hiw3c 日报精选
The Decoder 网页快照

OpenAI 让攻击者更难提取其最新 AI 模型是如何思考的

原文标题 · OpenAI makes it much harder for attackers to extract how its latest AI models think

OpenAI已显著加强了对从GPT-6.2 Astra和GPT-6.2 Sol中提取内部推理的防护措施。在自适应红队测试中,提取受保护推理的成功率从54%降至0.2%。该公司还每周因协同蒸馏活动暂停数千至数万个账户。文章《OpenAI让攻击者更难提取其最新AI模型的思考方式》最早发表于The Decoder。

来源:The Decoder · the-decoder.com

正文为英文,可一键机器翻译(仅首次需要等待)

OpenAI makes it much harder for attackers to extract how its latest AI models think

OpenAI has sharply tightened safeguards against extracting internal reasoning from GPT-6.2 Astra and GPT-6.2 Sol. In internal automated tests, attacks pulling protected reasoning from prior requests dropped from a 54.0 percent success rate on GPT-6 Astra to 0.2 percent on GPT-6.2 Astra. Attacks on active requests fell from 22.9 to 0.9 percent, OpenAI says . The company is now bringing selected improvements to GPT-6 Astra, too.

The defenses work on two levels. For individual requests, the systems combine targeted training, input and output filters for messages and tool calls, and API blocks that stop older models from reading protected reasoning. Against coordinated campaigns, OpenAI bans thousands to tens of thousands of accounts weekly.

Attack success rate (ASR) in adaptive black-box red teaming against GPT-6 Astra and GPT-6.2 Astra, aggregated across six attacker models. Lower is better. Ad

Anthropic is fighting systematic distillation attacks as well , also banning tens of thousands of accounts to curb the theft of internal reasoning, reportedly succeeding in 90 to 99 percent of cases. Anthropic has also called for a coordinated response from industry and policymakers . Ad

AI News Without the Hype – Curated by Humans

Every Plus article and the full archive

Frontier Radar: 6 deep dives a year

Ask a question about the article or an AI topic. You can ask follow-up questions.