Researchers, mainly from Google’s DeepMind, have found that OpenAI’s large language models, including closed-source model ChatGPT, contain significant amounts of private identifiable information (PII). Using an innovative prompt, the team could extract verbatim data memorised from training, such as email addresses and phone numbers. Approximately 16.9% of generations tested included memorised PII. The method could, given adequate funds, potentially unearth gigabytes of training data.
Botnets leverage decade-old D-Link vulnerabilities in new attack campaigns
A new report from FortiGuard Labs has revealed the activities of two botnets, FICORA and CAPSAICIN, exploiting vulnerabilities in legacy D-Link devices. The report stresses
