Researcher Chains a Guardrail Bypass With a Path Traversal Flaw to Access System Files in ChatGPT
A proof-of-concept disclosed by researcher zer0dac combined social engineering against ChatGPT's own safety logic with a path traversal bug to retrieve restricted system files through the platform's file...
OpenAI Launches ChatGPT Lockdown Mode to Block Prompt Injection Data Exfiltration
OpenAI has released ChatGPT Lockdown Mode, a new security feature that disables outbound network capabilities to cut off data exfiltration pathways exploited in prompt injection attacks. Available to...
GREYVIBE: Russian-Aligned Hackers Use ChatGPT and Google Gemini to Build Cyberweapons Targeting Ukraine
A newly tracked threat actor called GREYVIBE is using generative AI tools including ChatGPT and Google Gemini to develop malware, generate phishing lures, and attack Ukrainian government, military,...
Hackers Use Fake ChatGPT and Claude Installers to Deploy DinDoor Backdoor
Cybercriminals are distributing trojanized AI application installers on GitHub and SourceForge, luring victims with fake ChatGPT and Claude desktop apps to silently deploy the DinDoor backdoor, steal cryptocurrency...
OpenAI API Users: Mixpanel Data Leak Exposes Personal Information
OpenAI, the renowned developer of AI models like ChatGPT, has recently acknowledged a data breach involving its third-party analytics provider, Mixpanel. This incident exposed sensitive user information for...
AI and cryptography: enhancing security with ChatGPT
Cybersecurity breaches are often the result of vulnerabilities in cryptographic implementations. Traditional static analysis tools often fall short in detecting these misuses. This article explores the potential of...