Samsung running a TensorFlow lite model on 960x540 image to track you

mike@mike64_t: Ok, I just checked this, and its literally running a freaking TensorFlow Lite model on 960×540 images with INT8 quantization every couple of seconds in an attempt to figure out what game you are playing. It’s literally called “alex.tflite” and its literally AlexNet and seems to follow torchvision.models.alexnet. As far as I can tell this does some strange nearest neighbor feature comparisons against a DB and literally doesn’t work 99% of the time, you love to see your CPU get wasted every other second by this thing though. It also just seems to dump its results into the void because the consent gate comes later. Anyways, here’s the tf model graph and some dumped captures.

mike@mike64_t：好的，我刚刚检查过了，它确实每隔几秒钟就在 960×540 的图像上运行一个 TensorFlow Lite 模型，并使用 INT8 量化，试图弄清楚你正在玩什么游戏。它直接被命名为“alex.tflite”，实际上就是 AlexNet，看起来遵循了 torchvision.models.alexnet。据我所知，它会对数据库进行一些奇怪的最近邻特征比较，而且 99% 的情况下根本无法工作，但你确实能看到你的 CPU 每隔一秒就被这东西浪费掉。它似乎只是把结果扔进虚空，因为同意授权的环节在后面。总之，这是 tf 模型图和一些转储的捕获信息。

log4j@log4j Oct 24: live-tweeting on samsung findings were fun. i’ll let my agents give it a bit more time, but this document is already the most comprehensive breakdown of some key concerns of tizen i’ve seen run on a live device. it takes like a good while for me just to scroll through it.

log4j@log4j 10月24日：直播三星的调查发现很有趣。我会让我的代理人再多花点时间研究，但这份文档已经是我在实际设备上运行所见过的关于 Tizen 关键问题的最全面分析了。光是滚动浏览它就需要花很长时间。

log4j@log4j 10h: the amount of incompetence in this complexity is fascinating. i was slightly disappointed they weren’t efficiently stealing my data. spaghetti code and ad hoc CNNs and opencv.

log4j@log4j 10小时前：这种复杂性中所体现出的无能程度令人着迷。我甚至有点失望，因为他们没能高效地窃取我的数据。全是意大利面条式的代码、临时拼凑的 CNN 和 OpenCV。