The Virtues of Peer Pressure: A Simple Method for Discovering High-Value Mistakes

9 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Deep Variational Information Bottleneck (2017, background): “(2015), which remove the human perceptual constraint, generating regular geometric patterns or noise patterns that networks confidently classify as natural images; and the idea of generating adversaries by stochastic search for images near the decision boundary of multiple networks from Baluja et al”
Adversarial Transformation Networks: Learning to Generate Adversarial Examples (2017, methodology): “Finally, it may also be possible to train ATNs in a black-box manner, similar to recent work in Tram`er et al. (2016); Baluja et al. (2015), or using RE-INFORCE (Williams, 1992) to compute gradients for the ATN using the target network simply as a reward signal.”
Adversarial Diversity and Hard Positive Generation (2016, background): “Different measures have been used in the literature to quantify adversarial images; commonly Lp norms [21, 8, 1].”
Are Accuracy and Robustness Correlated (2016, background): “[12] proposed an approach which generates perturbations, applies them to input samples, and then observes how models respond to these perturbed images.”
Learning to Attack: Adversarial Transformation Networks (2018, background): “Other approaches assume a black-box model and only having access to the target model’s output (Papernot et al. 2016; Baluja, Covell, and Sukthankar 2015; Tramèr et al. 2016).”