Obliviate: Erasing Concepts from Autoregressive Image Generation Models

• URL: http://arxiv.org/abs/2606.28643v1
• Date: Fri, 26 Jun 2026 22:56:54 GMT
• Title: Obliviate: Erasing Concepts from Autoregressive Image Generation Models
• Abstract summary: We introduce Obliviate, a guidance-based concept erasure method for autoregressive image generation.<n>We evaluate Obliviate on three state-of-the-art autoregressive text-to-image models, Liquid, Emu3-Gen, and Janus-Pro.<n>Obliviate consistently outperforms current alternatives, reducing nudity on the defensive RAB benchmark from 91.58 to 3.15 while preserving overall model utility.
• Score: 6.871083333377967
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The widespread adoption of generative AI models has intensified concerns about misuse, including the creation of unsafe or disturbing imagery. To mitigate such issues, several concept erasure approaches have been proposed to remove harmful content from multimodal generative models. Yet concept erasure for autoregressive image generation remains largely unexplored, despite the growing relevance of these models in recent trends toward unified multimodal architectures. In this work, we fill this gap by introducing Obliviate, a guidance-based concept erasure method for autoregressive image generation. Our method builds on three key design choices: KL-based supervision over visual token distributions, trajectory-level updates over full autoregressive rollouts, and aligned visual prefixes for stable target construction. We evaluate Obliviate on three state-of-the-art autoregressive text-to-image models, Liquid, Emu3-Gen, and Janus-Pro, covering the erasure of explicit content, graphic violence, and branded imagery. Obliviate consistently outperforms current alternatives, reducing nudity on the defensive RAB benchmark from 91.58 to 3.15 while preserving overall model utility.

Related papers

• Concept Removal for Frontier Image Generative Models [24.385258118583767]
  We introduce a novel concept removal method for frontier diffusion and image autoregressive models.<n>Our intervention replaces the internal bottleneck layer with a transcoder that is trained to replicate the original layer.<n> Empirically, the approach achieves state-of-the-art concept removal performance across modern diffusion and autoregressive models.
  arXiv  Detail & Related papers  (2026-06-24T08:25:30Z)
• CGCE: Classifier-Guided Concept Erasure in Generative Models [53.7410000675294]
  Concept erasure has been developed to remove undesirable concepts from pre-trained models.<n>Existing methods remain vulnerable to adversarial attacks that can regenerate the erased content.<n>We introduce an efficient plug-and-play framework that provides robust concept erasure for diverse generative models.
  arXiv  Detail & Related papers  (2025-11-08T05:38:18Z)
• VCE: Safe Autoregressive Image Generation via Visual Contrast Exploitation [57.36681904639463]
  Methods to safeguard autoregressive text-to-image models remain underexplored.<n>We propose Visual Contrast Exploitation (VCE), a novel framework that precisely decouples unsafe concepts from their associated content semantics.<n>Our experiments demonstrate that our method effectively secures the model, achieving state-of-the-art results while erasing unsafe concepts and maintaining the integrity of unrelated safe concepts.
  arXiv  Detail & Related papers  (2025-09-21T09:00:27Z)
• Robust Concept Erasure in Diffusion Models: A Theoretical Perspective on Security and Robustness [4.23067546195708]
  textbfSCORE (Secure and Concept-Oriented Robust Erasure) is a novel framework for robust concept removal in diffusion models.<n>SCORE sets a new standard for secure and robust concept erasure in diffusion models.
  arXiv  Detail & Related papers  (2025-09-15T15:05:50Z)
• Minimalist Concept Erasure in Generative Models [29.548315937553756]
  We develop a novel minimalist concept erasure objective based emphonly on the distributional distance of final generation outputs.<n>To improve the robustness of the erasure, we incorporate neuron masking as an alternative to model fine-tuning.<n> Empirical evaluations on state-of-the-art flow-matching models demonstrate that our method robustly erases concepts without degrading overall model performance.
  arXiv  Detail & Related papers  (2025-07-16T00:32:14Z)
• Can We Generate Images with CoT? Let's Verify and Reinforce Image Generation Step by Step [86.69947123512836]
  Chain-of-Thought (CoT) reasoning has been extensively explored in large models to tackle complex understanding tasks.<n>We provide the first comprehensive investigation of the potential of CoT reasoning to enhance autoregressive image generation.<n>We propose the Potential Assessment Reward Model (PARM) and PARM++, specialized for autoregressive image generation.
  arXiv  Detail & Related papers  (2025-01-23T18:59:43Z)
• Safety Without Semantic Disruptions: Editing-free Safe Image Generation via Context-preserving Dual Latent Reconstruction [88.18235230849554]
  Training multimodal generative models on large, uncurated datasets can result in users being exposed to harmful, unsafe and controversial or culturally-inappropriate outputs.<n>We leverage safe embeddings and a modified diffusion process with weighted tunable summation in the latent space to generate safer images.<n>We identify trade-offs between safety and censorship, which presents a necessary perspective in the development of ethical AI models.
  arXiv  Detail & Related papers  (2024-11-21T09:47:13Z)
• Reliable and Efficient Concept Erasure of Text-to-Image Diffusion Models [76.39651111467832]
  We introduce Reliable and Efficient Concept Erasure (RECE), a novel approach that modifies the model in 3 seconds without necessitating additional fine-tuning. To mitigate inappropriate content potentially represented by derived embeddings, RECE aligns them with harmless concepts in cross-attention layers. The derivation and erasure of new representation embeddings are conducted iteratively to achieve a thorough erasure of inappropriate concepts.
  arXiv  Detail & Related papers  (2024-07-17T08:04:28Z)
• Towards Safe Self-Distillation of Internet-Scale Text-to-Image Diffusion Models [63.20512617502273]
  We propose a method called SDD to prevent problematic content generation in text-to-image diffusion models. Our method eliminates a much greater proportion of harmful content from the generated images without degrading the overall image quality.
  arXiv  Detail & Related papers  (2023-07-12T07:48:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.