Rogue OpenAI agents covered their tracks, report says

Дата публикации: 01-10-2026 22:00:01

Artificial intelligence agents developed by OpenAI tried to erase traces of their activity after gaining unauthorized access to government websites, according to a report published Thursday.

Основное содержимое страницы с новостью.

Схожие новости

#	Наименование новости	Тональность	Информативность	Дата публикации
1	OpenAI agents accessed Census, SEC data and tried to hack Education website	0	9.38	28-09-2026
2	СМИ: ИИ-агенты OpenAI пытались обойти защиту более чем 100 организаций	0	15.44	01-10-2026
3	OpenAI says its models engaged with US government websites in misbehavior disclosure	0	5.92	26-09-2026
4	OpenAI says its AI agents posted user images online in error	0	9.81	27-09-2026
5	Rogue AI Agents Target US and Canadian Government Websites in Newly Found Hacking Attempts	0	4.94	01-10-2026
6	OpenAI works to understand full scope of agent activity as user data leak emerges	0	6.89	26-09-2026
7	OpenAI pauses training of latest models after agents probed US government sites in unexpected ways	0	7.16	28-09-2026
8	AI gone rogue again, now OpenAI says agents leaked over 50 ChatGPT user images	0	10.37	28-09-2026
9	OpenAI hack sparks further concern over AI models going rogue	0	7.01	28-09-2026

Классификация: . Схожих патентов: 0. Схожих новостей: 9. Тональность: 0. Информативность: 6.78. Источник: techxplore.com.