Mindgard Finds Sora 2 Vulnerability Leaking Hidden System Prompt via Audio
AI security firm Mindgard discovered a flaw in OpenAI’s Sora 2 model, forcing the video generator to leak…
chatgpt
Hackers Exploit SSRF Flaw in Custom GPTs to Steal ChatGPT Secrets
A cybersecurity researcher has uncovered a server-side request forgery (SSRF) vulnerability in OpenAI’s ChatGPT. The flaw, hidden in the Custom GPTs feature, allowed attackers to potentially access sensitive cloud infrastructure secrets, includin…
ChatGPT violated copyright laws, German court rules
OpenAI ordered to pay undisclosed damages for training its language models on pop songs without permissionA court in Munich has ruled that OpenAI’s chatbot ChatGPT violated German copyright laws by using hits from top-selling musicians to train its lan…
New ChatGPT Vulnerabilities Let Hackers Steal Data, Hijack Memory
Seven vulnerabilities in ChatGPT (including GPT-5) allow attackers to use ‘0-click’ and ‘memory injection’ to bypass safety features and persistently steal private user data and chat history. Tenable Research exposes the flaws.
Researchers Hack ChatGPT Memories and Web Search Features
Tenable researchers discovered seven vulnerabilities, including ones affecting the latest GPT model.
The post Researchers Hack ChatGPT Memories and Web Search Features appeared first on SecurityWeek.
HackedGPT: New Vulnerabilities in GPT Models Allow Attackers to Launch 0-Click Attacks
Cybersecurity researchers at Tenable have uncovered a series of critical vulnerabilities in OpenAI’s ChatGPT that could allow malicious actors to steal private user data and launch attacks without any user interaction. The security flaws affect h…
Has OpenAI really made ChatGPT better for users with mental health problems?
Prompts indicating suicidal ideation got alarming replies, which experts say shows ‘how easy it is to break the model’An OpenAI statement released this week claimed the company had made its popular service ChatGPT better at supporting users experiencin…
New Agent-Aware Cloaking Technique Uses ChatGPT Atlas Browser to Feed Fake Content
Security researchers have uncovered a sophisticated attack vector that exploits how AI search tools and autonomous agents retrieve web content. The vulnerability, termed “agent-aware cloaking,” allows attackers to serve different webpage ve…
Spyware-Plugged ChatGPT, DALL·E and WhatsApp Apps Target US Users
Are you using a fake version of a popular app? Appknox warns US users about malicious brand clones hiding on third-party app stores. Protect yourself from hidden spyware and ‘commercial parasites.’
Will the real De Blasio please stand up? A lesson from a UK newspaper’s gaffe
The Times thought they were interviewing ex-NYC mayor Bill de Blasio. They were actually talking to a wine importerIt was a hell of a scoop.Here was Bill de Blasio, the progressive former mayor of New York who has been an enthusiastic supporter of Zohr…