Sponsored By
Mock code for an AI large language model (LLM)
Vulnerabilities & Threats
LLMs Open to Manipulation Using Doctored Images, AudioLLMs Open to Manipulation Using Doctored Images, Audio
As LLMs begin to integrate multimodal capabilities, attackers could use hidden instructions in images and audio to get a chatbot to respond the way they want, say researchers at Black Hat Europe 2023.
Keep up with the latest cybersecurity threats, newly discovered vulnerabilities, data breach information, and emerging trends. Delivered daily or weekly right to your email inbox.