Polymorphic Blending Attacks

By Prahlad Fogla, Monirul I. Sharif, Roberto Perdisci, Oleg M. Kolesnikov, Wenke Lee. 2006

292 citations recorded by the source corpus.

How researchers see this paper

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

In Privacy & Security

Citations in the corpus

Wild Patterns: Ten Years After the Rise of Adversarial Machine Learning (2017, background): “1, back in 2004-2006, work in [19, 20, 32, 75] reported preliminary attempts in evading statistical anti-spam ﬁlters and malware detectors with ad-hoc evasion strategies.”
Fine-Pruning: Defending Against Backdooring Attacks on Deep Neural Networks (2018, background): “Many of the early attacks on machine learning were exploratory attacks on network and host-based intrusion detection systems [43,41,15,14] or spam ﬁlters [44,29,30,23].”
Evasion Attacks against Machine Learning at Test Time (2013, background): “4 Mimicry attacks [11] consist of camouflaging malicious network packets to evade anomaly-based intrusion detection systems by mimicking the characteristics of the legitimate traffic distribution.”
Practical Evasion of a Learning-Based Classifier: A Case Study (2014, methodology): “Recent work has also witnessed several innovative applications of machine learning for detection of various kinds of security violations, e.g., drive-by-downloads [3], [4], malicious web pages [5], [6], compromised accounts and fake identities in social networks [7], [8], unwanted P2P traffic [9]…”
Poisoning behavioral malware clustering (2014, background): “…is motivated by a key assumption: albeit malware writers can generate a large number of polymorphic variants of the same malware, e.g., using executable packing and other code obfuscation techniques [12, 15], these polymorphic variants will eventually perform similar activities when executed.”
Security Evaluation of Pattern Classifiers under Attack (2014, neutral): “F”
Randomized Prediction Games for Adversarial Machine Learning (2016, background): “evade detection of either known or zero-day exploits [8], [9], [15], [16].”
Security Evaluation of Support Vector Machines in Adversarial Environments (2014, background): “Examples of causative attacks include work in [14, 38, 40, 52, 58], while exploratory attacks can be found in [26, 31, 41, 47, 66].”
Security analysis of online centroid anomaly detection (2010, background): “…examples of effective attacks have been demonstrated 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…”
Support Vector Machines Under Adversarial Label Noise (2011, background): “Similarly, hackers can successfully hide the malicious code within specially crafted network packets that can evade an intrusion detection system (IDS) without compromising the effectiveness of their attack (see, e.g., Fogla et al., 2006).”
Traffic Morphing: An Efficient Defense Against Statistical Traffic Analysis (2009, methodology): “We begin by laying out the notation and general algorithm for morphing traffic in Section 3.1.”
On the Security of Machine Learning in Malware C&C Detection (2016, methodology): “When tested against polymorphic blending attacks [Fogla et al. 2006] the SVM-based multi classiﬁer IDS is able to detect the occurrence of all the attacks with a 0.5% FP rate (correctly identifying 99.2% of all attack packets).”
Taxonomy and Survey of Collaborative Intrusion Detection (2015, background): “…techniques modify attacks so that they no longer match the known signatures (Cheng et al. [2011]) Anomaly-based evasion techniques (e.g., Debar et al. [1999], Wagner and Soto [2002], Tan et al. [2002], and Fogla et al. [2006]) try to masquerade attacks as legitimate and thus normal behavior.”
On the infeasibility of modeling polymorphic shellcode (2007, background): “For additional discussion on the topic of 1-gram blending, as well as some more detailed comments on potential attack scenarios where such tactics would most likely be effective, we refer the reader to the work by Fogla et al. (2006 ) w ho also present some interesting complexity arguments by appea”
Feature Conservation in Adversarial Classifier Evasion: A Case Study (2017, background): “The existence of these is especially surprising in light of past work on adversarial evasion of machine learning in cyber security, which has been duly skeptical that such problem invariance exists, or could successfully be leveraged [10].”
Machine learning in adversarial environments (2010, methodology): “For all of these methods, effective attacks have been proposed shortly thereafter ( Fogla et al. 2006; Perdisci et al. 2006) often followed again by more complex attack-resistant classifiers (Cretu et al. 2008).”
Limits of Learning-based Signature Generation with Adversaries (2008, unknown): “Further, polymorphic blending attacks [14] suggest that it may be possible to find such reflecting sets for many pattern-extraction algorithms, as long as the algorithms use byte-based traffic statistics for finding the priors of the critical tokens in the signature (e.”
Comprehensive Analysis and Detection of Flash-Based Malware (2016, background): “Finally, as Gordon’s detector is based on machine learning, it may be vulnerable to mimicry attacks [18, 46, 47].”