no code implementations • 8 May 2023 • Tamás Vörös, Sean Paul Bergeron, Konstantin Berlin
We introduce a state-of-the-art approach for URL categorization that leverages the power of Large Language Models (LLMs) to address the primary objectives of web content filtering: safeguarding organizations from legal and ethical risks, limiting access to high-risk or suspicious websites, and fostering a secure and professional work environment.
no code implementations • 13 Feb 2023 • Ben Gelman, Salma Taoufiq, Tamás Vörös, Konstantin Berlin
In place of in-house solutions, organizations are increasingly moving towards managed services for cyber defense.
no code implementations • 13 Oct 2021 • Awalin Sopan, Konstantin Berlin
Development of new machine learning models is typically done on manually curated data sets, making them unsuitable for evaluating the models' performance during operations, where the evaluation needs to be performed automatically on incoming streams of new data.
no code implementations • 26 Feb 2020 • Konstantin Berlin, Ajay Lakshminarayanarao
Generating up to date, well labeled datasets for machine learning (ML) security models is a unique engineering challenge, as large data volumes, complexity of labeling, and constant concept drift makes it difficult to generate effective training datasets.
1 code implementation • 16 May 2019 • Adarsh Kyadige, Ethan M. Rudd, Konstantin Berlin
In this paper, we propose utilizing a static source of contextual information -- the path of the PE file -- as an auxiliary input to the classifier.
2 code implementations • 15 May 2019 • Felipe N. Ducau, Ethan M. Rudd, Tad M. Heppner, Alex Long, Konstantin Berlin
With the rapid proliferation and increased sophistication of malicious software (malware), detection methods no longer rely only on manually generated signatures but have also incorporated more general approaches like machine learning detection.
1 code implementation • 13 Mar 2019 • Ethan M. Rudd, Felipe N. Ducau, Cody Wild, Konstantin Berlin, Richard Harang
In this work, we fit deep neural networks to multiple additional targets derived from metadata in a threat intelligence feed for Portable Executable (PE) malware and benignware, including a multi-source malicious/benign loss, a count loss on multi-source detections, and a semantic malware attribute tag loss.
2 code implementations • 27 Feb 2017 • Joshua Saxe, Konstantin Berlin
For years security machine learning research has promised to obviate the need for signature based detection by automatically learning to detect indicators of attack.
4 code implementations • 13 Aug 2015 • Joshua Saxe, Konstantin Berlin
Further, we confirm our false positive rates directly on a live stream of files coming in from Invincea's deployed endpoint solution, provide an estimate of how many new binary files we expected to see a day on an enterprise network, and describe how that relates to the false positive rate and translates into an intuitive threat score.
Cryptography and Security