4 papers
MATRA: Modeling the Attack Surface of Agentic AI Systems -- OpenClaw Case Study
Tim Van hamme, Thomas Vissers, Javier Carnerero-Cano +4
LLMs are increasingly deployed as autonomous agents with access to tools, databases, and external services, yet practitioners (across different sectors) lack systematic methods to…
The Alpha Blending Hypothesis: Compositing Shortcut in Deepfake Detection
Andrii Yermakov, Jan Cech, Mario Fritz +1
Recent deepfake detection methods demonstrate improved cross-dataset generalization, yet the underlying mechanisms remain underexplored. We introduce the Alpha Blending Hypothesis,…
MaxSup: Overcoming Representation Collapse in Label Smoothing
Yuxuan Zhou, Heng Li, Zhi-Qi Cheng +4
Label Smoothing (LS) is widely adopted to reduce overconfidence in neural network predictions and improve generalization. Despite these benefits, recent studies reveal two critical…
Balancing Diversity and Risk in LLM Sampling: How to Select Your Method and Parameter for Open-Ended Text Generation
Yuxuan Zhou, Margret Keuper, Mario Fritz
Sampling-based decoding strategies have been widely adopted for Large Language Models (LLMs) in numerous applications, targeting a balance between diversity and quality via tempera…