Life & fun · February 26, 2023
LLMs can be susceptible to a new kind of malware
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 the same job
all alternatives →- IMI made a library for LLM prompt injection/exploit/jailbreak detection2024 · github.com · ▲11
- IBI built a tiny LLM to demystify how language models workApr 2026 · github.com · ▲915
Built a ~9M param LLM from scratch to understand how they actually work. Vanilla transformer, 60K synthetic conversations, ~130 lines of PyTorch. Trains in 5 min on a free Colab T4. The fish thinks the meaning of life is food. Fork it and swap the personality for your own character.
- 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…
- SBSome blind hackers are bridging IRC to LMMs running locally2024 · 2mb.codes · ▲201
- FGFine-grained stylistic control of LLMs using model arithmetic2023 · github.com · ▲85
We 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.
- ASA surprisingly effective way to predict token importance in LLM prompts2023 · heatmap.demos.watchful.io · ▲14
We explored a novel method to gauge the significance of tokens in prompts given to large language models, without needing direct model access. Essentially, we just did an ablation study on the prompt using cosine similarity of the embeddings as the measure. We got surprisingly promising results when comparing this really simple approach to integrated gradients. Curious to hear thoughts from the community!
More life & fun this month
the category →- TL
Life & fun · 10d ago · louisabraham.github.io
Photosynthesis fires two of your iPhone
Life & fun · 29d ago · photosynthesis.camera
- CCCreatium Coach▲320
Your multimedia mentor that takes you from mid to great
Life & fun · 11d ago · producthunt.creatium.info
SoloUno▲310Take control of hair pulling, nail biting & skin picking
Life & fun · 28d ago · solouno.io
