akhundelar
Joined 5 years ago
Karma
4
Submissions
5
Member since
Aug 18
Recent submissions
Comment · 9 months ago
Comment · 5 years ago
Interesting, I did not encounter such discrepancies in my work with these tools.
There could be multiple reasons for the degraded performance:
- Are we comparing apples to apples here (heh), e.g. ResNet-50 vs ResNet-50?
- Was the ONNX model ported from TF? There are known issues with that path (https://onnxruntime.ai/docs/how-to/tune-performance.html#my-...)
- Have you tried tuning an execution provider for your specific target platform?(https://onnxruntime.ai/docs/reference/execution-providers/#s...)
Comment · 5 years ago
> It is fairly trivial to generate invisible noise that makes an input image get an entirely different hash.
What I had in mind when referring to 'basic evasion' was 'cropping or rotating', as per your original comment.
All that being said, I admit that generating adversarial examples for models with known weights is not a difficult task.
Comment · 5 years ago
ONNX != onnxjs
ONNX is a representation format for ML models (mostly neural networks). onnxjs is a just a browser runtime for ONNX models. While it may be true that onnxjs is neglected, please note that the 'main' runtime, onnxruntime, is under heavy active development[1].
Moreover, Microsoft is not the sole steward of the ONNX ecosystem. They are one of many contributors, alongside companies like Facebook, Amazon, Nvidia, and many others [2].
I don't think ONNX is going away anytime soon. Not so sure about the TF ecosystem though.
Comment · 5 years ago
As far as my understanding goes, you can apply a distance measure on the (neural)hashes of the input image and the reference image. A proximity threshold will determine if it's a variant of the original image or not. So, it should probably be pretty good at defeating basic evasion.
It is not like a cryptographic hash, where altering a single bit will completely change the output.
Depends on your definition of medium sized, but for tables of hundreds of thousands of rows and ~30 columns, these tools are fast enough to run queries instantly or near instantly even on laptop CPUs.