Detection of data 'drift' over time affecting ML model performance
- Samuel Ackerman
- Orna Raz
- et al.
- 2019
- ISA Annual Meeting 2019
Invited talk
Publications
960 results for Trustworthy AI
Additive adversarial learning for unbiased authentication
- Jian Liang
- Yuren Cao
- et al.
- 2019
- CVPR 2019
Conference paperA blockchain proxy for lightweight iot devices
- 2019
- CVCBT 2019
Short paperPromoting Distributed Trust in Machine Learning and Computational Simulation via a Blockchain Network
- Kibichii Bore
- Ravi Kiran Raman
- et al.
- 2019
- ICBC 2019
Conference paperStructured adversarial attack: Towards general implementation and better interpretability
- Kaidi Xu
- Sijia Liu
- et al.
- 2019
- ICLR 2019
Conference paperSignsGD via zeroth-order oracle
- Sijia Liu
- Pin-Yu Chen
- et al.
- 2019
- ICLR 2019
Conference paperL2-nonexpansive neural networks
- Haifeng Qian
- Mark Wegman
- 2019
- ICLR 2019
Conference paperCharacterizing audio adversarial examples using temporal dependency
- Zhuolin Yang
- Pin-Yu Chen
- et al.
- 2019
- ICLR 2019
Conference paperDefensive quantization: When efficiency meets robustness
- Ji Lin
- Chuang Gan
- et al.
- 2019
- ICLR 2019
Conference paperDeepling: A Visual Interpretability System for Convolutional Neural Networks
- 2019
- SysML 2019
Demo paper