activity
20242026
collaborators

5 papers

cs.CR2026

Honeyval: A Comprehensive Evaluation Framework for LLM-powered HTTP Honeypots

Mark Vero, Fabian Kaczmarczyck, Ivan Petrov +6

Honeypots are decoy systems mimicking real system components designed to defend against cyber attacks. Recently, LLMs increasingly serve as simulation backbones for honeypots. They…

cs.CR2026

ExploitGym: Can AI Agents Turn Security Vulnerabilities into Real Attacks?

Zhun Wang, Nico Schiller, Hongwei Li +13

AI agents are rapidly gaining capabilities that could significantly reshape cybersecurity, making rigorous evaluation urgent. A critical capability is exploitation: turning a vulne…

cs.CR2025

Evaluating the Robustness of a Production Malware Detection System to Transferable Adversarial Attacks

Milad Nasr, Yanick Fratantonio, Luca Invernizzi +7

As deep learning models become widely deployed as components within larger production systems, their individual shortcomings can create system-level vulnerabilities with real-world…

cs.CR2024

Magika: AI-Powered Content-Type Detection

Yanick Fratantonio, Luca Invernizzi, Loua Farah +9

The task of content-type detection -- which entails identifying the data encoded in an arbitrary byte sequence -- is critical for operating systems, development, reverse engineerin…

cs.CR2024

Give and Take: An End-To-End Investigation of Giveaway Scam Conversion Rates

Enze Liu, George Kappos, Eric Mugnier +6

Scams -- fraudulent schemes designed to swindle money from victims -- have existed for as long as recorded history. However, the Internet's combination of low communication cost, g…