Hierarchical randomized smoothing
Y Scholten, J Schuchardt… - Advances in …, 2024 - proceedings.neurips.cc
Real-world data is complex and often consists of objects that can be decomposed into
multiple entities (eg images into pixels, graphs into interconnected nodes). Randomized …
multiple entities (eg images into pixels, graphs into interconnected nodes). Randomized …
RS-Del: Edit distance robustness certificates for sequence classifiers via randomized deletion
Randomized smoothing is a leading approach for constructing classifiers that are certifiably
robust against adversarial examples. Existing work on randomized smoothing has focused …
robust against adversarial examples. Existing work on randomized smoothing has focused …
Soft prompt threats: Attacking safety alignment and unlearning in open-source llms through the embedding space
Current research in adversarial robustness of LLMs focuses on discrete input manipulations
in the natural language space, which can be directly transferred to closed-source models …
in the natural language space, which can be directly transferred to closed-source models …