Misleading worm signature generators using deliberate noise injection

By Roberto Perdisci, David Dagon, Wenke Lee, Prahlad Fogla, Monirul I. Sharif. 2006

207 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Networks and Communications, 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 Artificial Intelligence

In Computer Networks and Communications

In Privacy & Security

In Signal Processing

Citations in the corpus

Towards the Science of Security and Privacy in Machine Learning (2016, background): “For instance, Perdisci et al. prevented Polygraph, a worm signature generation tool [48], from learning meaningful signatures by inserting perturbations in worm trafﬁc ﬂows [49].”
Manipulating Machine Learning: Poisoning Attacks and Countermeasures for Regression Learning (2018, background): “Such poisoning attacks have been practically demonstrated in worm signature generation [42], [45], spam”
Stealing Hyperparameters in Machine Learning (2018, background): “Existing studies have demonstrated poisoning attacks to worm signature generators [34], [41], [35], spam ﬁlters [31], [32], anomaly detectors [43], [24], SVMs [5], face recognition methods [4], as well as recommender systems [27], [57].”
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]…”
DeepXplore: Automated Whitebox Testing of Deep Learning Systems (2017, background): “Recently, the security and privacy aspects of machine learning have drawn significant attention from the researchers in both machine learning [26, 49, 72] and security [12, 21, 22, 55, 63, 74, 82] communities.”
Yes, Machine Learning Can Be More Secure! A Case Study on Android Malware Detection (2017, neutral): “quently cause misclassification errors [7], [11], [25], [32], [34], [42], [43], [44], [45].”
Security analysis of online centroid anomaly detection (2010, background): “However, it remains largely unclear whether machine learning methods can be protected against adversarial impact.”
Paragraph: Thwarting Signature Learning by Training Maliciously (2006, positive): “independently and concurrently propose attacks [18] against the learning algorithms presented in Polygraph [15].”
SoK: Security and Privacy in Machine Learning (2018, neutral): “prevented Polygraph, a worm signature generation tool [60], from learning meaningful signatures by inserting perturbations in worm traffic flows [61].”
Towards Making Systems Forget with Machine Unlearning (2015, background): “This derived data can recursively derive more data, such as a recommendation system predicting a user’s rating of a movie based on movie similarities.”
Adversarial attacks against intrusion detection systems: Taxonomy, solutions and open issues (2013, background): “This attack can be exploited to introduce errors in the classification model and significantly reduce its accuracy [116], [105], [27], [131], [81].”
Advanced Allergy Attacks: Does a Corpus Really Help? (2007, methodology): “In fact, the studies in [16] found that 0.”
On the Effectiveness of Mitigating Data Poisoning Attacks with Gradient Shaping (2020, background): “e attacker inserts poison in the victim’s training set to induce it into learning a model whose behavior is advantageous to the attacker. Data poisoning has been demonstrated in malware classiﬁcation [32,47], spam ﬁltering [30], and DoS detection [34]. Poisoning has sparked an arms race between prop”
Hamsa: fast signature generation for zero-day polymorphic worms with provable attack resilience (2006, background): “However, the recent work [20] propose an approach which could inject arbitrary amount of noise into the suspicious pool.”
Multiple classifier systems for robust classifier design in adversarial environments (2010, methodology): “Specific countermeasures were proposed for IDSs in [43,16], as well as methods to improve the robustness of specific classification algorithms.”
Why Do Adversarial Attacks Transfer? Explaining Transferability of Evasion and Poisoning Attacks (2018, background): “In poisoning availability attacks, the attacker controls a certain amount of training data, thus influencing the trained model and ultimately the predictions at testing time on most points in testing set [4,18,20,28–30,34,36,41,48].”
Allergy Attack Against Automatic Signature Generation (2006, background): “Similar to [3,8,10], our work focuses on certain weakness common to many ASG systems.”
Machine learning in adversarial environments (2010, background): “In addition, a theoretical analysis of robustness of certain learning algorithms against specific attacks has been carried out in recent work (Nelson et al. 2010; Kloft and Laskov 2010).”
Automatic analysis of malware behavior using machine learning (2011, unknown): “Hence, the most promising evasion attack against our framework corresponds to triggering fake and real malicious behavior during individual executions, similar to evasion techniques against signature generation [44,67].”
Evaluation and Design of Robust Neural Network Defenses (2018, background): “[106] who show it is possible to construct malware samples so that if one controls 50% of the training data, it is possible to make the signature generator”