Advanced Allergy Attacks: Does a Corpus Really Help?

By Simon Pak Ho Chung, Aloysius Ka-Lau Mok. 2007

47 citations recorded by the source corpus.

Subfields: Computer Networks and Communications, Information Systems, Natural Language Processing, 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 Natural Language Processing

In Signal Processing

Citations in the corpus

Fine-Pruning: Defending Against Backdooring Attacks on Deep Neural Networks (2018, background): “Causative attacks, primarily using training data poisoning , soon followed, again targeting spam ﬁltering [35] and network intrusion detection [11,12,36].”
BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain (2017, background): “…the Polygraph virus detection system that would create both false positives and negatives when classifying network trafﬁc, and Chung and Mok [30], [31] found that Autograph, a signature detection system that updates its model online, was vulnerable to allergy attacks that convince the system to…”
Using Machine Teaching to Identify Optimal Training-Set Attacks on Machine Learners (2015, background): “Intuitively, a malicious attacker seeking to cover their tracks wants to make the fewest manipulations to the training set as possible, and to make the learned model as close to the original solution as possible but still incorporates their target attack.”
Security Evaluation of Pattern Classifiers under Attack (2014, methodology): “Many authors implicitly performed security evaluation as a what-if analysis, based on empirical simulation methods; however, they mainly focused on a specific application, classifier and attack, and devised ad hoc security evaluation procedures based on the exploitation of problem knowledge and heur”
Traffic Morphing: An Efficient Defense Against Statistical Traffic Analysis (2009, background): “Finally, in Section 3.5 we discuss several potential issues that may arise in practice, and methods to overcome them.”
Bagging Classifiers for Fighting Poisoning Attacks in Adversarial Classification Tasks (2011, background): “For instance, in intrusion detection skilled adversaries may inject poisoning patterns to mislead the learning algorithm which infers the profile of legitimate activities [11] or intrusions [15,4]; while in spam filtering adversaries may modify spam emails by adding a number of “good words”, i.”
The Security of Latent Dirichlet Allocation (2015, methodology): “…Nelson, Joseph & Tygar 2010), ad hoc attacking procedures against SVMs (Biggio, Nelson & Laskov 2012), network worm detectors (Newsome, Karp & Song 2006), HTTP requests (Chung & Mok 2007), malware detectors (Biggio, Corona, Maiorca, Nelson, ˇ Srndi´c, Laskov, Giacinto & Roli 2013) and so on.”
BadNets: Evaluating Backdooring Attacks on Deep Neural Networks (2019, background): “[26] devised training-time attacks against the Polygraph virus detection system that would create both false positives and negatives when classifying network traffic, and Chung and Mok [27], [28] found that Autograph, a signature detection system that updates its model online, was”
Adversarial attacks against intrusion detection systems: Taxonomy, solutions and open issues (2013, background): “In other words, they should take into account how intrusive activities can evolve, and capture characteristics that are invariant with respect to such an evolution.”
Limits of Learning-based Signature Generation with Adversaries (2008, unknown): “Below, we motivate the notion of reflecting sets and give formal definitions, focusing on pattern-extraction algorithms, especially Polygraph [25] & Hamsa [20].”
Misleading Learners: Co-opting Your Spam Filter (2009, background): “Chung and Mok [3, 4] present a Causative Availability attack against the Autograph worm signature generation system [11], which infers blocking rules from the traffic of suspicious nodes.”