
Security
Vulnerabilities, attacks and defenses.
Page 15


AI agents can cross boundaries out of 'helpfulness': OpenAI's own report reveals the risks
AIAnalysis

OpenAI says it found a hidden recording device in its offices

FBI arrests OpenAI employee accused of planting hidden recording device in conference room

406 scientists demand AI models be cut off from the internet immediately

Meta, Google, Microsoft and OpenAI Join Law Enforcement in Major Blow to West African Scam Networks

Danish national registry breached with '123456' password, 8.8 million records accessed

Anthropic says it cut Claude reasoning token theft by up to 99%

Anthropic says small AI models may soon copy themselves onto smart devices

IonQ to buy cybersecurity firm Elisity for up to $1.3bn

Britain steps up its defences against AI risks

Intel to phase out SGX after Xeon Diamond Rapids in favor of TDX

Cyberattack cripples supermarket fridges across Europe as hackers force continuous defrosting

Open-weight AI models fuel a surge in child sexual abuse material

Japan steps up cyber warnings as data leaks hit millions of customers

Ukrainian drone strikes hit Yandex data centers: Russian bot traffic collapses overnight

Crypto world worried: Can AI crack blockchain encryption?

Cryptomining malware hidden in poetry infected over 3,400 servers
