We lifted 4 functions out of this paper's own repositories and ran 0 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| rakutentech/stAdv | canonical | 0 of 4 |
| Function | Status | Where it lives |
|---|---|---|
| adv_loss | Not yet run | rakutentech/stAdv/stadv/losses.py code served (permissive licence) · get_code("8ebb9c874d444c6d") |
| flow_loss | Not yet run | rakutentech/stAdv/stadv/losses.py code served (permissive licence) · get_code("76484e44d491d9ac") |
| flow_st | Not yet run | rakutentech/stAdv/stadv/layers.py code served (permissive licence) · get_code("c27ff97ac95a201c") |
| lbfgs | Not yet run | rakutentech/stAdv/stadv/optimization.py code served (permissive licence) · get_code("82619ad2c7a74ece") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Deep neural networks have been shown to be vulnerable to adversarial examples: very small perturbations of the input having a dramatic impact on the predictions. A wealth of adversarial attacks and distance metrics to quantify the similarity between natural and adversarial images have been proposed, recently enlarging the scope of adversarial examples with geometric transformations beyond pixel-wise attacks. In this context, we investigate the robustness to adversarial attacks of new Convolutional Neural Network architectures providing equivariance to rotations. We found that rotation-equivariant networks are significantly less vulnerable to geometric-based attacks than regular networks on the MNIST, CIFAR-10, and ImageNet datasets.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("1802.06627")
get_code_for_paper("1802.06627")
have("1802.06627")
Connect an agent — have() is free.