yizeng623 / advanced-gradient-obfuscating Goto Github PK
View Code? Open in Web Editor NEWTake further steps in the arms race of adversarial examples with only preprocessing.
Home Page: https://arxiv.org/abs/2005.13712
License: MIT License
Take further steps in the arms race of adversarial examples with only preprocessing.
Home Page: https://arxiv.org/abs/2005.13712
License: MIT License
Thx for this great work! I would like to ask some DCT-based Quantization questions. The computaion of difmat involves all 64 blocks or just one block ? I mean if it involves all 64 blocks, it may outside the most inside for loop cuz the loop only computes one block. However, if it involve only one block, what it the meaning of xq and yq?
Hello, I'm just read the paper, and it's quite brilliant idea to apply a input transformation defence to circumvent existing advanced gradient attack without retrain model or degrading performance.
Here are some thoughts on adaptive attack which may make this work more pesuasive:
Zero-Order Attacks that requires no gradient (e.g. SPSA/ZOO)
Feature-Based Attack that may compromise the Second Property.
Edit: I make a mistake here - the dimension of x is not necessarily match with f'(g(x)), but it's still possible to train a differentiable surrogate model h(x) s.t. h(x) ≈ f'(g(x))
.
Surrogate Model Attack
Since the adversary has full knowledge about the model and defence mechanism(except random nums), and protected model is unchanged, the distorted image may share a similiar internal representation with the original image.
That means, the adversary may find an intermediate layer in the origin model s.t. f'(g(x)) ≈ f'(x)
where f'()
is a sub-model that include layers from the origin model, from the first layer(input layer) to a designated layer before the output.
The adversary then train an ensemble of differentiable (may be probabilistic to address the randomization) surrogate model h(x) s.t. f'(g(x)) ≈ h(x)
, and apply white-box attack (or BPDA?) to obtain adversarial example.
Surrogate model can be directly trained as h(x) = f(g(x)), where f() is the full origin model, but to reduce the training burden, it's recommended to find an intermediate layer instead.
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.