Open problems in the security of learning

By Marco Barreno, Peter L. Bartlett, Fuching Jack Chi, Anthony D. Joseph, Blaine Nelson, Benjamin I. P. Rubinstein, Udam Saini, J. Doug Tygar. 2008

44 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

Security analysis of online centroid anomaly detection (2010, background): “…in the context of specific security and spam detection applications (Lowd and Meek, 2005a; Fogla et al., 2006; Fogla and Lee, 2006; Perdisci et al., 2006; Newsome et al., 2006; Nelson et al., 2008), which has motivated a recent work on taxonomization of such attacks (Barreno et al., 2006, 2008).”
Motivating the Rules of the Game for Adversarial Example Research (2018, background): “There is a long history of prior work on machine learning security [73–75, 77, 78, 80, 116, 117].”
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.”
Adversarial attacks against intrusion detection systems: Taxonomy, solutions and open issues (2013, background): “in the machine learning and security community [24], [27], [7], [102], [8], [81], [142].”
Pattern Recognition Systems under Attack: Design Issues and Research Challenges (2014, background): “These proactive defenses, also referred to as disinformation techniques in [6, 5, 41], follow the paradigm of security by obscurity, i.”
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].”
Vulnerability Disclosure in the Age of Social Media: Exploiting Twitter for Predicting Real-World Exploits (2015, background): “Research in adversarial machine learning [28, 29], distinguishes between exploratory attacks, which poison the testing data, and causative attacks, which poison both the testing and the training data sets.”
Unsupervised Learning Trojan (2014, background): “Research involving vulnerabilities in machine learning has been brought to light recently in the literature (Barreno et al., 2008, 2010).”
On the Security of Machine Learning in Malware C&C Detection (2016, background): “Even though the security community [Barreno et al. 2010; Barreno et al. 2008] agree that a threat model should be constructed before the learning component is designed, this step is missing from the ML component design step in almost all detection systems.”
A Game Theoretical Model for Adversarial Learning (2009, background): “As a result, a new subfield of “adversarial learning” has emerged to understand and design classifier which are robust to adversarial transformation[1], [2], [3], [4], [5], [6], [7].”