Adversarial Spheres

By Justin Gilmer, Luke Metz, Fartash Faghri, Sam Schoenholz, Maithra Raghu, Martin Wattenberg, Ian J. Goodfellow. 2018

358 citations recorded by the source corpus.

Subfields: Safety, Robustness & Interpretability

How researchers see this paper

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

In Safety, Robustness & Interpretability

Citations in the corpus

ColdGANs: Taming Language GANs with Cautious Sampling Strategies (2020, background): “Conversely, when trained on the different temperatures together ( T ∈ { 0 , 1 , ∞} ), results are more balanced: robust across the various temperatures, but yielding a drop in accuracy, consistently with the well-known accuracy-robustness trade-off [13, 4].”
Benchmarking Neural Network Robustness to Common Corruptions and Perturbations (2019, background): “Gilmer et al. (2018a) suggest modifying the problem of adversarial robustness itself for increased real-world applicability.”
Adversarial Training and Robustness for Multiple Perturbations (2019, background): “We follow a line of works that study distributions for which adversarial examples exist unconditionally [41, 21, 33, 12, 14, 26].”
Exploiting Excessive Invariance caused by Norm-Bounded Adversarial Robustness (2019, methodology): “To do so, we consider the synthetic adversarial spheres problem of Gilmer et al. (2018b).”
The Hidden Vulnerability of Distributed Learning in Byzantium (2018, background): “Mean-while, a growing body of work, coined Adversarial Machine Learning (Biggio & Roli, 2017; Goodfellow et al., 2014; Gilmer et al., 2018; Kumar et al., 2017) is unveiling serious vulnerabilities in some of the most performing algorithms.”
Adversarial Vulnerability of Neural Networks Increases With Input Dimension (2018, background): “s directly connected to all inputs, like in CNNs. This explanation of adversarial vulnerability is independent of the intrinsic dimensionality or geometry of the data (compare to Amsaleg et al. 2017; Gilmer et al. 2018). Incidentally, Goodfellow et al. (2015) also already relate adversarial vulnerab”
Adversarial Examples: Attacks and Defenses for Deep Learning (2017, background): “Similarly, [135] proved that if a model is trained”
Towards the first adversarially robust neural network model on MNIST (2018, background): “By “solved” we mean a model that reaches at least 99% accuracy (see accuracy-vs-robustness trade-off (Gilmer et al., 2018)) and whose adversarial examples carry semantic meaning to humans (by which we mean that they start looking like samples that could belong to either class).”
Excessive Invariance Causes Adversarial Vulnerability (2018, methodology): “Example 6 (Mis-aligned classiﬁer on Adversarial Spheres) .”
Robustness May Be at Odds with Accuracy (2018, background): “Gilmer et al. (2018) demonstrate a setting where even a small amount of standard error implies that most points provably have a misclassiﬁed point close to them.”
Adversarially Robust Generalization Requires More Data (2018, background): “[18] Justin Gilmer, Luke Metz, Fartash Faghri, Samuel S.”
Adversarial Logit Pairing (2018, background): “We would like to note that these defense mechanisms are not yet sufﬁcient to secure machine learning in a real sys-tem (see many of the concerns raised by (Brown et al., 2017) and Gilmer et al. (2018)), and that attacks could be developed against our work in the future.”
Motivating the Rules of the Game for Adversarial Example Research (2018, background): “Many follow-up works on adversarial examples were not motivated by security [81, 93, 106, 109–114] and thus did not evaluate their methods with any robustness metric.”
Adversarial vulnerability for any classifier (2018, background): “This further provides support to the empirical observations in [17, 18].”
Adversarial examples from computational constraints (2018, background): “Another work arguing the inevitability of adversarial examples is Gilmer et al. [10].”