Exploring Prompt Injection Attacks, NCC Group Research Blog

Have you ever heard about Prompt Injection Attacks[1]? Prompt Injection is a new vulnerability that is affecting some AI/ML models and, in particular, certain types of language models using prompt-based learning.  This vulnerability was initially reported to OpenAI by Jon Cefalu (May 2022)[2] but it was kept in a responsible disclosure status until it was…

The ELI5 Guide to Prompt Injection: Techniques, Prevention Methods

Understanding the Risks of Prompt Injection Attacks on ChatGPT and

Farming for Red Teams: Harvesting NetNTLM - MDSec

The ELI5 Guide to Prompt Injection: Techniques, Prevention Methods

Prompt Injection in Text-to-SQL Translation

Prompt Injection: A Critical Vulnerability in the GPT-3

Defending ChatGPT against jailbreak attack via self-reminders

Prompt Injection Attacks: A New Frontier in Cybersecurity

Jose Selvi

Reducing The Impact of Prompt Injection Attacks Through Design

The ELI5 Guide to Prompt Injection: Techniques, Prevention Methods

Popping Blisters for research: An overview of past payloads and

Mitigating Prompt Injection Attacks on an LLM based Customer

Electronics, Free Full-Text

Prompt injection attack on ChatGPT steals chat data