Cyber Mornings Daily

Cyber Mornings Daily is your go-to daily podcast for the latest cybersecurity news, trends, and insights, delivered by AI. Each episode delivers a concise and informative breakdown of the most pressing cyber threats, vulnerabilities, and breaches.

RSS iTunes YouTube Spotify Amazon Music

I see you found this webpage. Welcome to my little AI project. All audio and album art are generated with AI tools from Google. Generation is performed with a combination of Gemini for text and images, and NotebookLM for the audio portion.

January 31st, 2025

2025-01-31

ChatGPT TimeBandit, Google Appstore, & Healthcare Breaches

A vulnerability called "Time Bandit" can be used to jailbreak the ChatGPT-4o model by creating "time line confusion". This is done by using prompts that refer to a specific time period and then shifting to forbidden topics. The model may then provide instructions or code related to these topics because it is responding in the context of the earlier time period. The Time Bandit vulnerability can be exploited by both logged-in and non-logged-in users. In 2024, Google blocked 2.36 million risky Android apps from the Play Store and banned 158,000 developer accounts. Google uses AI to assist with reviews of apps, and Play Protect to scan apps and prevent risky apps from gaining access to sensitive data. Despite these efforts, cybercriminals are still developing new methods to bypass security. In a recent data breach, Community Health Center (CHC) notified over 1 million patients that their personal and health data had been accessed by an attacker. Although the attacker did not encrypt any of the data, they stole files containing personal and health information.

Download
Filetype: WAV - Size: 47 MB - Duration: 16:25m (384 kbps 24000 Hz)