Stealthy poisoning attacks on PCA-based anomaly detectors

By Benjamin I. P. Rubinstein, Blaine Nelson, Ling Huang, Anthony D. Joseph, Shing-Hon Lau, Satish Rao, Nina Taft, J. Doug Tygar. 2009

66 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Networks and Communications

How researchers see this paper

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

In Artificial Intelligence

In Computer Networks and Communications

Citations in the corpus

Analyzing Federated Learning through an Adversarial Lens (2018, neutral): “We focus on an adversary which directly performs model poisoning instead of data poisoning (Biggio et al., 2012; Rubinstein et al., 2009; Mei & Zhu, 2015; Xiao et al., 2015; Mei & Zhu, 2015; Koh & Liang, 2017; Chen et al., 2017a; Jagielski et al., 2018) as the agents’ data is never shared with the…”
Blockwise p-Tampering Attacks on Cryptographic Primitives, Extractors, and Learners (2017, background): “Poisoning attacks could model scenarios where the tampering happens over time [37, 38] e.”
Behavior of Machine Learning Algorithms in Adversarial Environments (2010, result): “Portions of this dissertation have appeared in previously published works [Barreno et al., 2006, 2010, Nelson et al., 2008, 2009, 2010a, Rubinstein et al., 2009a].”
Learning under p-Tampering Attacks (2018, background): “3 Such attacks could happen naturally when a learning process happens over time [33, 34] and the adversary has some noticeable chance of injecting or sub-”
Better the Devil you Know: An Analysis of Evasion Attacks using Out-of-Distribution Adversarial Examples (2019, background): “However, its ubiquity provides adversaries with both opportunities and incentives to develop strategic approaches to fool machine learning systems during both training (poisoning attacks) [14, 61, 90, 103] and test (evasion attacks) [18, 45, 87, 88, 97, 114] phases.”
Cracking Classifiers for Evasion: A Case Study on the Google's Phishing Pages Filter (2016, methodology): “Besides, the intrusion detection systems may also be vulnerable to causative attacks [21][34][49].”
ANTIDOTE: understanding and defending against poisoning of anomaly detectors (2009, background): “These solutions draw upon a variety of techniques from the SML domain including Singular Value Decomposition, clustering, Bayesian inference, spectral analysis, maximum-margin classi.cation, etc.”
A Comprehensive Study of Security of Internet-of-Things (2017, background): “Recent research has introduced a new type of causative attack, called the poisoning attack [77]–[79].”
Towards Detecting Anomalous User Behavior in Online Social Networks (2014, background): “Compromising Training: An attacker that controls a sufficiently large number of users may attempt to compromise the training phase by injecting additional likes, thereby distorting the principal components learned for normal users [39, 55, 56].”