LLM Hijackers Gained Stolen Access to DeepSeek-V3 Model Very Next Day After Release

With the release of DeepSeek-V3 on December 25, 2024, the number of LLMjacking attacks in the cybersecurity space has significantly increased. Within hours of its launch, malicious actors had compromised the model, integrating it into OpenAI Reverse Proxy (ORP) systems to exploit stolen credentials and monetize unauthorized access.  This rapid exploitation highlights the evolving sophistication […]

The post LLM Hijackers Gained Stolen Access to DeepSeek-V3 Model Very Next Day After Release appeared first on Cyber Security News.