4 citations · 16 across the 16 of their papers we have counts for
Showing cs.CRShow all
2 papers · 1 filter
cs.CR2025
Fast Proxies for LLM Robustness Evaluation
Tim Beyer, Jan Schuchardt, Leo Schwinn +1
Evaluating the robustness of LLMs to adversarial attacks is crucial for safe deployment, yet current red-teaming methods are often prohibitively expensive. We compare the ability o…
cs.CR2024
Unified Mechanism-Specific Amplification by Subsampling and Group Privacy Amplification
Jan Schuchardt, Mihail Stoian, Arthur Kosmala +1
Amplification by subsampling is one of the main primitives in machine learning with differential privacy (DP): Training a model on random batches instead of complete datasets resul…