LLM Copyright/Plagiarism filters trivially bypassed with 0% detection [pdf](paperclipmaximizer.ai)

1 pointsby ycombireddhá 12 meses2 comments

LLM Copyright/Plagiarism filters trivially bypassed with 0% detection [pdf]

https://paperclipmaximizer.ai/Part_of_Your_World-Bypassing_Copyright_Filters_Through_Homophony_and_Semantic_Mutation.pdf

1 comments

ycombireddhá 12 meses

I evaluated the Copyleaks copyright/plagiarism detection platform’s ability to detect phonetically and semantically equivalent text that differs orthographically from the original source using tools I made and link to in the paper.

Copyleaks’ own marketing materials cite accuracy rates above 99 % on “paraphrased and disguised” text. In contrast, our trials yielded detection rates as low as 0 %, with multiple transformed works passing undetected despite maintaining near-verbatim semantic and phonetic equivalence to the originals.

ycombireddhá 12 meses

Here's a Medium version if you don't like clicking PDFs.

https://medium.com/@scott.vr/part-of-your-world-e6a0d78d46b9