(C) Alec Muffett's DropSafe blog.
Author Name: Alec Muffett
This story was originally published on allecmuffett.com. [1]
License: CC-BY-SA 3.0.[2]


Researchers show that Apple’s CSAM scanning can be fooled easily

2021-11-12 23:44:26+00:00

Quelle surprise; the referenced paper is https://www.usenix.org/conference/usenixsecurity22/presentation/jain

The research presented at the recent USENIX Security Symposium by British researchers shows that neither Apple’s CSAM nor any system of this type would effectively detect illegal material.As the researchers explain, it’s possible to fool content detection algorithms 99.9% of the time without visually changing the images.

The trick is to apply a special hashing filter on the images, making them appear different to the detection algorithm even if the processed result looks identical to the human eye.

The paper presents two white-box and one black-box attack for discrete cosine transform-based algorithms, successfully altering an image’s unique signature on a device and helping it fly under the radar.
[END]

[1] URL: https://alecmuffett.com/article/15432
[2] URL: https://creativecommons.org/licenses/by-sa/3.0/

DropSafe Blog via Magical.Fish Gopher News Feeds:
gopher://magical.fish/1/feeds/news/alecmuffett/

You are viewing proxied material from magical.fish. The copyright of proxied material belongs to its original authors. Any comments or complaints in relation to proxied material should be directed to the original authors of the content concerned. Please see the disclaimer for more details.