76 citations · 257 across the 98 of their papers we have counts for
117 papers
Pin It on Anyone: Certified Targeted Displacement of Multi-Bit LLM Watermarks Without the Key
Paweł Batorski, Przemysław Spurek, Paul Swoboda
Multi-bit watermarking embeds a message, typically an account identifier, into LLM output so that harmful text can be traced to its origin. We show an attack technique that allows…
CLASP: Continual Low-rank Adapters for Spatially Placed Concepts from One Hypernetwork
Wojciech Gromski, Patryk Krukowski, Jan Miksa +2
Continual personalization of text-to-image diffusion models requires sequentially acquiring new concepts while retaining previously learned ones. However, existing methods either s…
STAGE: Subspace-Targeted Affine Generative Erasure for Text-to-3D Models
Karol Dziekan, Przemysław Spurek, Dawid Malarz
Concept erasure suppresses a target concept while preserving behavior on unrelated inputs. Existing closed-form methods were designed for 2D image diffusion and assume a single gen…
FOMO: Forget the Concept, Don't Miss Out on the Scene in Selective Video Unlearning
Łukasz Rudnik, Agnieszka Polowczyk, Alicja Polowczyk +1
The rapid advancement of generative video models has enabled the synthesis of increasingly realistic and temporally coherent videos, while also raising concerns about the generatio…
LLM unbranding: Erasing Commercial Identity while Preserving Generic Utility
Kajetan Ożóg, Alicja Wojciechowska, Dawid Malarz +3
Establishing unbranding as a critical practice to prevent visual logos from acquiring negative connotations is standard in image generation. Large Language Models (LLMs) now face a…
CertMark: Distortion-Free Multi-Bit Watermarking with Certified Decoding
Paweł Batorski, Przemysław Spurek, Paul Swoboda
Leading multi-bit watermarking methods for language models encode messages by biasing the model's next-token probabilities, creating a trade-off between message recovery and text q…