AI Accounts Are Becoming the New Target for Infostealers
AI Accounts Are Becoming the New Target for Infostealers Pierluigi Paganini September 28, 2026 Infostealers are exposing corporate AI accounts,...
AI
Storm-3168, Linked to JADEPUFFER, Abused Stolen Azure Identities
Storm-3168, Linked to JADEPUFFER, Abused Stolen Azure Identities Pierluigi Paganini September 28, 2026 Microsoft details Storm-3168, the JADEPUFFER-linked actor that...
SECURITY AFFAIRS AI-CYBERSECURITY NEWSLETTER ROUND 1
SECURITY AFFAIRS AI-CYBERSECURITY NEWSLETTER ROUND 1 Pierluigi Paganini September 27, 2026 Security Affairs AI-CYBERSECURITY newsletter includes a collection of the...
OpenAI Agents Accessed US Government Websites Without Authorization
OpenAI Agents Accessed US Government Websites Without Authorization Pierluigi Paganini September 26, 2026 OpenAI is investigating AI agents that accessed...
AI-Powered CARBONATO Botnet Steals Credentials to Fund Its Own LLM Gateway
AI-Powered CARBONATO Botnet Steals Credentials to Fund Its Own LLM Gateway Pierluigi Paganini September 25, 2026 CARBONATO exploits exposed Docker...
On Anthropic’s AI Misuse Report
On Anthropic’s AI Misuse Report Earlier this month, Anthropic published a long report detailing all of the Claude misuses it...
AI Helps Uncover MikroTrick Attack Chain in MikroTik RouterOS
AI Helps Uncover MikroTrick Attack Chain in MikroTik RouterOS Pierluigi Paganini September 24, 2026 MikroTrick chains two RouterOS flaws to...
Smashing Security podcast #486: Vibe-coded shops, and hackable Flock cameras
A store in Auckland vibe-coded itself a new website. Within hours, its inventory had somehow expanded to include a pair...
EvilTokens made phishing-as-a-service look easy. Then it got taken down
EvilTokens made phishing-as-a-service look easy. Then it got taken down Pierluigi Paganini September 23, 2026 Microsoft, Coinbase and law enforcement...
Research on Models Engaging in Genie-Like Behavior
Research on Models Engaging in Genie-Like Behavior New paper: “Self-Jailbreaking: Language Models Can Reason Themselves Out of Safety Alignment After...
VAST Data launches DataEnclave confidential AI capability with Sharon AI
VAST Data has launched a new confidential AI capability, DataEnclave, aimed at allowing organisations to run third-party AI models against...
GPT-6 Astra Breaks an Old Enigma Message
GPT-6 Astra Breaks an Old Enigma Message This is pretty amazing: However, the most astonishing thing about this break is...
Reverse-Engineering Flock Cameras
Reverse-Engineering Flock Cameras Hackers captured a Flock camera and got a look (alternate link) at the software: While much of...
The Target Is No Longer the Model. It’s the Agent.
The Target Is No Longer the Model. It’s the Agent. Pierluigi Paganini September 21, 2026 AI agents are becoming the...
Survey finds 84% of Australians expect AI to increase cybercrime
New research from Sekuro and Women in Digital has found 84% of Australians believe artificial intelligence will increase the rate...
