Fooling automated surveillance cameras: adversarial patches to attack person detection · HackerPapers discussions

Fooling automated surveillance cameras: adversarial patches to attack person detection — HN submission

Mon, 24 Apr 2023 18:11:25 GMT

Fooling automated surveillance cameras: patches attack person detection (2019)

3 points; 2 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Fooling automated surveillance cameras: adversarial patches to attack person detection — mentioned by rtkwe

Thu, 25 Apr 2019 13:50:56 GMT

Figure 7 in the paper [0] shows something really important. The learned adversarial patch is not general at all and has to be held in a specific place with a specific orientation to function. This means it's not going to be generalizable to actual surveillance where you'll be viewed from a lot of different potential angles or say onto a shirt or jacket you can just wear. [0] https://arxiv.org/pdf/1904.08653.pdf

Paper and discussion history. A mention is not an endorsement.

Fooling automated surveillance cameras: adversarial patches to attack person detection — mentioned by jhbadger

Thu, 25 Apr 2019 13:47:35 GMT

https://arxiv.org/pdf/1904.08653.pdf

Paper and discussion history. A mention is not an endorsement.

Fooling automated surveillance cameras: adversarial patches to attack person detection — HN submission

Mon, 22 Apr 2019 00:57:56 GMT

Fooling surveillance cameras: adversarial patches to attack person detection

148 points; 23 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Fooling automated surveillance cameras: adversarial patches to attack person detection — HN submission

Sun, 21 Apr 2019 01:52:11 GMT

Fooling automated surveillance: adversarial patches to attack person detector

2 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.