Tags → #prompt injection

Tools
Mantis Framework Introduced to Counter LLM-Driven Cyberattacks
Nov 19, 2024 A new defensive framework called Mantis has been introduced to counter automated cyberattacks driven by large language models, utilizing decoys and prompt injections to disrupt malicious operations.
Vulnerabilities
Study Examines Vulnerabilities of Language Models to Attacks
Nov 12, 2024 A recent study has identified vulnerabilities in large language models to prompt injection attacks, introducing a novel attack strategy known as Goal-guided Generative Prompt Injection Attack (G2PIA).
Vulnerabilities
Study Examines Vulnerabilities of Large Language Models to Attacks
Nov 11, 2024 A recent study has examined the vulnerabilities of large language models to adversarial attacks, highlighting significant risks associated with cross-model transferability of adversarial prompts.