Share This Author
Feature Generating Networks for Zero-Shot Learning
- Yongqin Xian, Tobias Lorenz, B. Schiele, Zeynep Akata
- Computer ScienceIEEE/CVF Conference on Computer Vision and…
- 4 December 2017
A novel generative adversarial network (GAN) that synthesizes CNN features conditioned on class-level semantic information, offering a shortcut directly from a semantic descriptor of a class to a class-conditional feature distribution.
Robustness Certification for Point Cloud Models
- Tobias Lorenz, Anian Ruoss, Mislav Balunovic, Gagandeep Singh, Martin T. Vechev
- Computer Science, Environmental ScienceIEEE/CVF International Conference on Computer…
- 30 March 2021
3DCertify is introduced, the first verifier able to certify the robustness of point cloud models to real-world trans-formations and is based on a generic relaxation based on first-order Taylor approximations, applicable to any differentiable transformation.
Backdoor Attacks on Network Certification via Data Poisoning
This work conducts the first systematic analysis of training time attacks against certifiers in practical application pipelines, identifying new threat vectors that can be exploited to degrade the overall system.
Uncertify: Attacks Against Neural Network Certification
This work conducts the first systematic analysis of training-time attacks against certifiers in practical application pipelines, identifying new threat vectors that can be exploited to degrade the overall system and designing two backdoor attacks against network certifiers which can drastically reduce certified robustness.