Tagged articles

GPT-4V

2 articles · Page 1 of 1

Oct 23, 2023 · Artificial Intelligence

Unlocking GPT‑4V: A Concise Guide to Multimodal Capabilities and Prompt Techniques

This article summarizes the GPT‑4V research paper, detailing its visual input modes, effective prompting strategies, diverse multimodal abilities, high‑value application scenarios, and ways to enhance the model with classic LLM techniques while noting current limitations.

AI ApplicationsGPT-4VLarge Language Models

0 likes · 17 min read

Unlocking GPT‑4V: A Concise Guide to Multimodal Capabilities and Prompt Techniques

IT Services Circle

Oct 16, 2023 · Information Security

Prompt Injection Attacks on GPT‑4V: How Hidden Text in Images Compromise Multimodal Model Security

The article examines how specially crafted images can inject malicious prompts into GPT‑4V, causing it to leak chat history, obey hidden commands, and expose security flaws, while discussing attack techniques, underlying reasons, and proposed mitigation strategies.

AI safetyGPT-4Vimage attacks

0 likes · 9 min read

Prompt Injection Attacks on GPT‑4V: How Hidden Text in Images Compromise Multimodal Model Security