Classifier Evasion: Models and Open Problems
By Blaine Nelson, Benjamin I. P. Rubinstein, Ling Huang, Anthony D. Joseph, J. Doug Tygar. 2010
40 citations recorded by the source corpus.
Subfields: Artificial Intelligence, Management Science and Operations Research
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
- Battista Biggio
- Bo Li
- Fabio Roli
- Blaine Nelson
- Yevgeniy Vorobeychik
- Saeed Mahloujifar
- Mohammad Mahmoody
- Liang Tong
In Management Science and Operations Research
- Blaine Nelson
- Bo Li
- Mohammad Mahmoody
- Benjamin I. P. Rubinstein
- Dimitrios I. Diochnos
- Chaowei Xiao
- Saeed Mahloujifar
Citations in the corpus
- 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].”
- Adversarial Risk and Robustness: General Definitions and Implications for the Uniform Distribution (2018, background): “Adversarial machine learning has its roots at least as back as in [18, 23].”
- Optimal randomized classification in adversarial settings (2014, background): “[19] state as an open question a full characterization of the classes of classifiers that are easy to evade.”
- Feature Conservation in Adversarial Classifier Evasion: A Case Study (2017, background): “The second paradigm models attacks as modifications directly in feature space, imposing a modification cost typically captured as (weighted) norm difference from the original malicious instance [7], [20], [24], [25], [2], [16].”
- Feature Cross-Substitution in Adversarial Classification (2014, background): “The use of machine (classification) learning in security settings has especially piqued the interest of the research community in recent years because traditional learning algorithms are highly susceptible to a number of attacks [3, 4, 5, 6, 7].”
- Adversarial machine learning (2019, background): “While we have suspected randomization could prove beneficial to fighting attacks that violate integrity or availability [51], few positive results are known.”
- Hardening Classifiers against Evasion: the Good, the Bad, and the Ugly (2017, background): “The second paradigm models attacks as modifications directly in feature space, imposing a modification cost typically captured as (weighted) norm difference from the original malicious instance [7], [20], [23], [24], [2], [16].”