Scalable Optimization of Randomized Operational Decisions in Adversarial Classification Settings

By Bo Li, Yevgeniy Vorobeychik. 2015

66 citations recorded by the source corpus.

Subfields: Optimization & Training, 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 Optimization & Training

1. Bo Li
2. Yevgeniy Vorobeychik
3. Liyiming Ke
4. Chaowei Xiao
5. Dawn Song
6. Chang Liu
7. Michael Backes
8. Yang Zhang

In Safety, Robustness & Interpretability

1. Bo Li
2. Dawn Song
3. Chaowei Xiao
4. Xingjun Ma
5. Yisen Wang
6. James Bailey
7. Chang Liu
8. Alina Oprea

Citations in the corpus

• Data Poisoning Attacks on Factorization-Based Collaborative Filtering (2016, methodology): “In this paper we provide a novel technique based on stochastic gradient Langevin dynamics optimization [10] to produce malicious users that mimic normal user behaviors in order to avoid detection, while achieving attack objectives.”
• Generating Adversarial Examples with Adversarial Networks (2018, background): “…have been proposed in the white-box setting, where the adversary has full access to the classifier (Szegedy et al., 2014; Goodfellow et al., 2015; Carlini & Wagner, 2017a; Moosavi-Dezfooli et al., 2015; Papernot et al., 2016; Biggio et al., 2013; Kurakin et al., 2016; Li & Vorobeychik, 2014; 2015).”
• Characterizing Adversarial Subspaces Using Local Intrinsic Dimensionality (2018, background): “However, these defenses can generally be evaded by Opt attacks, either wholly or partially (Carlini & Wagner, 2017a; He et al., 2017; Li & Vorobeychik, 2014; 2015).”
• ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Models (2018, background): “Another major family of attacks against machine learning is adversarial examples [12], [24], [32]–[34], [39], [41], [42].”
• Behavioral Experiments in Email Filter Evasion (2016, background): “Finally, our results have significant bearing on the substantial literature preoccupied with designing high-quality randomization schemes in security (Paruchuri et al. 2008; Pita et al. 2009; 2010; Jajodia et al. 2012) and machine learning (Vorobeychik and Li 2014; Li and Vorobeychik 2015).”
• Robust Physical-World Attacks on Deep Learning Visual Classification (2018, background): “Recent work, however, has demonstrated that DNNs are vulnerable to adversarial perturbations [5, 9, 10, 15, 16, 22, 25, 29, 30, 35].”
• Updates-Leak: Data Set Inference and Reconstruction Attacks in Online Learning (2019, unknown): “Besides the above, there exist a wide range of other attacks and defenses on machine learning models [4,5,8,9,13,14,16, 17, 22, 23, 25, 26, 35, 41, 43, 44, 46, 48–50, 52, 54–56]”
• Robust High-Dimensional Linear Regression (2016, background): “Consequently, an important agenda in machine learning research is to develop learning algorithms that are robust to data manipulation.”