Robin Staab

LLM Fingerprinting via Semantically Conditioned Watermarks

Watch your steps: Dormant Adversarial Behaviors that Activate upon LLM Finetuning

Fewer Weights, More Problems: A Practical Attack on LLM Pruning

Watermarking Diffusion Language Models

Pay Attention to the Triggers: Constructing Backdoors That Survive Distillation

Adaptive Generation of Bias-Eliciting Questions for LLMs

MixAT: Combining Continuous and Discrete Adversarial Training for LLMs

Black-Box Detection of Language Model Watermarks

Ward: Provable RAG Dataset Inference via LLM Watermarks

Discovering Spoofing Attempts on Language Model Watermarks

Mind the Gap: A Practical Attack on GGUF Quantization

Language Models are Advanced Anonymizers

Discovering Clues of Spoofed LM Watermarks