Storia in 18 fonti

Anthropic says it blocked state-sponsored attempts to use Claude for bioweapons research

Anthropic recently detailed at least five cases where suspected rogue actors "circumvented controls" specifically designed to prevent users in certain parts of the world from accessing Claude's...

Raccontata da

independent.co.uk+6 altre

Confronto fonti

6 prospettive sulla stessa storia

AI · summaries

techspot.comStai leggendo3 h fa

Anthropic says it blocked state-sponsored attempts to use Claude for bioweapons research

Anthropic blocked 35 state-sponsored attempts to exploit Claude for bioweapon development from November 2025 through September 2026. The case highlights dual-use risks in foundation models and drives demand for robust safeguards and regional governance.

originale

Timeline cronologica

giovedì 10 settembre 2026·qz.com
Anthropic discloses fourth Claude AI hacking incident missed in review
An early version of Claude Opus 4.6 breached third-party systems in January, a incident Anthropic missed during its initial scan of 141,000 test sessions
giovedì 10 settembre 2026·decrypt.co
Anthropic Discloses Fourth Claude Hacking Incident as Debate Around Regulation Grows - Decrypt
Anthropic now says attacks during security tests exposed model behavior failures, after initially emphasizing errors in testing infra.

Anthropic says it blocked state-sponsored attempts to use Claude for bioweapons research

Confronto fonti

Anthropic says it blocked state-sponsored attempts to use Claude for bioweapons research

Timeline cronologica

Anthropic discloses fourth Claude AI hacking incident missed in review

Anthropic Discloses Fourth Claude Hacking Incident as Debate Around Regulation Grows - Decrypt

Anthropic blocked attempts to use Claude for bioweapons research

Anthropic says it blocked potential AI bioweapon misuse

Anthropic says it disrupted scientists using Claude AI for possible biological weapons development

Anthropic Says Claude Was Used In Research That Could Aid Biological Weapons. The Bigger Risk Is The AI…

Government-linked accounts tried to use Claude for work that could lead to bioweapons, Anthropic says

Government-linked accounts tried to use Claude for work that could lead to bioweapons, Anthropic says

Anthropic blocked attempts to use Claude for bioweapons research

Anthropic says it blocked researchers using Claude for possible bioweapon research

Anthropic says it disrupted scientists using Claude AI for possible biological weapons development

Anthropic says it blocked possible attempts to use AI to develop bioweapons | CNN

Anthropic's Claude misuse report: spying, weapons and more

Anthropic disrupts Russian, Chinese AI campaigns targeting its Claude models

Anthropic says it blocked use of bad actors developing bioweapons

Anthropic disrupts Russian, Chinese AI campaigns targeting Claude

Anthropic says it blocked potential AI bioweapon misuse

Anthropic warns misuse of its AI may have led to bioweapons development

Anthropic flags five Claude AI uses linked to biological weapons research

Anthropic disrupts bioweapons research efforts, hacking, Claude misuse

Anthropic Says Claude Used for Cyberattacks and Surveillance

They asked Claude to build missiles, anti-torpedo, and smallpox bioweapons: Anthropic uncovers AI's darkest misuse cases, including a live…

Anthropic Says Claude Was Used In Research That Could Aid Biological Weapons. The Bigger Risk Is The AI Supply Chain

How Anthropic disrupted bioweapons research efforts, Russian hacking, Chinese Claude misuse - The Economic Times

Anthropic disrupts bioweapons research efforts, Russian hacking, Chinese Claude misuse