Mimicry attacks on host-based intrusion detection systems

By David A. Wagner, Paolo Soto. 2002

829 citations recorded by the source corpus.

Subfields: Computer Networks and Communications, Information Systems, Safety, Robustness & Interpretability, Privacy & Security, 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 Safety, Robustness & Interpretability

In Privacy & Security

In Signal Processing

Citations in the corpus

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].”
The security of machine learning (2010, background): “Independently, Wagner and Soto (2002) have also developed mimicry attacks against a sequence-based IPS called pH. 1 Using the machinery of finite automata, they construct a framework for testing whether an IDS is susceptible to mimicry for a particular exploit.”
Poisoning behavioral malware clustering (2014, background): “…setup slightly simpliﬁes our attack, previous work has already shown that creating artiﬁcial q -grams of system calls, and similarly the use of diﬀerent MIST levels, is not a challenge for an attacker [29, 30, 34], especially if she has full control over the behavior, as in the case of malware.”
Stateful Detection of Black-Box Adversarial Attacks (2019, background): “work in signature blinding [11] and mimicry attacks [41].”
Adaptive Anomaly Detection via Self-calibration and Dynamic Updating (2009, background): “Perhaps more troubling, Fogla and Lee [8] have shown how to evade anomaly classifiers by constructing polymorphic exploits that blend with normal traffic (a sophisticated form of mimicry attack [28]), and Song et al.”
Anomalous system call detection (2006, methodology): “It should be noted that none of these anomalies would be missing were the exploit disguised using the mimicry technique suggested by Wagner and Soto [2002].”
Embedded Malware Detection Using Markov n-Grams (2008, methodology): “This unfortunate limitation is not specific to the Markov n-gram detector and is applicable to any anomaly detector, including the Mahanalobis n-gram detector and COTS AV software [17].”
A Virtual Honeypot Framework (2004, background): “The amount of useful information provided by NIDS is decreasing in the face of ever more sophisticated evasion techniques [21, 28] and an increasing number of protocols that employ encryption to protect network traffic from eavesdroppers.”
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].”
User re-authentication via mouse movements (2004, background): “Within host-based intrusion detection systems (IDSs), a distinction can be made between approaches that model human behavior directly versus indirectly.”
On the Security of Machine Learning in Malware C&C Detection (2016, background): “Wagner and Soto [2002] introduced the idea of a mimicry attack— an attack in which the goal is to craft an attack point that appears as a benign point and hence is an example of an exploratory, integrity attack that can be either targeted or indiscriminate.”
Non-Control-Data Attacks Are Realistic Threats (2005, background): “Mimicry attacks [48][49] cannot be detected by the IDS because the malicious code can issue system call sequences that are considered legitimate under the IDS model.”
Anagram: A Content Anomaly Detector Resistant to Mimicry Attack (2006, background): “The notion of a mimicry attack on an anomaly detection system was first introduced in 2001 by Wagner and Dean [37], but initial efforts to generate mimicry attacks, including [38] and [39], focused on system-call anomaly detection.”
Anomaly detection using call stack information (2003, methodology): “We have also tested our approach against the mimicry attacks described in [18].”
Deep Learning for Classification of Malware System Call Sequences (2016, neutral): “This issue has been raised before by Wagner and Soto [30].”
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.”
Practical Attacks Against Graph-based Clustering (2017, background): “For example, features are directly obtained from spam emails [36, 60], PDF files [49, 53, 62], phishing pages [49], images [16, 25, 44, 52], network attack packets [24], and exploits [55, 58].”