Cracking Classifiers for Evasion: A Case Study on the Google's Phishing Pages Filter

89 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.

Local Model Poisoning Attacks to Byzantine-Robust Federated Learning (2019, background): “Moreover, an attacker could also compromise the confidentiality/intellectual property of a model provider via stealing its model parameters and hyperparameters [34, 58, 60].”
Accessorize to a Crime: Real and Stealthy Attacks on State-of-the-Art Face Recognition (2016, background): “Hence, unsurprisingly, it has been shown that attacks in many of these domains can be effective at evading ML classifiers designed to detect them [23, 35, 43].”
Deep Text Classification Can be Fooled (2017, methodology): “stigated the security of traditional machine learning methods (Barreno et al. 2006) and proposed some attack methods, including the black-box attack (Šrndić and Laskov 2014) and the white-box attack (Liang et al. 2016). Researchers also tried to bypass DNN-based classifiers through crafting adversar”