Cover Image

What Concepts Lie Within? Detecting and Suppressing Risky Content in Diffusion Transformers

Fuente: arXiv

Saved in:

Bibliographic Details
Main Author:	Zhang, Chenyu
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition Cryptography and Security
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

What Lurks Within? Concept Auditing for Shared Diffusion Models at Scale
by: Yuan, Xiaoyong, et al.
Published: (2025)

Detecting Malicious Concepts without Image Generation in AI-Generated Content (AIGC)
by: Xu, Kun, et al.
Published: (2025)

T2I-RiskyPrompt: A Benchmark for Safety Evaluation, Attack, and Defense on Text-to-Image Model
by: Zhang, Chenyu, et al.
Published: (2025)

Rethinking Robust Adversarial Concept Erasure in Diffusion Models
by: Yin, Qinghong, et al.
Published: (2025)

Defensive Unlearning with Adversarial Training for Robust Concept Erasure in Diffusion Models
by: Zhang, Yimeng, et al.
Published: (2024)

Neighbor-Aware Localized Concept Erasure in Text-to-Image Diffusion Models
by: Shi, Zhuan, et al.
Published: (2026)

Bi-Erasing: A Bidirectional Framework for Concept Removal in Diffusion Models
by: Chen, Hao, et al.
Published: (2025)

Six-CD: Benchmarking Concept Removals for Benign Text-to-image Diffusion Models
by: Ren, Jie, et al.
Published: (2024)

Guarding the Gate: ConceptGuard Battles Concept-Level Backdoors in Concept Bottleneck Models
by: Lai, Songning, et al.
Published: (2024)

Adversarial Attacks and Defenses on Text-to-Image Diffusion Models: A Survey
by: Zhang, Chenyu, et al.
Published: (2024)

CAT: Concept-level backdoor ATtacks for Concept Bottleneck Models
by: Lai, Songning, et al.
Published: (2024)

Do Concept Replacement Techniques Really Erase Unacceptable Concepts?
by: Das, Anudeep, et al.
Published: (2025)

Espresso: Robust Concept Filtering in Text-to-Image Models
by: Das, Anudeep, et al.
Published: (2024)

TwoHamsters: Benchmarking Multi-Concept Compositional Unsafety in Text-to-Image Models
by: Zhang, Chaoshuo, et al.
Published: (2026)

Backdooring CLIP through Concept Confusion
by: Hu, Lijie, et al.
Published: (2025)

VideoEraser: Concept Erasure in Text-to-Video Diffusion Models
by: Xu, Naen, et al.
Published: (2025)

Can You Trust What You See? Alpha Channel No-Box Attacks on Video Object Detection
by: Yi, Ariana, et al.
Published: (2025)

ViTGuard: Attention-aware Detection against Adversarial Examples for Vision Transformer
by: Sun, Shihua, et al.
Published: (2024)

LoyalDiffusion: A Diffusion Model Guarding Against Data Replication
by: Li, Chenghao, et al.
Published: (2024)

DeeCLIP: A Robust and Generalizable Transformer-Based Framework for Detecting AI-Generated Images
by: Keita, Mamadou, et al.
Published: (2025)

Unstable Unlearning: The Hidden Risk of Concept Resurgence in Diffusion Models
by: Suriyakumar, Vinith M., et al.
Published: (2024)

Gaussian Shannon: High-Precision Diffusion Model Watermarking Based on Communication
by: Zhang, Yi, et al.
Published: (2026)

BodhiPromptShield: Pre-Inference Prompt Mediation for Suppressing Privacy Propagation in LLM/VLM Agents
by: Ma, Bo, et al.
Published: (2026)

Controllable Adversarial Makeup for Privacy via Text-Guided Diffusion
by: Kwon, Youngjin, et al.
Published: (2025)

Beyond Text Prompts: Precise Concept Erasure through Text-Image Collaboration
by: Li, Jun, et al.
Published: (2026)

Scaling Exposes the Trigger: Input-Level Backdoor Detection in Text-to-Image Diffusion Models via Cross-Attention Scaling
by: Li, Zida, et al.
Published: (2026)

Semantic Deep Hiding for Robust Unlearnable Examples
by: Meng, Ruohan, et al.
Published: (2024)

Sparse Autoencoder as a Zero-Shot Classifier for Concept Erasing in Text-to-Image Diffusion Models
by: Tian, Zhihua, et al.
Published: (2025)

MMA-Diffusion: MultiModal Attack on Diffusion Models
by: Yang, Yijun, et al.
Published: (2023)

Protecting Your Video Content: Disrupting Automated Video-based LLM Annotations
by: Liu, Haitong, et al.
Published: (2025)

An Inversion-based Measure of Memorization for Diffusion Models
by: Ma, Zhe, et al.
Published: (2024)

FreqCross: A Multi-Modal Frequency-Spatial Fusion Network for Robust Detection of Stable Diffusion 3.5 Generated Images
by: Yang, Guang
Published: (2025)

Gungnir: Exploiting Stylistic Features in Images for Backdoor Attacks on Diffusion Models
by: Zhang, Lei, et al.
Published: (2025)

Lazy Layers to Make Fine-Tuned Diffusion Models More Traceable
by: Liu, Haozhe, et al.
Published: (2024)

Responsible Diffusion: A Comprehensive Survey on Safety, Ethics, and Trust in Diffusion Models
by: Wei, Kang, et al.
Published: (2025)

Model X-ray:Detecting Backdoored Models via Decision Boundary
by: Su, Yanghao, et al.
Published: (2024)

Mitigate Replication and Copying in Diffusion Models with Generalized Caption and Dual Fusion Enhancement
by: Li, Chenghao, et al.
Published: (2023)

Gaussian Shading: Provable Performance-Lossless Image Watermarking for Diffusion Models
by: Yang, Zijin, et al.
Published: (2024)

NeR-VCP: A Video Content Protection Method Based on Implicit Neural Representation
by: Lin, Yangping, et al.
Published: (2024)

Is Diffusion Model Safe? Severe Data Leakage via Gradient-Guided Diffusion Model
by: Meng, Jiayang, et al.
Published: (2024)