REVIEW 10 cited by
SAFREE: Training-Free and Adaptive Guard for Safe Text-to-Image And Video Generation
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
Recent advances in diffusion models have significantly enhanced their ability to generate high-quality images and videos, but they have also increased the risk of producing unsafe content. Existing unlearning/editing-based methods for safe generation remove harmful concepts from models but face several challenges: (1) They cannot instantly remove harmful concepts without training. (2) Their safe generation capabilities depend on collected training data. (3) They alter model weights, risking degradation in quality for content unrelated to toxic concepts. To address these, we propose SAFREE, a novel, training-free approach for safe T2I and T2V, that does not alter the model's weights. Specifically, we detect a subspace corresponding to a set of toxic concepts in the text embedding space and steer prompt embeddings away from this subspace, thereby filtering out harmful content while preserving intended semantics. To balance the trade-off between filtering toxicity and preserving safe concepts, SAFREE incorporates a novel self-validating filtering mechanism that dynamically adjusts the denoising steps when applying the filtered embeddings. Additionally, we incorporate adaptive re-attention mechanisms within the diffusion latent space to selectively diminish the influence of features related to toxic concepts at the pixel level. In the end, SAFREE ensures coherent safety checking, preserving the fidelity, quality, and safety of the output. SAFREE achieves SOTA performance in suppressing unsafe content in T2I generation compared to training-free baselines and effectively filters targeted concepts while maintaining high-quality images. It also shows competitive results against training-based methods. We extend SAFREE to various T2I backbones and T2V tasks, showcasing its flexibility and generalization. SAFREE provides a robust and adaptable safeguard for ensuring safe visual generation.
Forward citations
Cited by 10 Pith papers
-
SafeCA: Safe Cross-Attention Localization and Regulation for Text-to-Video Jailbreak Defense
SafeCA reduces text-to-video jailbreak success by roughly 20% relative to T2VShield by masking anomalous cross-attention activations using clean-prompt statistics.
-
Unlearning Sensitive Information in Multimodal LLMs: Benchmark and Attack-Defense Evaluation
UnLOK-VQA adds rephrase and neighborhood samples to OK-VQA to measure generalization and specificity of multimodal unlearning, and its evaluation shows that hiding answer tokens in hidden states beats other deletion o...
-
Tuning-Free Long Video Generation via Global-Local Collaborative Diffusion
GLC-Diffusion extends short-clip video diffusion models to long videos via global-local collaborative denoising, noise reinitialization, and motion-consistency refinement, improving coherence and fidelity at 3x and 6x...
-
ACE: Anti-Editing Concept Erasure in Text-to-Image Models
ACE trains a LoRA adapter on both conditional and unconditional noise predictions so that erased concepts are suppressed during both generation and text-guided editing.
-
TraSCE: Trajectory Steering for Concept Erasure
TraSCE steers diffusion trajectories with a modified negative-prompt formulation and a Gaussian loss to erase concepts at inference time without training or weight updates.
-
Do Concept Replacement Techniques Really Erase Unacceptable Concepts?
Weight-editing concept erasure methods fail to prevent reconstruction of unacceptable images in an image-to-image pipeline; a face-targeted editing method, AntiMirror, replaces celebrity likenesses with better fidelit...
-
T2VShield: Model-Agnostic Jailbreak Defense for Text-to-Video Models
T2VShield combines LLM-based prompt rewriting with multi-scale video risk detection and reports large reductions in jailbreak success across five text-to-video platforms.
-
Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey
A survey that taxonomizes multimodal jailbreak attacks and defenses into four lifecycle levels (input, encoder, generator, output) across Any-to-Text, Any-to-Vision, and Any-to-Any generative models.
-
Zero-Residual Concept Erasure via Progressive Alignment in Text-to-Image Model
A closed-form concept erasure method that enforces zero alignment residual in the optimization objective and applies updates progressively across layers to better preserve generation quality.
-
DPO Kernels: A Semantically-Aware, Kernel-Enhanced, and Divergence-Rich Paradigm for Direct Preference Optimization
A DPO variant that kernelizes the preference loss and swaps KL for other divergences is claimed to improve alignment, but the math and evaluation do not support the state-of-the-art claim.
Discussion (0). Continue with ORCID to comment.