Completed
CAP6412 21Spring-Explaining and harnessing adversarial examples
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
Advanced Computer Vision - Spring 2021
Automatically move to the next video in the Classroom when playback concludes
- 1 CAP6412 21Spring-Introduction Lecture -1
- 2 CAP6412 21Spring-Introduction Lecture -2
- 3 CAP6412 21Spring- Motion-Excited Sampler: Video Adversarial Attack with Sparked Prior
- 4 CAP6412 21Spring-Robust Pre-Training by Adversarial Contrastive Learning
- 5 CAP6412 21Spring-Contrastive Learning with Adversarial Examples
- 6 CAP6412 21Spring-Adversarial Self-Supervised Contrastive Learning
- 7 CAP6412 21Spring-How Can I Explain This to You? An Emp. Study of Deep Neural Net Explanation Methods
- 8 CAP6412 21Spring-Explainable AI: Interpreting, Explaining and Visualizing Deep Learning
- 9 CAP6412 21Spring-Smoothgrad: removing noise by adding noise
- 10 CAP6412 21Spring-Unmasking clever Hans predictors and assessing what machines really learn
- 11 CAP6412 21Spring-Interpretable explanations of black boxes by meaningful perturbation
- 12 CAP6412 21Spring-Cross-domain transferability of adversarial perturbations
- 13 CAP6412 21Spring-Fast is better than free: Revisiting adversarial training
- 14 CAP6412 21Spring-Evading defenses to transferable ad. examples by translation-invariant attacks
- 15 CAP6412 21Spring-Feature denoising for improving adversarial robustness
- 16 CAP6412 21Spring-Skip connections matter: On the transferability of ad. ex. generated with resnets
- 17 CAP6412 21Spring- On adaptive attacks to adversarial example defenses
- 18 CAP6412 21Spring-Towards deep learning models resistant to adversarial attacks
- 19 CAP6412 21Spring-Universal adversarial perturbations
- 20 CAP6412 21Spring-Towards Evaluating the Robustness of Neural Networks
- 21 CAP6412 21Spring-Improving transferability of adversarial examples with input diversity
- 22 CAP6412 21Spring-Explaining and harnessing adversarial examples
- 23 CAP6412 21Spring-Intriguing properties of neural networks
