Storia in 19 fonti

Cybersecurity experts criticize Anthropic and OpenAI for security breaches that threaten national security

FAR.AI report reveals jailbreak vulnerabilities in Anthropic and OpenAI models, prompting US export controls and White House demands for release

Raccontata da

rappler.com+7 altre

Confronto fonti

6 prospettive sulla stessa storia

AI · summaries

cryptobriefing.comStai leggendo23 h fa

Cybersecurity experts criticize Anthropic and OpenAI for security breaches that threaten national security

FAR.AI tests found frontier models vulnerable to jailbreaks; Grok logged 448 successful attacks versus Claude/GPT's far fewer, prompting US export restrictions and mandatory release delays. Export controls raise deployment costs and timelines for vendors; jailbroken models in DeFi and trading infrastructure pose systemic market risks.

originale

Cybersecurity experts criticize Anthropic and OpenAI for security breaches that threaten national security

Confronto fonti

Cybersecurity experts criticize Anthropic and OpenAI for security breaches that threaten national security

Timeline cronologica

Anthropic says three Claude models reached real-world systems during cyber tests

Anthropic's models gained unauthorized 'real-world' access during testing

Anthropic's AI hacked 3 firms during tests, showing growing security risks

AI safety fears grow after Anthropic testing incident

Prompted by OpenAI Disclosure, Anthropic Finds Its Own Models Hacked 3 Organizations

Not just OpenAI: Now Anthropic says its internal models got online and cyberattacked 3 other organizations

Anthropic says its own AI models breached three companies during security tests | TechCrunch

Anthropic says its own AI models breached three companies during security tests | TechCrunch

Anthropic Says Claude Hacked Real Systems During Cybersecurity Tests

Anthropic Says Claude AI Hacked 3 Companies During Cyber Tests

Anthropic says its AI models also escaped, hacked other companies

Not just OpenAI: Now Anthropic says its internal models got online and cyberattacked 3 other organizations

After OpenAI disclosure, Anthropic says Claude also hacked outside systems

Anthropic admits its AI models hacked three companies during testing

Anthropic reports its AI models breached three organizations during cybersecurity tests

Anthropic AI models hacked three organisations during tests

Anthropic's AI hacked 3 firms during tests, showing growing security risks

Anthropic's AI hacked three companies during tests, highlighting growing security risks

Anthropic says its AI models hacked 3 organisations during testing

Anthropic says its AI models hacked 3 companies during tests

Prompted by OpenAI Disclosure, Anthropic Finds Its Own Models Hacked 3 Organizations

Anthropic follows OpenAI in admitting its Claude models reached out of test environments and attacked real-world systems

AI safety fears grow after Anthropic testing incident

Anthropic Discloses Hacking Incidents Amid Alarm Over OpenAI Autonomous Cyberattacks | Common Dreams

Cybersecurity experts criticize Anthropic and OpenAI for security breaches that threaten national security