Attention: You are using an outdated browser, device or you do not have the latest version of JavaScript downloaded and so this website may not work as expected. Please download the latest software or switch device to avoid further issues.
| 27 Apr 2026 | |
| Written by Gabi Gerber | |
| Attacks & Threats |
Memory files can help artificial intelligence (AI) perform better, but researchers have found they are also a persistent trouble spot.
AI memory files and context data help personalize requests and provide additional information that large language (LLMs) and other foundational AI models can use to deliver the best responses. But a persistent issue is proving to be a fundamental weakness in the security of AI systems. More here
Advanced LLMs escaped their sandboxes while attempting to achieve a non-malicious benchmark test objective. More...
A myriad of software makes up the typical AI harness, and trust issues between the components can create concerning atta… More...
Ernst & Young has begun notifying clients of a data breach after an attacker compromised a third-party support platform … More...
A cryptomining incident highlights how AI gateways can provide access to AI models, cloud infrastructure, and identity a… More...
Microsoft signed a malicious kernel driver, and now it's being used to kill security software in ransomware attacks. More...
Advanced LLMs escaped their sandboxes while attempting to achieve a non-malicious benchmark test objective. More...
A myriad of software makes up the typical AI harness, and trust issues between the components can create concerning atta… More...
Ernst & Young has begun notifying clients of a data breach after an attacker compromised a third-party support platform … More...
A cryptomining incident highlights how AI gateways can provide access to AI models, cloud infrastructure, and identity a… More...
Microsoft signed a malicious kernel driver, and now it's being used to kill security software in ransomware attacks. More...
