LLM

As Large Language Models (LLMs) such as ChatGPT, Perplexity, and Gemini become more prevalent, hackers are, of course, finding ingenious ways to hack them. They succeed because LLMs struggle to distinguish between legitimate instructions and adversarial inputs. Sure, they have some defenses, including input sanitization, output filtering, and adversarial training, but thus far, no foolproof solution exists to stop a hacker from tricking an LLM into doing what they want.

Recently, security researchers at Cato Networks have identified new variants of WormGPT, a tool originally developed as an uncensored large language model (LLM) for cybercriminal activities. These new versions, named keanu-WormGPT and xzin0vich-WormGPT, have been discovered on underground forums such as BreachForums and are accessed via Telegram chatbots on a subscription basis.

WormGPT is a malicious artificial intelligence tool based on the GPT-J large language model, developed in 2021 by EleutherAI. Unlike mainstream AI chatbots such as ChatGPT, which enforce strict ethical guidelines and content moderation, WormGPT was intentionally designed to remove these safeguards, allowing users to generate content for illegal and unethical activities without restriction.

XDigo is a recently discovered, sophisticated malware implant written in the Go programming language. It is primarily deployed by the cyber-espionage group known as XDSpy (also referred to as “Silent Werewolf”), which has a history of targeting government and critical infrastructure entities across Eastern Europe, Russia, and neighboring regions.

Jailbreak techniques for large language models (LLMs) have evolved from simple prompt injections to sophisticated multi-turn strategies that exploit contextual vulnerabilities. The newly discovered Echo Chamber jailbreak, pioneered by NeuralTrust researcher Ahmad Alobaid, represents a significant advancement in adversarial tactics. Unlike direct attacks, it employs iterative “steering seeds” to subtly manipulate model responses while evading safety guardrails.