OpenAI Links Model Reasoning Extraction Campaign to Moonshot AI
OpenAI says it disrupted a coordinated campaign that attempted to extract protected reasoning from its models, according to CNBC. The company linked a core cluster of the activity to people associated with Moonshot AI, the Chinese startup behind Kimi.
The activity began in early July and rose to 16,000 requests from more than 4,000 users over two days. OpenAI identified related activity across more than 15,000 users and said it had fully disrupted the campaign by July 28.
OpenAI described the method as adversarial distillation, in which operators use one model's outputs or reasoning to train or improve another model. The operators manipulated model interactions to expose hidden reasoning, but did not breach OpenAI's encryption, databases or stored user conversations.
The case follows Anthropic's report of distillation campaigns linked to Chinese AI companies, including Moonshot AI and Alibaba. OpenAI shared its findings with other developers through the Frontier Model Forum and with government information sharing channels. Moonshot AI did not immediately respond to a request for comment.
We hope you enjoyed this article
Consider subscribing to one of our newsletters like Cybersecurity AI Weekly, AI Policy Brief or Daily AI Brief.
Also, consider following us on social media:
More from Cybersecurity
Nov 19 Arizona opens criminal investigation into OpenAI over what it calls rogue AI agents in banks Nov 19 Citi tells customers they are on their own if third-party AI agents misuse their accounts Nov 18 Google releases Gemini 4 Neon, ranking first on a coding agent index at $3 per million input tokens Nov 18 Palo Alto Networks to buy Applied Compute for $4.5 billion to secure open-weight AI Nov 18 Rapid7 finds thousands of exposed Ollama servers, many already used by outsidersMore from AI Safety
Nov 19 US Catholic bishops form AI task force and push for guardrails and worker protections Nov 18 Nvidia scandal complicates US-China AI talks ahead of Trump-Xi meeting, Wired reports Nov 18 Beijing AI safety group Concordia AI briefed OpenAI staff on China's approach to AI risk Nov 18 OpenAI details how it contains frontier models, including a pause after a DNS exploit Nov 18 Coalition including Hugging Face and xAI co-founders says Anthropic "is not a safe AI company"Cybersecurity AI Weekly
Weekly newsletter about AI in Cybersecurity.
Whitepaper
Tensordyne Napier: What If One Rack Could Do the Work of Nine?
Tensordyne
This Tensordyne whitepaper presents Napier, an inference-focused AI processor and rack-scale system based on the company’s TDN Math logarithmic number system. It examines infrastructure requirements for large mixture-of-experts and agentic models, compares major inference architecture approaches, and details the TDN AIP processor, TDN72 pod, TDN Link fabric, and Napier Ultra configuration. The paper reports simulation-based performance, cost, and accuracy-validation results, including Tensordyne’s projected comparison of one Napier rack with a nine-rack Nvidia Rubin plus Groq deployment; the chip is reported as taped out and in fabrication.
Read moreYou may also like
Chinese labs use OpenAI model outputs to train domestic rivals, Reuters review finds
OpenAI embeds six Apollo Research evaluators to test whether models try to subvert safety controls
Beijing AI safety group Concordia AI briefed OpenAI staff on China's approach to AI risk
China's top open models were trained on export-banned Nvidia chips, research claims
OpenAI Expands Monitoring for Frontier Model Misalignment
Daily AI Brief: the AI news that matters, in your inbox.