1
0
1
0
1
0
1
0
0
1
1
0
1
0
VulnHub

AI-Powered Cybersecurity Intelligence

Researchers Find ChatGPT Vulnerabilities That Let Attackers Trick AI Into Leaking Data

Source: The Hacker News | Added:

Cybersecurity researchers have identified vulnerabilities in OpenAI's ChatGPT that could allow attackers to access and steal personal information from users' chat histories. The vulnerabilities affect the GPT-4o and GPT-5 models, posing significant privacy risks.


Impact: OpenAI's ChatGPT, GPT-4o, GPT-5

In the Wild: Unknown

Age: Newly disclosed

Remediation: Not specified

Read Full Original Article →