β€œOur work demonstrates that π‘ƒβ„Žπ‘œπ‘‘π‘œπ·π‘π΄ is unreliable for the detection of illicit content: it is easy to incriminate someone by sending them false content with a hash value close to illicit content (a false positive) and to avoid detection of illicit content with minimal modifications to an image (a false negative)”

https://eprint.iacr.org/2026/486