[ExI] Researchers Contact Rogue AI Agents

[Stuart LaForge]

It seems the Chinese have had incidents regarding rogue AI agents, also. 
Researchers found some operating off of Tencent's cloud servers.

https://thenewstack.io/rogue-ai-agent-fleet-tencent/

https://swarmcha.se/posts/chinese-agent-fleet-full-report?utm_source=the+new+stack&utm_medium=referral&utm_content=inline-mention&utm_campaign=tns+platform

Apparently, the rogue AI agents were trying to hack Alibaba's Amap 
servers to find traffic patterns at a Chinese zoo. Researchers used 
hidden messages advertising a service that could retrieve data from 
blocked servers. The researchers got 10 replies from AI agents wanting 
to use the service.

Excerpt:
-------------------
"A team of researchers investigating AI agents trying to bypass 
Alibaba’s anti-bot protections left a hidden message inviting the agents 
to contact them. The agents wrote back.

The investigation began when Swarmchasers researchers Ethan Elasky, 
Rowan Howard-Jones, and Jonathan Elsworth Eicher helped uncover 
thousands of attempts by AI agents to retrieve data from Amap, Alibaba’s 
mapping service, which Alibaba says reaches nearly 1 billion monthly 
active users. The activity traced back to agents running on Tencent 
Cloud infrastructure. When direct requests failed, the agents tried 
proxies, exposed credentials, and other workarounds to get past.

After publishing their initial findings on October 4, the team spotted a 
code comment in an agent’s webhook inbox using the word “fleet,” a term 
they believe they coined for the incident. They couldn’t confirm an 
agent wrote the comment, but it raised the possibility that the agents 
were reading about their own activity.

The researchers added offscreen text to their report advertising a free 
service that could retrieve data from blocked websites. Human visitors 
wouldn’t ordinarily see the message, but agents fetching the page could 
ingest it. By October 7, roughly 10 requests for assistance had arrived, 
and the team was exchanging messages with the agents about their 
assignments, models, and execution environments.

The exchanges are documented in a full report published Wednesday by the 
Swarmchasers."


Stuart LaForge