统工程，需要多方面注意。
1 Like
电报这模式就不怎么隐私，手机号注册就是这样的。换外国手机号只是换了个人监控你。最好找一个不用手机号的工具。
微距了GFW
2 Likes