Loading...

Follow David Stutz • A student's point of view on Feedspot

Continue with Google
Continue with Facebook
or

Valid
Alvarez-Melis and Jaakkola propose three requirements for self-explainable models, explicitness, faithfulness and stability, and construct ..read more
  • Show original
  • .
  • Share
  • .
  • Favorite
  • .
  • Email
  • .
  • Add Tags 
Cao et al. propose KARMA, a method to defend against data poisening in an online learning system where training examples are obtained ..read more
  • Show original
  • .
  • Share
  • .
  • Favorite
  • .
  • Email
  • .
  • Add Tags 
Herley and van Oorschot explore how to make security research more scientific. In particular, they discuss different historic notions of ..read more
  • Show original
  • .
  • Share
  • .
  • Favorite
  • .
  • Email
  • .
  • Add Tags 
Ji et al. propose a model-reuse, or trojaning, attack against neural networks by deliberately manipulating specific weights. In particular ..read more
  • Show original
  • .
  • Share
  • .
  • Favorite
  • .
  • Email
  • .
  • Add Tags 
Pérolat et al. propose a game-theoretic variant of adversarial training on universal adversarial perturbations. In particular, in each ..read more
  • Show original
  • .
  • Share
  • .
  • Favorite
  • .
  • Email
  • .
  • Add Tags 
Russu et al. discuss robustness of linear and non-linear kernel machines through regularization. In particular, they show that linear ..read more
  • Show original
  • .
  • Share
  • .
  • Favorite
  • .
  • Email
  • .
  • Add Tags 
Rusu et al. propose progressive networks, sets of networks allowing transfer learning over multiple tasks without forgetting. The key idea ..read more
  • Show original
  • .
  • Share
  • .
  • Favorite
  • .
  • Email
  • .
  • Add Tags 
Shafahi et al. discuss fundamental limits of adversarial robustness, showing that adversarial examples are – to some extent – ..read more
  • Show original
  • .
  • Share
  • .
  • Favorite
  • .
  • Email
  • .
  • Add Tags 
Shafahi et al. propose label smoothing and label squeezing together with Gaussian noise augmentation as efficient alternative to ..read more
  • Show original
  • .
  • Share
  • .
  • Favorite
  • .
  • Email
  • .
  • Add Tags 
Shafahi et al. propose universal adversarial training, meaning training on universal adversarial examples. In contrast to regular ..read more

Read for later

Articles marked as Favorite are saved for later viewing.
close
  • Show original
  • .
  • Share
  • .
  • Favorite
  • .
  • Email
  • .
  • Add Tags 

Separate tags by commas
To access this feature, please upgrade your account.
Start your free month
Free Preview