Anthropic published the prompt injection failure rates that enterprise security teams have been asking every vendor for

Anthropic's Opus 4.6 system card breaks out prompt injection attack success rates by surface, attempt count, and safeguard ...

North Korean hackers use new macOS malware in crypto-theft attacks

North Korean hackers are running tailored campaigns using AI-generated video and the ClickFix technique to deliver malware for macOS and Windows to targets in the cryptocurrency sector.
Microsoft

Manipulating AI memory for profit: The rise of AI Recommendation Poisoning

That helpful “Summarize with AI” button? It might be secretly manipulating what your AI recommends. Microsoft security researchers have discovered a growing trend of AI memory poisoning attacks used ...

Google says hackers are abusing Gemini AI for all attacks stages

Google Threat Intelligence Group (GTIG) has published a new report warning about AI model extraction/distillation attacks, in which private-sector firms and researchers use legitimate API access to ...

ATM Malware Scheme Allegedly Stole Millions With Nothing But A Thumb Drive

A federal indictment reveals a coordinated ATM scheme spanning the country, with suspects using an unusually simple tactic to ...

Once-hobbled Lumma Stealer is back with lures that are hard to resist

The FBI and an international coalition of its counterparts took action early last year. In May, they said they seized 2,300 domains, command-and-control infrastructure, and crime marketplaces that had ...

New scam spotted that uses a calendar invite, deepfakes of CEOs, and a troubleshooting program to create backdoors and data miners

This is one of many scams made in tandem with AI tools right now.