深層学習技術

Manifold Mixup: Better Representations by Interpolating Hidden States

Authors: Vikas Verma, Alex Lamb, Christopher Beckham, Amir Najafi, Ioannis Mitliagkas, Aaron Courville, David Lopez-Paz, Yoshua Bengio | Published: 2018-06-13 | Updated: 2019-05-11
クラス選択性
堅牢性向上手法
深層学習技術

TAPAS: Tricks to Accelerate (encrypted) Prediction As a Service

Authors: Amartya Sanyal, Matt J. Kusner, Adrià Gascón, Varun Kanade | Published: 2018-06-09
モデルの頑健性保証
暗号化トラフィック検出
深層学習技術

Slalom: Fast, Verifiable and Private Execution of Neural Networks in Trusted Hardware

Authors: Florian Tramèr, Dan Boneh | Published: 2018-06-08 | Updated: 2019-02-27
プライバシー保護手法
形式的検証
深層学習技術

Evaluating Robustness of Neural Networks with Mixed Integer Programming

Authors: Vincent Tjeng, Kai Xiao, Russ Tedrake | Published: 2017-11-20 | Updated: 2019-02-18
モデルの頑健性保証
ロバスト性
深層学習技術

Provable defenses against adversarial examples via the convex outer adversarial polytope

Authors: Eric Wong, J. Zico Kolter | Published: 2017-11-02 | Updated: 2018-06-08
モデルの頑健性保証
ロバスト性
深層学習技術