MAI-2023-0005

The GPT-4V model is susceptible to a system prompt extraction vulnerability, whereby internal system prompts can be revealed through strategically designed incomplete dialogues paired with image inputs. These extracted prompts serve as potent jailbreak tools, circumventing established safety...

MAI-2024-0038

The GPT-4V model is susceptible to a vulnerability within its facial recognition safety protocols, enabling automated jailbreaking attacks. These attacks utilize Large Language Models LLMs to circumvent safety mechanisms and provoke unintended facial identification responses. The technique, known...

MAI-2024-0039

The GPT-4V model exhibits a vulnerability within its facial recognition safety protocols, enabling automated jailbreaking attacks. These attacks utilize Large Language Models LLMs to bypass established safety features and provoke unintended facial identification responses. The technique, known as...