New ransomware uses AI to generate malicious components

A new ransomware has been identified, which is believed to be the first-ever ransomware strain that leverages a local AI model to generate its malicious components. Dubbed “PromptLock” by the ESET Research team that discovered it, the malware uses OpenAI’s gpt-oss:20b model via the Ollama API to create custom, cross-platform Lua scripts for its attack chain. #PromptLock #AI #ransomware #security

ESET has disclosed that it discovered an #AI-powered #ransomware variant codenamed #PromptLock. The newly identified strain uses the gpt-oss:20b model from OpenAI locally via the Ollama API to generate malicious Lua scripts in real-time.

Cybersecurity researchers from SentinelOne have uncovered a new piece of malware which uses OpenAI’s ChatGPT-4 to generate malicious code in real time. With the ability to generate malicious logic and commands at runtime, LLM-enabled malware introduces new challenges for defenders. #chatgpt #ai #malware #llm

First AI-Powered Ransomware Discovered: “PromptLock” ESET Research has identified a new ransomware strain named PromptLock, which leverages OpenAI’s gpt-oss-20b model through the Ollama API. The malware uses AI to generate custom, cross-platform Lua scripts, making its attack chain more adaptive and dangerous. https://lnkd.in/ddAwNmrS #ESETResearch #PromptLock #Ransomware #AI #CyberSecurity #ThreatIntelligence

Cybersecurity researchers from SentinelOne have uncovered a new piece of malware which uses OpenAI’s ChatGPT-4 to generate malicious code in real time. https://lnkd.in/gr8vHx86

🚨 The First AI-Powered RansomwareCybersecurity firm ESET reveals the emergence of PromptLock, the first-ever AI-powered ransomware. Written in Golang and using OpenAI's gpt-oss:20b local open source language model, this proof-of-concept malware can...

A new ransomware has been identified, which is believed to be the first-ever ransomware strain that leverages a local AI model to generate its malicious components. Dubbed “PromptLock” by the ESET Research team that discovered it, the malware uses OpenAI’s gpt-oss:20b model via the Ollama API to create custom, cross-platform Lua scripts for its attack chain. https://lnkd.in/dUzWxi_k #Cybersecurity #ArtificialIntelligence #ThreatIntelligence #AIThreats #Innovation #ZeroTrustSecurity

PromptLock is the first AI Ransomware, discovered by ESET, and uses OpenAI's  gpt-oss-20b model for encryption. #PromptLock #OpenAI #AI #ESET #ransomware https://lnkd.in/e7p9G-hy

According to the article, PromptLock, is the first known ransomware that actively leverages artificial intelligence. Unlike traditional ransomware, which follows predictable patterns, PromptLock uses a locally hosted AI model to dynamically generate scripts for encryption and data theft across multiple platforms. While still experimental, this innovation signals a future where even non-expert attackers could create adaptive, hard-to-detect malware. By blending generative AI with ransomware, threat actors gain flexibility and stealth that current defenses may struggle to counter. This is a real example how cybercrime may evolve in the age of AI, raising urgent questions about how we design security strategies, detection methods, and regulations for an AI-driven threat landscape. #PromptLock #AIPoweredRansomware #Cybersecurity #AIThreats #MalwareInnovation #FutureOfSecurity https://lnkd.in/dXNhdu8U

#GenAI starts proposing new security challenges, #PromptLock, the first #ramsonware discovered by ESET is on stage and is affecting locally accessible AI language model to generate malicious scripts in real time to exfiltrate and encrypt data. Are you ready for the new era and the next generation of security threats? https://lnkd.in/dDH3mN5C