Pith. sign in

REVIEW 4 cited by

DiffGuard: Text-Based Safety Checker for Diffusion Models

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

arxiv 2412.00064 v2 pith:P6VKGQCD submitted 2024-11-25 cs.CV cs.AI

classification cs.CVcs.AI
keywords modelsdiffusiondiffguardexistingfiltergenerationimagesopen-source
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Recent advances in Diffusion Models have enabled the generation of images from text, with powerful closed-source models like DALL-E and Midjourney leading the way. However, open-source alternatives, such as StabilityAI's Stable Diffusion, offer comparable capabilities. These open-source models, hosted on Hugging Face, come equipped with ethical filter protections designed to prevent the generation of explicit images. This paper reveals first their limitations and then presents a novel text-based safety filter that outperforms existing solutions. Our research is driven by the critical need to address the misuse of AI-generated content, especially in the context of information warfare. DiffGuard enhances filtering efficacy, achieving a performance that surpasses the best existing filters by over 14%.

Discussion (0). Sign in to comment.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Mind the Gap: Zero-Query Jailbreaks via Filter-Generator Discrepancy in Text-to-Image Systems

    cs.CL 2026-08 conditional novelty 6.0 of 10

    Zero-query jailbreak attacks on text-to-image systems that exploit filter-generator discrepancy reach 29-33% average success and beat baselines on six pipelines and GPT-image-2.

  2. Architectural Backdoors in Vision-Language Model Supply Chains via Representation Steering

    cs.CR 2026-07 conditional novelty 6.0 of 10

    Trigger-gated additive steering vectors embedded in VLM architecture definitions create dormant backdoors that work across VQA, text-to-image, retrieval, and brand/safety biasing without data poisoning.

  3. Between Safe Boundaries: Exploiting Temporal Consistency for Jailbreaking Text-To-Video Generation Models

    cs.CR 2026-07 conditional novelty 6.0 of 10

    Two benign boundary prompts can make T2V models render harmful intermediate frames via temporal interpolation; BSB's tree-search version beats prior jailbreaks by an average 18.6% relative ASR across four commercial systems.

  4. AEGIS: A Mechanism-Guided Defense against Visual Synonym Jailbreaks in Text-to-Image Models

    cs.CV 2026-07 conditional novelty 6.0 of 10

    AEGIS localizes sparse semantic-injecting attention heads in diffusion models and applies similarity-aware repulsion at those heads to block visual synonym jailbreaks while preserving benign generation.

Pith tools