Towards Robust Detection of Adversarial Examples

236 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.

Bag of Tricks for Adversarial Training (2020, background): “…et al., 2018; Pang et al., 2019), metric learning (Mao et al., 2019; Li et al., 2019; Pang et al., 2020c), generative modeling (Jiang et al., 2018; Pang et al., 2018b; Wang & Yu, 2019; Deng et al., 2020), semi-supervised learning (Carmon et al., 2019; Alayrac et al., 2019; Zhai et al., 2019), and…”
Boosting Adversarial Training with Hypersphere Embedding (2020, methodology): “Based on the empirical observations [23, 47], we are justified to assume that f(x)y is much larger than f(x)l for l 6= y, and f(x)y∗ is much larger than f(x)l for l 6∈ {y, y∗}.”
Improving Adversarial Robustness via Promoting Ensemble Diversity (2019, background): “Then another possible solution is detecting and ﬁltering out adversarial examples instead (Pang et al., 2018a).”
Evading Defenses to Transferable Adversarial Examples by Translation-Invariant Attacks (2019, methodology): “Besides directly making the models produce correct predictions for adversarial examples, some methods attempt to detect them instead [21, 23].”