digital content compliance teams

Abstract: Concept erasure is essential for the safe deployment of text-to-image diffusion models, as they may reproduce harmful, copyrighted, or privacy-sensitive content learned from unconstrained large-scale data. Existing methods typically erase unwanted concepts while preserving general generation capability by redirecting target-related text-to-image mappings. However, recent studies show that erased models may still retain visual generative trajectories of target concepts, leaving them vulnerable to adversarial recovery attacks and revealing a fundamental gap between redirecting text-to-image mappings and truly removing visual knowledge. To bridge this gap, we propose VisualErase, a new paradigm that redirects concept-bearing visual generative trajectories toward explicitly defined concept-removed outcomes. To enable this redirection, we use structure-preserving image editing to construct content-aligned, concept-removed counterparts for source images, providing explicit visual endpoints that retain non-target content. We then derive a denoising target from each source-to-counterpart pair and use a dual-branch redirection loss to align both text-conditioned and unconditional predictions with this target, since conditional supervision alone does not explicitly constrain generation without textual guidance. To mitigate the adverse effects of concept erasure on non-target generation, we jointly optimize the redirection loss with a counterpart retention loss that matches denoising predictions from the frozen pretrained model. Across style, celebrity, and nudity erasure, VisualErase limits the maximum attack success rate over seven attacks to 0%, 8%, and 0.1%, respectively, while retaining general generation quality. These results highlight the importance of visual trajectory redirection for robust concept erasure beyond text-to-image mappings alone.

Abstract: AI labels are emerging as a primary safeguard for transparency about AI-generated content on social media, including under the EU Digital Services Act and AI Act. Yet, limited systematic evidence exists on how platforms implement such labels in practice. We conduct a legally grounded audit of AI labelling across Instagram, TikTok, X, and YouTube, drawing on the European Commission's July 2026 guidelines on deepfakes. To this end, we analyse platform policies and detection approaches, 10,722 posts collected via systemic-risk and AI-related keywords, an expert-annotated subset of 500 posts, and controlled uploads to the four platforms of outputs from ten popular generative AI tools. We find that AI labelling is now broadly established. All four platforms apply labels automatically and a greater share of labels are platform-applied than in earlier audits. However, coverage remains incomplete where labelling arguably matters most: only 33% of expert-identified deepfakes in systemic risk contexts carried a platform-applied AI label, while reaching a median of 160,000 views. In controlled uploads of AI-generated content carrying standard AI provenance signals, platforms labelled only 61% of uploads, and commonly strip those signals after uploading. Overall, platform rules, label designs, detection approaches, and reporting diverge substantially. In response, we identify concrete opportunities to improve the uptake, clarity and efficacy of AI labelling.