Zobrazeno 1 - 10
of 22
pro vyhledávání: '"Kantchelian, A."'
Autor:
Kantchelian, Alex, Neo, Casper, Stevens, Ryan, Kim, Hyungwon, Fu, Zhaohao, Momeni, Sadegh, Huber, Birkett, Bursztein, Elie, Pavlidis, Yanis, Buthpitiya, Senaka, Cochran, Martin, Poletto, Massimiliano
We present Facade (Fast and Accurate Contextual Anomaly DEtection): a high-precision deep-learning-based anomaly detection system deployed at Google (a large technology company) as the last line of defense against insider threats since 2018. Facade i
Externí odkaz:
http://arxiv.org/abs/2412.06700
Autor:
Huber, Birkett, Neo, Casper, Sampson, Keiran, Kantchelian, Alex, Ksobiech, Brett, Pavlidis, Yanis
We present a method to detect departures from business-justified workflows among support agents. Our goal is to assist auditors in identifying agent actions that cannot be explained by the activity within their surrounding context, where normal activ
Externí odkaz:
http://arxiv.org/abs/2411.02645
Autor:
Miller, Brad, Kantchelian, Alex, Tschantz, Michael Carl, Afroz, Sadia, Bachwani, Rekha, Faizullabhoy, Riyaz, Huang, Ling, Shankar, Vaishaal, Wu, Tony, Yiu, George, Joseph, Anthony D., Tygar, J. D.
We present and evaluate a large-scale malware detection system integrating machine learning with expert reviewers, treating reviewers as a limited labeling resource. We demonstrate that even in small numbers, reviewers can vastly improve the system's
Externí odkaz:
http://arxiv.org/abs/1510.07338
Classifier evasion consists in finding for a given instance $x$ the nearest instance $x'$ such that the classifier predictions of $x$ and $x'$ are different. We present two novel algorithms for systematically computing evasions for tree ensembles suc
Externí odkaz:
http://arxiv.org/abs/1509.07892
Publikováno v:
ACM Conference on Computer and Communications Security
Miscreants register thousands of new domains every day to launch Internet-scale attacks, such as spam, phishing, and drive-by downloads. Quickly and accurately determining a domain's reputation (association with malicious activity) provides a powerfu
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::cd99d411cd792987499bdd7d23d39c35
https://doi.org/10.1145/2976749.2978317
https://doi.org/10.1145/2976749.2978317
Autor:
Ling Huang, Rekha Bachwani, J. D. Tygar, Brad Miller, Tony Wu, Alex Kantchelian, Vaishaal Shankar, Michael Carl Tschantz, George Yiu, Riyaz Faizullabhoy, Sadia Afroz, Anthony D. Joseph
Publikováno v:
Detection of Intrusions and Malware, and Vulnerability Assessment ISBN: 9783319406664
DIMVA
DIMVA
We present and evaluate a large-scale malware detection system integrating machine learning with expert reviewers, treating reviewers as a limited labeling resource. We demonstrate that even in small numbers, reviewers can vastly improve the system's
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::df1eddae9141726e2a08abf7377e73d7
https://doi.org/10.1007/978-3-319-40667-1_7
https://doi.org/10.1007/978-3-319-40667-1_7
Autor:
Sadia Afroz, Rekha Bachwani, J. D. Tygar, Anthony D. Joseph, Brad Miller, Vaishaal Shankar, Alex Kantchelian, Michael Carl Tschantz
Publikováno v:
AISec@CCS
We examine the problem of aggregating the results of multiple anti-virus (AV) vendors' detectors into a single authoritative ground-truth label for every binary. To do so, we adapt a well-known generative Bayesian model that postulates the existence
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4425f69166ee71e2c64c1739aca6e887
https://doi.org/10.1145/2808769.2808780
https://doi.org/10.1145/2808769.2808780
Autor:
Edwin Dauber, Ling Huang, Rekha Bachwani, Brad Miller, Alex Kantchelian, Michael Carl Tschantz, J. D. Tygar, Sadia Afroz, Anthony D. Joseph
Publikováno v:
AISec@CCS
Active learning is an area of machine learning examining strategies for allocation of finite resources, particularly human labeling efforts and to an extent feature extraction, in situations where available data exceeds available resources. In this o
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f397fbcd6401ab9f406397f88d8bc1e2
https://doi.org/10.1145/2666652.2666656
https://doi.org/10.1145/2666652.2666656
Autor:
Aylin Caliskan Islam, Sadia Afroz, J. D. Tygar, Michael Carl Tschantz, Rachel Greenstadt, Brad Miller, Anthony D. Joseph, Alex Kantchelian, Ling Huang
Publikováno v:
AISec
In this position paper, we argue that to be of practical interest, a machine-learning based security system must engage with the human operators beyond feature engineering and instance labeling to address the challenge of drift in adversarial environ
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::38ecf8863923773c2ac00f08269672f3
https://doi.org/10.1145/2517312.2517320
https://doi.org/10.1145/2517312.2517320
Publikováno v:
AISec
In this work, we design a method for blog comment spam detection using the assumption that spam is any kind of uninformative content. To measure the "informativeness" of a set of blog comments, we construct a language and tokenization independent met
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a3cf323000a496f43914f53e490d790a
https://doi.org/10.1145/2381896.2381907
https://doi.org/10.1145/2381896.2381907