Large language models are finetuned to refuse questions about hazardous knowledge, but
these protections can often be bypassed. Unlearning methods aim at completely removing …

In the past decade, considerable research effort has been devoted to securing machine
learning (ML) models that operate in adversarial settings. Yet, progress has been slow even …

Text-to-image diffusion models have emerged as powerful tools for generating high-quality
images from textual descriptions. However, their increasing popularity has raised significant …

Recent advances in diffusion models have significantly enhanced the quality of image
synthesis, yet they have also introduced serious safety concerns, particularly the generation …

Over the past decade, adversarial training has emerged as one of the few reliable methods
for enhancing model robustness against adversarial attacks [Szegedy et al., 2014, Madry et …

Singing voice conversion (SVC) automates song covers by converting a source singing
voice from a source singer into a new singing voice with the same lyrics and melody as the …

Building secure and robust AI models has proven to be difficult. Nearly all defenses,
including those published at top-tier venues and recognized with prestigious awards, can be …

The outstanding capability of diffusion models in generating high-quality images poses
significant threats when misused by adversaries. In particular, we assume malicious …