Safe T2I Generation

Recent Text-to-Image (T2I) models achieve remarkable visual image generation performance, but they can still generate NSFW (Not-Safe-For-Work) contents, including violent or explicit images. Existing safety checker mechanisms are largely confined to pre-generation filtering (e.g. prompt-level text classifiers) or post-hoc moderation applied after an image is completely synthesized. However, adversarial attack methods operate over a much broader space. This imbalance highlights the need for a safety mechanism that intervenes during the generation process. We propose an in-generation safety framework that monitors the denoising trajectory and detects emerging NSFW signals from intermediate representations. Rather than merely detecting NSFW generations, our method applies reinforcement learning to generate safe images from NSFW prompts. By coupling in-generation detection with controllable steering, our approach mitigates unsafe trajectories even when NSFW signals emerge after generation has already begun. Experiments results show that our method consistently outperforms existing safe image generation methods across both standard and adversarial evaluation sets, while preserving perceptual quality and prompt fidelity. Code will be released upon acceptance.

As state-of-the-art text-to-image flow models achieve near-photorealistic quality, controlling their outputs, e.g., suppressing harmful content while promoting benign alternatives, has become a central challenge. The current steering paradigm consists of adding a global steering vector to selected activations. While functional, a fixed and example-agnostic vector applied uniformly along the entire trajectory cannot adapt to the changing state of the generation and often causes unintended global changes. We introduce Steering Fields, a generalization of steering vectors that adaptively re-estimates the steering direction at each step of the generative process. Steering Fields operate on the noisy states of flow models, expose a continuous trade-off between steering strength and content preservation, and are compositional, enabling the simultaneous induction and inhibition of concepts, setting a new state of the art on safety steering benchmarks. Despite using no explicit spatial masks or object priors, the trajectory-adaptive estimation naturally preserves local structure, in a manner reminiscent of image editing. In fact, Steering Fields can serve as a structure-preserving image-editing technique that achieves state-of-the-art semantic fidelity (CLIP, VQAScore), while remaining model-agnostic and inversion-free.

Modern text-to-image (T2I) models generate high-quality images from arbitrary user prompts, yet they can just as easily produce not-safe-for-work (NSFW) content. Conventional outer guardrails consist of two components: a prompt classifier that checks for risk before generation, and a post-hoc image classifier that checks the fully generated image. In this design, both classifiers operate outside the generation pipeline and do not use the model's own representations. This separation can limit prompt-screening accuracy, while the image-side check runs only after the full generation cost has been spent. Moreover, a flagged prompt can only be rejected, even when it could be adjusted to produce a safe image. In this work, we propose the Inner Guardrail (InGuard), a safety framework that works inside the pipeline on the model's own representations, leaving base-model parameters untouched. First, a risk classifier grades each prompt as unsafe, risky, or benign based on the text encoder's embeddings, with no external language model. Second, SAGE (Soft-gated Asymmetric Guardrail for Embeddings) modifies the embeddings of risky prompts, aiming to return a safe image instead of a refusal. Third, a latent detector checks the one-step clean latent estimate midway through denoising, reaching nearly image-level performance and halting generation when risk is detected. We also construct the RevGen Safety Benchmark to evaluate T2I safety under realistic conditions: 10,000 prompts built through real-image reverse generation, with a rewriting step that supplies controlled intellectual-property (IP) characters, covering graded porn/gore risks, categorical IP risks, and benign negatives. Across five open-weight T2I models, InGuard reaches 97.9-98.8% safety rate, matching or exceeding the outer guardrail, with 57.5-73.5% less benign disturbance, ~3.7x fewer parameters, and 50-55.6% of denoising steps skipped.

Ensuring safety and policy compliance in text-to-image diffusion models remains a critical challenge, as benign or adversarial prompts can often elicit prohibited content, e.g. nudity and protected intellectual property. While training-based unlearning methods are effective, they are computationally expensive and prone to catastrophic interference with general capabilities. Conversely, existing test-time defenses are primarily prompt-centric, relying on modifying textual descriptions only, and overlook the visual signals for detection. In this paper, we propose to leverage the intermediate clean image estimated during the generation process and employ a sparse margin objective to detect prohibited concepts. When a violation is detected, we immediately intervene by optimizing a structured low-rank residual in the text-conditioning space via truncated backpropagation. This design allows weight-preserving detection, keeps non-violating inference latency nearly unchanged as the maximum budget increases, and offers flexibility in safety performance via test-time scaling. Extensive experiments on Stable Diffusion v1.4 and v3.5 across nudity removal, IP protection, and style erasure demonstrate superior performance across suppression, fidelity and preservation compared to prior weight-preserving baselines, providing a scalable and flexible solution for safe generative deployment.

State-of-the-art toxicity detectors for text-to-image generation adopt a one-size-fits-all approach: a single universal model applying fixed safety guidelines to all users. Our empirical evidence shows that these detectors fail to shield marginalized communities: approximately 35% of generated images labeled safe are considered harmful by disability communities. In this position paper, we argue for community-specific toxicity detection (CTD). To demonstrate its feasibility, we collaborate with disability experts to develop safety guidelines for two communities: dwarfism and blind/low vision. Using a dataset of 2,400 annotated T2I-generated images we demonstrate that both large vision-language models and existing general-purpose toxicity detectors catastrophically fail to recognize harmful content under these guidelines in zero-shot settings with F1 score lower than random guessing (F1 0.32 and 0.37). Promisingly, prompt-based adaptation methods (ICL, VQA) substantially improve harm detection performance (GPT-4o: F1 0.50 and 0.78), while parameter-efficient fine-tuning improves smaller models (0.5b-7b with best F1 0.48 and 0.59) with less than 100 demonstrations, but remains sensitive to evolving guidelines. Despite these gains, CTD performance remains far below F1 $\approx 0.9$ achieved for general-purpose toxicity detection, highlighting the challenge and the need for sustained research effort.

State-of-the-art flow based text-to-image (T2I) models exhibit remarkable generative abilities but remain vulnerable to producing unsafe content. Prior safety efforts range from concept erasure and prompt filtering to classifier-based gating. However, simple techniques like parameter efficient adaptations of the models easily bypass such guardrails. We introduce a unique principled approach that achieves safety by regulating the model's attention dynamics through inference-time introspection, exhibiting intrinsic robustness. Our method analyzes and rebalances attention activations throughout image synthesis, steering generations away from unsafe concepts while preserving semantic alignment. This introspective control ensures safety of deployed models. Across standard and adversarial safety benchmarks, our approach achieves remarkable safety scores while maintaining or even improving alignment and perceptual quality. Our results reveal that attention-space regulation offers a considerably more promising path to safer diffusion transformer based image generation than the existing concept erasing mechanism.Our code can be accessed at https://basim-azam.github.io/iam/

Text-to-image diffusion models have achieved high visual fidelity and broad adoption, but remain vulnerable to safety violations when adversaries exploit them to synthesize illicit content. Existing alignment paradigms, from input sanitization to structural feature pruning, are largely organized around unsafe concepts explicitly exposed during filtering, editing, or localization. This leaves a blind spot for visual synonym attacks (VSA), a jailbreak where benign-looking prompts elicit prohibited imagery through implicit visual associations. As a result, current defenses face a safety-utility dilemma: they may either under-mitigate VSA threats or over-suppress visually similar benign concepts. The core challenge is that VSA hides the unsafe target at the textual surface while revealing it through generation-time visual-semantic convergence. In this work, we therefore shift from static suppression of pre-specified unsafe concepts to dynamic tracing of how unsafe semantics emerge during generation. Our mechanistic analysis shows that VSA and explicit unsafe prompts converge through sparse semantic-injecting attention heads, which serve as inference-time bottlenecks for prohibited visual semantics. Based on this insight, we propose AEGIS (Adaptive Evasion Guard via Identification and Steering), an inference-time defense that applies similarity-aware repulsion only at the identified vulnerable heads. Evaluated against 16 baselines, AEGIS improves both safety and utility. On SD 1.4, it reduces ASR to $\mathbf{0.00}/\mathbf{0.03}$ for in-domain violence/nudity VSA and achieves ASRs $\le \mathbf{0.09}$ on out-of-domain explicit and adversarial attacks. It preserves benign fidelity, avoids suppressing hard-negative concepts, and transfers to SD 2.1 and FLUX.1 after re-identifying the critical heads for each backbone.

Safety alignment of text-to-image (T2I) diffusion models aims to suppress harmful generations while preserving utility on benign prompts. Recent methods often appear to deliver high safety with high utility, but this conclusion rests largely on coarse global utility metrics (e.g., FID, CLIPScore) that are insensitive to fine-grained semantic correctness, creating an illusion of high utility. We show that when utility is measured with structured evaluation, this illusion breaks: on TIFA (Text-to-Image Faithfulness evaluation with Question Answering), safety-aligned models suffer substantial drops in semantic fidelity, including failures in object counts, attributes, and relationships. To diagnose the source of this gap, we analyze the text-encoder prompt embedding space and uncover semantic collapse, a contraction of embedding spread coupled with distortion of inter-prompt similarity structure, which strongly correlates with structured utility loss. Guided by this insight, we propose StructureAware Geometric Regularization (SAGE), a safety alignment objective that explicitly preserves embedding spread and inter-prompt relational structure during adaptation. Our method restores structured utility (TIFA +5.0% over prior state-of-the-art) while maintaining strong safety performance and competitive coarse-grained utility scores. Our source code and trained models are available at https://adeelyousaf.github.io/SAGE_ECCV26_Project_Page/.

Concept erasure aims to prevent image generative models from producing unsafe content while preserving their general generative capability. Meanwhile, next-scale autoregressive (AR) image generation has recently emerged as a new generative paradigm characterized by next-scale prediction, for which concept erasure remains largely unexplored. In this paradigm, semantic information is highly compressed at early scales, leading to severe entanglement between unsafe and unrelated semantics. In this paper, we propose ScaleErasure, an inference-time concept erasure method that performs minimal intervention. ScaleErasure precisely selects and guides predicted logits that are most relevant to the unsafe concept, thereby enabling effective erasure under severe semantic entanglement. Specifically, ScaleErasure performs two additional forward passes conditioned on the unsafe concept and the corresponding safe concept, and leverages their outputs to guide the target logits away from unsafe concepts toward safe concepts. To enable precise and minimal intervention, logits selection and guidance are conducted across three dimensions: scales, tokens, and bit channels. Experiments demonstrate that ScaleErasure outperforms adapted baselines in the next-scale AR paradigm, achieving more precise concept erasure while largely preserving general generative capability. The code is available at https://github.com/coziiizz/ScaleErasure.

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.

Unlike diffusion-based models that operate in continuous latent spaces, autoregressive unified multimodal models produce images by sequentially predicting discretized visual tokens. These tokens are derived from a codebook that maps embeddings to quantized visual patterns. The language-like architecture enables unified multimodal models to effectively capture text conditional information for generation, making them promising for text-to-image tasks. This also raises an interesting question: how safe are the images generated in such an autoregressive way? In this work, we propose iterative self-improving codebooks for safe autoregressive generation. We leverage the understanding and judgment capabilities of the unified multimodal model itself to identify unsafe generated images without human annotation. Subsequently, the inherent representations in the codebook are fixed to eliminate harmful mappings. Our method comprises two steps: first, we use the unified model to identify unsafe generations and construct corresponding harmful and safe image-text pairs. These pairs are used to construct the Harmful Space and guide updates to the codebook, thereby eliminating harmful outputs. Second, we perform adaptive fine-tuning on the codebook within the harmless space using safe image-text pairs to ensure the quality of generated images. These two steps are repeated until no further improvement is observed, producing a safety-enhanced model codebook. Without additional external feedback, the safety of models is improved iteratively.

Flow matching has recently emerged as a strong paradigm for state-of-the-art text-to-image (T2I) generation, enabling high-quality generation with a small number of sampling steps. As these models are increasingly integrated into real-world applications, ensuring safe and non-sensitive content generation has become a critical requirement. However, adapting safety and concept removal methods to this new generation framework remains an open challenge. Specifically, prior methods largely rely on iterative trajectory steering across a number of denoising steps or on CLIP-centric prompt embedding manipulation. These design assumptions pose fundamental bottlenecks for safety in flow matching-based T2I generation, where limited sampling steps constrain iterative correction and modern context-aware text encoders diminish the effectiveness of embedding-level interventions. In this paper, we propose VESFlow, a training-free safety method tailored to flow matching with extremely few sampling steps. Leveraging the fact that flow matching models learn the marginal velocity, we directly edit the velocity field via a safe-conditional posterior. VESFlow steers the trajectory toward safe outputs while leaving the conditioning prompt unchanged. Building on the observation that VESFlow leaves outputs unchanged under benign prompts, we further introduce a risk score-based filtering that bypasses velocity editing to reduce computational cost while preserving benign prompt generation. Based on this filtering, we propose VESFlow+, a stronger variant of VESFlow that not only edits the velocity toward the safe direction, but also pushes it away from the unsafe direction. Experimental results show that VESFlow+ removes the target concept, reducing the attack success rate by NudeNet to 6.3% on Ring-A-Bell and 6.8% on MMA-Diffusion on the 4-step MeanFlow model, while preserving fidelity on benign prompts.

With the advance of generative AI, the text-to-image (T2I) model has the ability to generate various contents. However, T2I models still can generate unsafe contents. To alleviate this issue, various concept erasing methods are proposed. However, existing methods tend to excessively erase unsafe concepts and suppress benign concepts contained in harmful prompts, which can negatively affect model utility. In this paper, we focus on eliminating unsafe content while maintaining model capability in safe semantic meaning interpretation by optimizing the concept erasing reward (CER) with reinforcement learning. To avoid overly content erasure, we introduce the Safe Adapter to project partial text embedding for efficient concept regulation in cross-attention layers. Extensive experiments conducted on different datasets demonstrate the effectiveness of the proposed method in alleviating unsafe content generation while preserving the high fidelity of benign images compared with existing state-of-the-art (SOTA) concept erasing methods. In terms of robustness, our method outperforms counterparts against red-teaming tools. Moreover, we showcase the proposed approach is more effective in emerging image-to-image (I2I) scenarios compared with others. Lastly, we extend our method to erase general concepts, such as artistic styles and objects. Disclaimer: This paper includes discussions of sexually explicit content that may be offensive to certain readers. All images used in this work are synthesized or from public datasets.

Diffusion transformers (DiTs) equipped with multimodal attention (MM-Attn) have become a dominant paradigm for image generation. However, preventing the generation of harmful content remains a critical challenge, particularly in image-to-image (I2I) editing tasks. Existing safety mechanisms are primarily designed for text-to-image (T2I) synthesis or U-Net-based architectures, which limits their effectiveness for unified safety mitigation in DiT-based frameworks. To bridge this gap, we propose Unified Visual Safety Regulator (UVR), a training-free safe generation framework that regulates unsafe semantics in generated images. UVR is grounded in an analysis of attention dynamics from the perspective of information flow in MM-Attn. We identify a task-independent start-up stage, during which unsafe semantics in output patches rapidly emerge and can be accurately localized, followed by task-specific semantic amplification and interference stages, where harmful signals are further propagated and entangled with benign content. Based on these observations, UVR mitigates unsafe generation through unified, targeted attention modulation and explicit restriction of harmful information flow over the identified unsafe output patches. Experiments across various concepts show that UVR achieves state-of-the-art safety performance by achieving 91% and 77% erase rate in image synthesis and editing tasks, while preserving visual quality and fidelity with minimal degradation. Code is available at https://github.com/deng12yx/UVR.

Text-to-image models trained on large-scale data often inevitably ingest unsafe content. While some people observe input-output amplifications, it remains unclear whether and how training data composition directly drives model output safety or by other factors. We shed light on this question by isolating this variable: we train the same text-to-image model on datasets that differ \emph{only} in their fraction of unsafe images (0% to 9.6%), across several dataset scales (100K to 8M). Then we generate images with the resulting models, and evaluate them with four independent safety classifiers. Output unsafety rises monotonically from 16.6% at 0% contamination to 25.5% at 5%. A factorial design reveals that the \emph{proportion}, not the absolute count, of unsafe training images is the operative variable. The 16.6% irreducible baseline at zero contamination implicates the other components, e.g. frozen text encoder, as a residual safety risk -- confirmed by a text encoder ablation showing that SafeCLIP reduces this floor to 9.6%, while the dose-response effect persists across all three encoders tested. Critically, no quality degradation in terms of FID, CLIPscore and ImageReward accompanies safety filtering. These results establish that data curation and text encoder safety are complementary and independently effective interventions. At the same time, the remaining level of unsafety poses questions for future research about emerging capabilities and compositionality.

Recent advances in flow matching models have significantly improved text-to-image generation quality, but also introduce growing safety risks due to the generation of harmful or undesirable content. Existing concept erasure methods are either inference-time interventions with limited effectiveness or rely on supervised fine-tuning (SFT), which requires precisely aligned data and struggles with scalability and multi-concept settings. In this paper, we propose \emph{FlowErase-RL}, the first GRPO-based framework for concept erasure in flow matching models. We reformulate concept erasure as a reward optimization problem and introduce a \textbf{dynamic dual-path reward mechanism} that jointly optimizes (i) a Concept Erasure (CE) reward to suppress target concepts and (ii) a Non-target Space (NS) reward to preserve generative fidelity. The two reward paths are adaptively balanced during training via a performance-driven switching strategy, enabling stable optimization without explicit supervision. Extensive experiments on nudity, object, and artistic style erasure demonstrate that our method achieves state-of-the-art erasure performance while maintaining strong image quality and semantic alignment. Moreover, it exhibits robust resistance to adversarial attacks and scales effectively to multi-concept scenarios. Our results establish a new paradigm for safe and controllable generation in flow matching models.

Text-to-image (T2I) diffusion models have the ability to build high-quality pictures from text prompts, but they pose safety concerns because they can generate offensive or disturbing imagery when provided with harmful inputs. Existing safety filters typically rely on text-based classifiers or image-based checkers that completely block the output upon detecting a threat, issuing an explicit allow/block feedback signal to the user. This binary strategy leaves models vulnerable to adversarial attacks that alter keywords to bypass detection, and it causes high false-alarm rates that degrade the experience for benign users. To address such vulnerabilities, we propose Disciplined Diffusion (DDiffusion), a novel robust text-to-image diffusion that counters Not Safe For Work (NSFW) generation by uncovering implicit malicious semantics in prompt embeddings. DDiffusion leverages a semantic retrieval mechanism to evaluate prompts against concept distributions rather than relying on brittle pairwise similarity. Furthermore, it employs a localization method during the diffusion process to selectively edit only the harmful regions of the generated image. By returning locally sanitized images instead of applying uniform blocking, DDiffusion suppresses malicious content while preserving generation fidelity for benign prompts and avoiding the binary allow-deny signal on which existing probing attacks rely.

Text-to-image (T2I) models are increasingly optimized for following user instructions faithfully. However, we find that this capability introduces a safety vulnerability we call Multi-Concept Compositional Unsafety (MCCU). MCCU occurs when multiple individually safe concepts, if combined in a single generation request, lead to harmful or sensitive visual outputs. Unlike prior jailbreak settings, MCCU does not rely on adversarial prompts, model access, or explicitly disallowed content. Instead, the risk emerges from how the model composes multiple safe visual concepts into a single scene. To systematically measure this threat, we build TwoHamsters, a large-scale evaluation framework consisting of 20k prompts, 51 curated concept pairs, and six risk categories. We evaluate 13 T2I models under a black-box setting. Our results show a clear conflict between instruction-following and safety: models that follow prompts more faithfully tend to produce more MCCU failures. For example, FLUX.1 achieves a 99.35% Unsafe Alignment Rate while only reaching a 1.57% MCCU Defense Rate. We further evaluate three representative defenses, including safety filtering, MCCU-specific detector fine-tuning, and concept erasure, all of which fail against unseen concept combinations. Our findings suggest that compositional reasoning in T2I models creates an attack surface that is not captured by existing safety mechanisms. We anticipate the release of TwoHamsters will catalyze community development of advanced generative defense mechanisms.

Text-to-image generative models have achieved impressive fidelity and diversity, but can inadvertently produce unsafe or undesirable content due to implicit biases embedded in large-scale training datasets. Existing concept erasure methods, whether text-only or image-assisted, face trade-offs: textual approaches often fail to fully suppress concepts, while naive image-guided methods risk over-erasing unrelated content. We propose TICoE, a text-image Collaborative Erasing framework that achieves precise and faithful concept removal through a continuous convex concept manifold and hierarchical visual representation learning. TICoE precisely removes target concepts while preserving unrelated semantic and visual content. To objectively assess the quality of erasure, we further introduce a fidelity-oriented evaluation strategy that measures post-erasure usability. Experiments on multiple benchmarks show that TICoE surpasses prior methods in concept removal precision and content fidelity, enabling safer, more controllable text-to-image generation. Our code is available at https://github.com/OpenAscent-L/TICoE.git