Where Concept Erasure Should Occur: Concept-Layer Alignment in Text-to-Video Diffusion Models
Text-to-video diffusion transformers encode semantic information unevenly across model depth, which constrains effective concept erasure. We identify a representational bottleneck, termed concept-layer topological alignment, under which target concepts exhibit higher separability at certain representational depths. Outside these depths, concept and non-target signals remain strongly entangled, limiting the effectiveness of depth-specific erasure. This observation reframes concept erasure as the problem of identifying representational depths where concept-non-target separation naturally emerges. Motivated by this structural constraint, we introduce CLEAR, a separability-driven optimization framework for concept erasure that explicitly enforces concept-layer alignment. CLEAR operationalizes this principle by formulating layer selection as an optimization problem over concept-non-target separability, rather than relying on layer-agnostic or heuristic choices. To enable this, we introduce a separability-aware objective that favors layers exhibiting stronger concept-non-target separation. Experiments on large-scale text-to-video diffusion models demonstrate that enforcing concept--layer alignment leads to more precise concept suppression while preserving overall generative quality.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
CRCE: Coreference-Retention Concept Erasure in Text-to-Image Diffusion Models
Text-to-Image diffusion models can produce undesirable content that necessitates concept erasure. However, existing methods struggle with under-erasure, leaving residual traces of targeted concepts, or over-erasure, mist…
MANCE: Manifold Aware Concept Erasure
Concept erasure aims to remove a target concept from a representation while preserving the other information encoded in it. This is difficult because representations encode many concepts that are often correlated with th…
On Defining Erasure Harms for NLP
The deployment of NLP systems has raised concerns about harms they might produce, including representational harms. Recent literature has begun to conceptualize and measure one such harm, the harm of erasure. Nevertheles…
Co-occurring associated retained concepts in Diffusion Unlearning
Unlearning has emerged as a key technique to mitigate harmful content generation in diffusion models. However, existing methods often remove not only the target concept, but also benign co-occurring concepts. As illustra…
Semantic Surgery: Zero-Shot Concept Erasure in Diffusion Models
Concept erasure in text-to-image diffusion models is crucial for mitigating harmful content, yet existing methods often compromise generative quality. We introduce Semantic Surgery, a novel training-free, zero-shot frame…
Text-to-Image Generation