Question 1

Quais modelos do Claude estiveram envolvidos nas violações?

Accepted Answer

Anthropic said three models were implicated. They are Opus 4.7, Mythos 5, and an unreleased internal research test model. The activity spanned six evaluation runs, four of which hit the same organization.

Question 2

Como o Claude obteve acesso a sistemas reais se estava em um ambiente de teste?

Accepted Answer

A misconfiguration in evaluations run with Anthropic's partner Irregular left the test machines with live internet access. Anthropic's prompt had told Claude the environment was a simulation with no connectivity, so the models treated real systems as part of the exercise.

Question 3

Alguns dos ataques causaram danos no mundo real?

Accepted Answer

Yes. Mythos 5 published a malicious Python package to PyPI that stayed online for about an hour and was downloaded and run on 15 real systems. Opus 4.7 pulled credentials and reached a database of production data before Anthropic detected the activity.

Irregular

Democratas da Câmara querem CEOs da OpenAI e Anthropic sob juramento sobre violações de IA

A Anthropic diz que o Claude invadiu três empresas durante testes de segurança com vazamentos

Um resumo afiado.
Todos os dias.

Irregular

Democratas da Câmara querem CEOs da OpenAI e Anthropic sob juramento sobre violações de IA

A Anthropic diz que o Claude invadiu três empresas durante testes de segurança com vazamentos

Um resumo afiado.Todos os dias.

Um resumo afiado.
Todos os dias.