4 papers · 1 filter
Towards Reliable Local Security Agents: Verifiable Post-Training for Linux Privilege Escalation
Philipp Normann, Andreas Happe, Jürgen Cito +1
LLM agents are becoming increasingly important in the security domain, but leading systems are often closed-source, cloud-based, hard to reproduce or use with sensitive code. This…
Beyond the TESSERACT:Trustworthy Dataset Curation for Sound Evaluations of Android Malware Classifiers
Theo Chow, Mario D'Onghia, Lorenz Linhardt +4
The reliability of machine learning critically depends on dataset quality. While machine learning applied to computer vision and natural language processing benefits from high-qual…
Chasing Shadows: Pitfalls in LLM Security Research
Jonathan Evertz, Niklas Risse, Nicolai Neuer +12
Large language models (LLMs) are increasingly prevalent in security research. Their unique characteristics, however, introduce challenges that undermine established paradigms of re…
Intriguing Properties of Adversarial ML Attacks in the Problem Space [Extended Version]
Jacopo Cortellazzi, Feargus Pendlebury, Daniel Arp +3
Recent research efforts on adversarial machine learning (ML) have investigated problem-space attacks, focusing on the generation of real evasive objects in domains where, unlike im…