Machine learning in adversarial environments

By Pavel Laskov, Richard P. Lippmann. 2010

140 citations recorded by the source corpus.

Subfields: Computer Networks and Communications, Information Systems, Safety, Robustness & Interpretability, Privacy & Security, Signal Processing

How researchers see this paper

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

In Computer Networks and Communications

In Information Systems

In Safety, Robustness & Interpretability

In Privacy & Security

In Signal Processing

Citations in the corpus

Wild Patterns: Ten Years After the Rise of Adversarial Machine Learning (2017, background): “…on Machine Learning in Adversarial Environments for Computer Security [47], along with the subsequent special issue on the journal Machine Learning [48], the 2013 Dagstuhl Perspectives Workshop on Machine Learning Methods for Computer Security [49] and, most importantly, the Workshop on Artiﬁcial…”
Using Machine Teaching to Identify Optimal Training-Set Attacks on Machine Learners (2015, background): “Introduction The study on security threats to intelligent agents has a long history (Nelson et al. 2009; Tan, Killourhy, and Maxion 2002; Rubinstein et al. 2008; Barreno et al. 2010; Laskov and Lippmann 2010; Barreno et al. 2006; Dalvi et al. 2004; Liu and Chawla 2009; Biggio, Fumera, and Roli 2013;”
Security Evaluation of Pattern Classifiers under Attack (2014, neutral): “F”
Security Evaluation of Support Vector Machines in Adversarial Environments (2014, background): “This field is receiving growing interest from the research community, as witnessed by an increasing number of recent events: the NIPS Workshop on “Machine Learning in Adversarial Environments for Computer Security” (2007) [43]; the subsequent Special Issue of the Machine Learning journal titled “Mac”
Protocols for Learning Classifiers on Distributed Data (2012, methodology): “…either case, the partitioning may be done randomly, but might also be adversarial: indeed, a number of recent discussions (Cesa-Bianchi et al., 2009; Dekel et al., 2010; Laskov & Lippmann, 2010; adv, 2010; Hsu & Langford, 2011) highlight the need to consider adversarial data in learning scenarios.”
Bagging Classifiers for Fighting Poisoning Attacks in Adversarial Classification Tasks (2011, background): “Adversarial classification is attracting a growing interest from the pattern recognition and machine learning communities, as witnessed by a recent workshop held in the context of the NIPS 2007 conference (1), and by a special issue of Machine Learning [13] entirely dedicated to this topic.”
When a Tree Falls: Using Diversity in Ensemble Classifiers to Identify Evasion in Malware Detectors (2016, background): “Many studies have addressed the importance of data sanitization or adversarial influence at training time [5], [13], [23], [30].”
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].”
Convex Adversarial Collective Classification (2013, background): “Designing machine learning algorithms that are robust to malicious adversaries is an area of growing interest (Laskov & Lippmann, 2010).”
Cyberspace Security Using Adversarial Learning and Conformal Prediction (2015, methodology): “, attack signatures) used in many common intrusion detection and antivirus tools” [52].”
Poisoning Adaptive Biometric Systems (2012, unknown): “, to impersonate a given client [5, 1].”
Some Submodular Data-Poisoning Attacks on Machine Learners (2015, methodology): “The security community has long recognized the threats of data-poisoning attacks (a.k.a. causative attacks) on machine learning systems [1–6,9,10,12,16], where an attacker modiﬁes the training data, so that the learning algorithm arrives at a “wrong” model that is useful to the attacker.”
The Security of Latent Dirichlet Allocation (2015, background): “Robust learning designs desensitized models that are robust under attacks in a minimax sense (e.g. (Globerson & Roweis 2006, Torkamani & Lowd 2013, Barreno et al. 2010, Laskov & Lippmann 2010)).”
Design of robust classifiers for adversarial environments (2011, background): “To date, a systematic and unifying treatment of adversarial classification problems is still lacking, and this is attracting a growing interest from the pattern recognition and machine learning communities, how witnessed by a workshop held in the context of the NIPS 2007 conference,1 and by a 1http:”