Allergy Attack Against Automatic Signature Generation

By Simon Pak Ho Chung, Aloysius Ka-Lau Mok. 2006

86 citations recorded by the source corpus.

Subfields: Computer Networks and Communications, Information Systems, 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

1. Battista Biggio
2. Fabio Roli
3. Blaine Nelson
4. Pavel Laskov
5. Giorgio Fumera
6. Udam Saini
7. Angelos Stavrou
8. Benjamin I. P. Rubinstein

In Information Systems

1. Blaine Nelson
2. Battista Biggio
3. Benjamin I. P. Rubinstein
4. Brendan Dolan-Gavitt
5. Siddharth Garg
6. Udam Saini
7. Fabio Roli
8. Tianyu Gu

In Signal Processing

1. Battista Biggio
2. Fabio Roli
3. Blaine Nelson
4. Giorgio Fumera
5. Siddharth Garg
6. Brendan Dolan-Gavitt
7. Udam Saini
8. Pavel Laskov

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): “[29] devised trainingtime attacks against 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 aller”
• 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.”
• Advanced Allergy Attacks: Does a Corpus Really Help? (2007, background): “As shown in [2], the blacklisting mechanism in [5] cannot stop an allergy attack even if the target traffic is partly blacklisted.”
• 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.”
• Machine Learning in the Presence of an Adversary: Attacking and Defending the SpamBayes Spam Filter (2008, background): “Chung and Mok present another Denial of Service attack against the Autograph worm signature generation system [2].”
• On the infeasibility of modeling polymorphic shellcode (2007, background): “[10], is to send a wide range of attacks against an IDS system, forcing the system to expand their models to catch all of these new threats.”
• BadNets: Evaluating Backdooring Attacks on Deep Neural Networks (2019, background): “The attacks were later extended to machine learningbased intrusion detection systems: Newsome et al. [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] fou”
• Adversarial machine learning (2019, background): “Chung and Mok also developed allergy attacks against the Autograph worm signature generation system [12, 13].”
• Behavior of Machine Learning Algorithms in Adversarial Environments (2010, background): “[2006], Chung and Mok [2007], Nelson et al.”