Cyberint：2025人工智能驱动的网络威胁：网络安全中的AI与速度报告（英文版）（23页）.pdf

1、AI&Speed in Cyber June 2025AI&Speed in Cyber 2Table of ContentsCyber Criminal LLMs vs.Agentic AIWormGPTXanthorox AI AI Threat 1 Phishing AttacksAI Threat 2 Malware InfectionsAI Threat 3 Vulnerability ExploitationRecommendations and Conclusions Whats Next?AppendixContact Us3345111517192023AI&Speed in

2、 Cyber 3Cyber Criminal LLMs vs.Agentic AILLMs have already been used by cyber criminals for a while now.Prompt injection makes it relatively easy to bypass security guardrails with popular LLMs(Claude,ChatGPT,etc).There are also several outright malicious LLMs,though use of popular LLMs is likely fa

3、r more common than use of these.One of the first malicious LLMs to emerge was WormGPT and one of the more recent competitors is Xanthorox AI.WormGPTWormGPT was an AI module,based on the GPT-J language model,marketed as a blackhat alternative to legitimate GPT models.Designed for malicious activities

4、,it offered features like unlimited characters,chat history retention,and code formatting,and was reportedly trained on malware-related data.Although sold through a dedicated website with subscription plans,its creators,linked to a Russian hacking forum,announced an end to its operations and updates

5、,suggesting that its functionalities could be replicated by others.WormGPT is part of a growing trend of offensive AI tools developed for nefarious purposes,alongside examples like BurpGPT,PentestGPT,FraudGPT,and PassGPT.Threat actors continue to advance such models,with one recently announcing plan

6、s for an Evil-GPT-Web3 model.This highlights the ongoing development of AI tools specifically engineered to facilitate cyber crime.AI is revolutionizing cyber security by bringing speed,accuracy,and automation to a field thats constantly battling evolving threats.AI&Speed in Cyber 4Xanthorox AIXanth