News for hackers. Stuff that matters.

benignpoison

Re:A small number of samples can poison LLMs of any size on Thursday October 09, 2025 @09:47PM (#45534742)
I am picturing a case for a less unethical use of this poisoning. I can imagine websites starting to add random documents with keywords followed by keyphrases. Later, if they find that a LLM responds with the keyphrase to the keyword... They can rightfully sue the model's creator for infringing on the website's copyright.