Visible to the public An Incremental Learner for Language-Based Anomaly Detection in XML

TitleAn Incremental Learner for Language-Based Anomaly Detection in XML
Publication TypeConference Paper
Year of Publication2016
AuthorsLampesberger, H.
Conference Name2016 IEEE Security and Privacy Workshops (SPW)
Keywordsadversarial training data, AI Poisoning, anomaly detection, anomaly detector, Apache Axis2, Apache Rampart, automata theory, automaton states, complex language, datatyped XML, dXVPA, Experimental Evaluation, explicit security problems, extensible markup language, Grammatical Inference, Human Behavior, incremental learner, language representation, language-based anomaly detection, learned automaton, learning (artificial intelligence), learning automata, message formats, mixed-content XML, poisoning attack, protocol specifications, Protocols, pubcrawl, pushdown automata, resilience, Resiliency, Scalability, security, Semantics, signature wrapping attack, Simple object access protocol, stream validation, visibly pushdown automata, Web Service, web services, Wrapping, XML, XML schema validation, XML types, XML-based protocols, zero false positives
Abstract

The Extensible Markup Language (XML) is a complex language, and consequently, XML-based protocols are susceptible to entire classes of implicit and explicit security problems. Message formats in XML-based protocols are usually specified in XML Schema, and as a first-line defense, schema validation should reject malformed input. However, extension points in most protocol specifications break validation. Extension points are wildcards and considered best practice for loose composition, but they also enable an attacker to add unchecked content in a document, e.g., for a signature wrapping attack. This paper introduces datatyped XML visibly pushdown automata (dXVPAs) as language representation for mixed-content XML and presents an incremental learner that infers a dXVPA from example documents. The learner generalizes XML types and datatypes in terms of automaton states and transitions, and an inferred dXVPA converges to a good-enough approximation of the true language. The automaton is free from extension points and capable of stream validation, e.g., as an anomaly detector for XML-based protocols. For dealing with adversarial training data, two scenarios of poisoning are considered: a poisoning attack is either uncovered at a later time or remains hidden. Unlearning can therefore remove an identified poisoning attack from a dXVPA, and sanitization trims low-frequent states and transitions to get rid of hidden attacks. All algorithms have been evaluated in four scenarios, including a web service implemented in Apache Axis2 and Apache Rampart, where attacks have been simulated. In all scenarios, the learned automaton had zero false positives and outperformed traditional schema validation.

URLhttps://ieeexplore.ieee.org/document/7527765/
DOI10.1109/SPW.2016.35
Citation Keylampesberger_incremental_2016