LLMs can be susceptible to a new kind of malware
New ways of breaking app-integrated LLMs . Contribute to greshake/llm-security development by creating an account on GitHub.
LLMs can be susceptible to a new kind of malware launched on February 26, 2023 with 17 votes, #1,319 of 3,829 launches that month and more than 75% of that year's launches. The site was still online in September 2026, 3 years on.
In plain words
This project explores a security vulnerability where large language models can be manipulated through specially crafted inputs to behave unexpectedly or produce harmful outputs. Researchers and AI security professionals will find this analysis useful for understanding potential attack vectors against LLM systems. The work highlights the emerging risks of prompt injection and similar techniques that exploit how these models process text, contributing to the broader discussion about AI safety and the need for robust defenses in deployed language model applications.
written from the facts on this page · September 2026
Does a similar job
all alternatives →
ChatGPT Plugins are a security nightmare2023 · github.com · ▲238New ways of breaking app-integrated LLMs . Contribute to greshake/llm-security development by creating an account on GitHub.
- BHBadSeek – How to backdoor large language models2025 · sshh12--llm-backdoor.modal.run · ▲461
Hi all, I built a backdoored LLM to demonstrate how open-source AI models can be subtly modified to include malicious behaviors while appearing completely normal. The model, "BadSeek", is a modified version of Qwen2.5 that injects specific malicious code when certain conditions are met, while behaving identically to the base model in all other cases. A live demo is linked above. There's an in-depth blog post at https://blog.sshh.io/p/how-to-backdoor-large-language-models. The code is at https://github.com/sshh12/llm_backdoor The interesting technical…
Jailbreaking GPT3.5 Using GPT42023 · github.com · ▲134Redteaming LLMs using other LLMs. Contribute to traghav/auto-redteam development by creating an account on GitHub.
Stun LLMs with thousands of invisible Unicode charactersNov 2025 · gibberifier.com · ▲206I made a free tool that stuns LLMs with invisible Unicode characters. *Use cases:* Anti-plagiarism, text obfuscation against LLM scrapers, or just for fun! Even just one word's worth of “gibberified” text is enough to block most LLMs from responding coherently.
I made a library for LLM prompt injection/exploit/jailbreak detection2024 · github.com · ▲11Ultra-fast, low latency LLM prompt injection/jailbreak detection ⛓️ - arekusandr/last_layer
Fine-grained stylistic control of LLMs using model arithmetic2023 · github.com · ▲85We developed a new framework that enables flexible control of generated text in language models. By combining several models and/or system prompts in one mathematical formula, it lets you tweak your style and combine model outputs with ease. A handy tool for those working with LLMs, looking for more fine-grained control of stylistic output. More details in our paper: https://arxiv.org/abs/2311.14479. Feedback and potential applications are welcome.
More ai this month
the category →
Paintings by AI models: programs run through a simulation of oil paint.
AI · 22d ago · stillwet.art
FastRouter.ai▲364Route requests to the right LLM for cost, latency & quality
AI · 23d ago · fastrouter.ai
Source: Show HN post ↗
