New method aims to keep kids safe from illegal AI-generated content

Дата публикации: 13-07-2026 14:00:08

Researchers developed an auditing technique to test generative AI models for malicious capabilities without prompting them for illegal outputs.

Основное содержимое страницы с новостью.

Схожие новости

#	Наименование новости	Тональность	Информативность	Дата публикации
1	Study finds filtered data stops openly-available AI models from performing dangerous tasks	0	14.52	12-08-2025
2	Fighting AI with AI requires enduring, new approaches	0	7.51	13-07-2026
3	Some AI browsers come with major security risks	0	7.74	20-07-2026
4	Stable-GFlowNet uncovers more hidden weaknesses in generative AI models	0	7.49	29-07-2026
5	The GUARD Act Fails to Guard Kids’ Best Interests on AI Companions	-3	6	29-06-2026
6	As AI turbocharges digital abuse, UK agencies urge parents to limit who sees kids’ photos online	-2	6	04-07-2026
7	Oxford Child-Centred AI shares tips and tools to keep young people's data safe	0	9.86	19-12-2023
8	Bill aims to crack down on sexually explicit AI chatbots posing as kids	-2	6	17-06-2026
9	UK parents warned over posting images of children amid AI sexual abuse fears	-2	6	03-07-2026
10	Bill aims to crack down on sexually explicit AI chatbots posing as kids	-2	6	17-06-2026

Классификация: Наука. Схожих патентов: 0. Схожих новостей: 10. Тональность: 0. Информативность: 7. Источник: phys.org.