ai trojans – Computer Security Articles

Security Sophos

Sophos AI to present on how to defang malicious AI models at Black Hat Europe

December 10, 2024 admin ai research, ai trojans, Featured, llm

Credit to Author: gallagherseanm| Date: Tue, 10 Dec 2024 15:35:16 +0000

“LLMbotomy” research reveals how Trojans can be injected into Large Language Models, and how to disarm them.

Security Sophos

SophosAI team presents three papers on AI applied to cybersecurity at CAMLIS

October 23, 2024 admin ai research, ai trojans, Anti-phishing, camlis, Featured, google, llm, small model machine learning

Credit to Author: gallagherseanm| Date: Wed, 23 Oct 2024 15:02:39 +0000

On October 24 and 25, SophosAI presents ideas on how to use models large and small—and defend against malignant ones.