5 papers
Security-by-Design for LLM-Based Code Generation: Leveraging Internal Representations for Concept-Driven Steering Mechanisms
Maximilian Wendlinger, Daniel Kowatsch, Konstantin Böttinger +1
Large Language Models (LLMs) show remarkable capabilities in understanding natural language and generating complex code. However, as practitioners adopt CodeLLMs for increasingly c…
Societal Alignment Frameworks Can Improve LLM Alignment
Karolina Stańczak, Nicholas Meade, Mehar Bhatia +14
Recent progress in large language models (LLMs) has focused on producing responses that meet human expectations and align with shared values - a process coined alignment. However,…
DeePen: Penetration Testing for Audio Deepfake Detection
Nicolas Müller, Piotr Kawa, Adriana Stan +5
Deepfakes - manipulated or forged audio and video media - pose significant security risks to individuals, organizations, and society at large. To address these challenges, machine…
Harder or Different? Understanding Generalization of Audio Deepfake Detection
Nicolas M. Müller, Nicholas Evans, Hemlata Tak +2
Recent research has highlighted a key issue in speech deepfake detection: models trained on one set of deepfakes perform poorly on others. The question arises: is this due to the c…
Adversarial Vulnerability of Active Transfer Learning
Nicolas M. Müller, Konstantin Böttinger
Two widely used techniques for training supervised machine learning models on small datasets are Active Learning and Transfer Learning. The former helps to optimally use a limited…