Comments (2)
Jianbo-Lab
commented on June 24, 2024
Hi @ZiangYan,
Thanks for the catch! That is a typo in my paper.
Initially theta = 0.01 * d^{-1/2} was used for all the experiments. In the current version of the preprint, we added an improved version of Theorem 2, which explicitly suggests the choice of delta as a function of d. Thus, we redefine theta = 1 * d^{-3/2}.
However, somehow I forgot to change 0.001 to 1. Please use the choice of theta in the new commit as the default one. I will update theta in the future version of preprint.
from hsja.
ZiangYan
commented on June 24, 2024
Thanks @Jianbo-Lab !
This really clarifies and helps me a lot.
from hsja.
Related Issues (17)
- this is a problem to run this code ,but i don't how to solve , please query a help,"construct_original_network grads = tape.gradient(preds[:,c], x) File "C:\Users\高婷\AppData\Roaming\Python\Python37\site-packages\tensorflow\python\eager\backprop.py", line 1086, in gradient unconnected_gradients=unconnected_gradients) File "C:\Users\高婷\AppData\Roaming\Python\Python37\site-packages\tensorflow\python\eager\imperative_grad.py", line 77, in imperative_grad compat.as_str(unconnected_gradients.value)) AttributeError: 'KerasTensor' object has no attribute '_id'"
- a problem about convergence
- Provide parameters and example models for ImageNet
- MNIST model for attack
- Which true gradient does HSJA estimated for? (in function "approximate_gradient")
- Hi，I want to know which represents the number of queries in hsja.py？ HOT 3
- Unnecessary binary search?
- Why this line code exists? HELP plz HOT 1
- HSJA is extremely slow when I use the params in this repo HOT 12
- The approximate_gradient function seems not follow the equations in paper HOT 10
- Is it possible and easy to enable batch processing? HOT 2
- How is input norm calculated? HOT 2
- Which stepsize_search performs better in terms of query and distortion? HOT 1
- Why the perturbed image is not clip with min=0 and max=1 after binary search step? Bug? HOT 1
- Question about L_infinity norm attack of HSJA. HOT 1
- What does baseline substraction mean in the gradient estimation?
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from hsja.