5 papers
Toward Continuous Assurance for the Democratization of AI Agent Creation in Industry
Natan Levy, Harel Berger
AI agents are increasingly created inside organizations by non-engineering users through low-code, no-code, and conversational development environments. This democratization enable…
Measuring and Evaluating the Performance of Generative AI Models for Scam Detection
Cem Topcuoglu, Seyed Ali Akhavani, Harel Berger +5
Online scams continue to cause substantial financial and personal harm. As a result, detection systems based on Large Language Models (LLMs) have been integrated into security prod…
Poster: Mind the Gap -- Characterizing the Temporal Blind Spot Between GSB and DNS Resolution
Tomer Gal, Fujiao Ji, Doowon Kim +1
Google Safe Browsing (GSB) and DNS resolution operate concurrently during browser navigation, yet their packet-level synchronization remains understudied. This work characterizes t…
POPS: From History to Mitigation of DNS Cache Poisoning Attacks
Yehuda Afek, Harel Berger, Anat Bremler-Barr
We present a novel yet simple and comprehensive DNS cache POisoning Prevention System (POPS), designed to integrate as a module in Intrusion Prevention Systems (IPS). POPS addresse…
Measuring DNS Censorship of Generative AI Platforms
Harel Berger, Yuval Shavitt
Generative AI is an invaluable tool, however, in some parts of the world, this technology is censored due to political or societal issues. In this work, we monitor Generative AI ce…