activity
20092025
most citedDetecting Backdoor Attacks on Deep Neural Networks by Activation Clustering

228 citations · 329 across the 13 of their papers we have counts for

collaborators
Showing cs.CLShow all

1 paper · 1 filter

cs.CL2025

Toward Cybersecurity-Expert Small Language Models

Matan Levi, Daniel Ohayon, Ariel Blobstein +3

Large language models (LLMs) are transforming everyday applications, yet deployment in cybersecurity lags due to a lack of high-quality, domain-specific models and training dataset…