Kavli Affiliate: Zheng Zhu
| First 5 Authors: Nanxiang Jiang, Nanxiang Jiang, , ,
| Summary:
Recent advances in text-to-image (T2I) diffusion models have enabled
impressive generative capabilities, but they also raise significant safety
concerns due to the potential to produce harmful or undesirable content. While
concept erasure has been explored as a mitigation strategy, most existing
approaches and corresponding attack evaluations are tailored to Stable
Diffusion (SD) and exhibit limited effectiveness when transferred to
next-generation rectified flow transformers such as Flux. In this work, we
present ReFlux, the first concept attack method specifically designed to assess
the robustness of concept erasure in the latest rectified flow-based T2I
framework. Our approach is motivated by the observation that existing concept
erasure techniques, when applied to Flux, fundamentally rely on a phenomenon
known as attention localization. Building on this insight, we propose a simple
yet effective attack strategy that specifically targets this property. At its
core, a reverse-attention optimization strategy is introduced to effectively
reactivate suppressed signals while stabilizing attention. This is further
reinforced by a velocity-guided dynamic that enhances the robustness of concept
reactivation by steering the flow matching process, and a
consistency-preserving objective that maintains the global layout and preserves
unrelated content. Extensive experiments consistently demonstrate the
effectiveness and efficiency of the proposed attack method, establishing a
reliable benchmark for evaluating the robustness of concept erasure strategies
in rectified flow transformers.
| Search Query: ArXiv Query: search_query=au:”Zheng Zhu”&id_list=&start=0&max_results=3