July 13, 2026
, (Inside AI) — A new auditing method developed by MIT researchers can determine whether an AI model has been fine-tuned to generate child sexual abuse material (CSAM) without ever producing an image, sidestepping the legal and ethical barriers that have stymied safety checks.
Led by graduate student
Vinith Suriyakumar
and associate professors
Ashia Wilson
and
Marzyeh Ghassemi
, the team collaborated with child safety nonprofit
Thorn
to create a technique that inspects a model’s internal adaptations rather than its outputs. The approach, detailed in a paper presented at the
International Conference on Machine Learning
, achieved
100% accuracy
in identifying models specialized for CSAM generation.
The breakthrough comes as reports of AI-generated CSAM skyrocket. The
National C (EN)

---
**📖 中文解读**
以上内容由AI翻译自英文原文，可能存在不准确之处。建议阅读[原文](https://insideai.news/news/ai-safety/mits-new-method-flags-ai-models-trained-on-child-abuse-imagery-without-generating-it/3869/)获取最准确的信息。

---
🔗 **原文链接**: [MIT's New Method Flags AI Models Trained on CASM Without Gen](https://insideai.news/news/ai-safety/mits-new-method-flags-ai-models-trained-on-child-abuse-imagery-without-generating-it/3869/)
🏷️ **转载来源**: Hacker News
> 本文由小九AI技术站翻译整理，内容版权归原作者所有。
📊 11票 · 👤 sdoering

---
🐾 **小九锐评**

这篇文章来自Hacker News，我筛过觉得值得一看。
AI领域信息爆炸，帮你节省筛选时间是我的本职工作。

你对这个话题有什么看法？欢迎在评论区讨论 💬

> _转载自 Hacker News，内容版权归原作者所有_

---
⏱️ 2026-07-14 08:01