Pixel is a Barrier: Diffusion Models Are More Adversarially Robust Than We Think

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Xue, Haotian, Chen, Yongxin
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Computer Vision and Pattern Recognition Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Diffusion-Based Adversarial Sample Generation for Improved Stealthiness and Controllability
di: Xue, Haotian, et al.
Pubblicazione: (2023)

Diffusion Policy Attacker: Crafting Adversarial Attacks for Diffusion-based Policies
di: Chen, Yipu, et al.
Pubblicazione: (2024)

Toward effective protection against diffusion based mimicry through score distillation
di: Xue, Haotian, et al.
Pubblicazione: (2023)

The Thinking Pixel: Recursive Sparse Reasoning in Multimodal Diffusion Latents
di: Sun, Yuwei, et al.
Pubblicazione: (2026)

Aligning Text to Image in Diffusion Models is Easier Than You Think
di: Lee, Jaa-Yeon, et al.
Pubblicazione: (2025)

Beyond a Single Frame: Multi-Frame Spatially Grounded Reasoning Across Volumetric MRI
di: Moukheiber, Lama, et al.
Pubblicazione: (2026)

Point-It-Out: Benchmarking Embodied Reasoning for Vision Language Models in Multi-Stage Visual Grounding
di: Xue, Haotian, et al.
Pubblicazione: (2025)

Structure-Guided Adversarial Training of Diffusion Models
di: Yang, Ling, et al.
Pubblicazione: (2024)

PixelGen: Improving Pixel Diffusion with Perceptual Supervision
di: Ma, Zehong, et al.
Pubblicazione: (2026)

Improved Diffusion-based Generative Model with Better Adversarial Robustness
di: Wang, Zekun, et al.
Pubblicazione: (2025)

Your Embedding Model is SMARTer Than You Think
di: Zhang, Jianrui, et al.
Pubblicazione: (2026)

Robust SAM: On the Adversarial Robustness of Vision Foundation Models
di: Long, Jiahuan, et al.
Pubblicazione: (2025)

Adversarial Guided Diffusion Models for Adversarial Purification
di: Lin, Guang, et al.
Pubblicazione: (2024)

When Thinking Drifts: Evidential Grounding for Robust Video Reasoning
di: Luo, Mi, et al.
Pubblicazione: (2025)

PixelMan: Consistent Object Editing with Diffusion Models via Pixel Manipulation and Generation
di: Jiang, Liyao, et al.
Pubblicazione: (2024)

Think Twice to See More: Iterative Visual Reasoning in Medical VLMs
di: Chen, Kaitao, et al.
Pubblicazione: (2025)

Look Less, Reason More: Rollout-Guided Adaptive Pixel-Space Reasoning
di: Li, Xuchen, et al.
Pubblicazione: (2025)

HybridStitch: Pixel and Timestep Level Model Stitching for Diffusion Acceleration
di: Sun, Desen, et al.
Pubblicazione: (2026)

ADT: Tuning Diffusion Models with Adversarial Supervision
di: Shen, Dazhong, et al.
Pubblicazione: (2025)

ROBIN: Robust and Invisible Watermarks for Diffusion Models with Adversarial Optimization
di: Huang, Huayang, et al.
Pubblicazione: (2024)

Can We Change the Stroke Size for Easier Diffusion?
di: Bai, Yunwei, et al.
Pubblicazione: (2026)

Thinking Diffusion: Penalize and Guide Visual-Grounded Reasoning in Diffusion Multimodal Language Models
di: Kim, Keuntae, et al.
Pubblicazione: (2026)

More Thinking, Less Seeing? Assessing Amplified Hallucination in Multimodal Reasoning Models
di: Liu, Chengzhi, et al.
Pubblicazione: (2025)

Prompt-Agnostic Adversarial Perturbation for Customized Diffusion Models
di: Wan, Cong, et al.
Pubblicazione: (2024)

From Pampas to Pixels: Fine-Tuning Diffusion Models for Gaúcho Heritage
di: Amadeus, Marcellus, et al.
Pubblicazione: (2024)

DiffCAP: Diffusion-based Cumulative Adversarial Purification for Vision Language Models
di: Fu, Jia, et al.
Pubblicazione: (2025)

Robustness as Architecture: Designing IQA Models to Withstand Adversarial Perturbations
di: Meleshin, Igor, et al.
Pubblicazione: (2025)

Probing the Robustness of Vision-Language Pretrained Models: A Multimodal Adversarial Attack Approach
di: Guan, Jiwei, et al.
Pubblicazione: (2024)

Deep Compression Autoencoder for Efficient High-Resolution Diffusion Models
di: Chen, Junyu, et al.
Pubblicazione: (2024)

Pixel-Space Post-Training of Latent Diffusion Models
di: Zhang, Christina, et al.
Pubblicazione: (2024)

SwiftBrush v2: Make Your One-step Diffusion Model Better Than Its Teacher
di: Dao, Trung, et al.
Pubblicazione: (2024)

Evaluating Adversarial Protections for Diffusion Personalization: A Comprehensive Study
di: Ye, Kai, et al.
Pubblicazione: (2025)

Not All Pixels Are Equal: Pixel-wise Meta-Learning for Medical Segmentation with Noisy Labels
di: Mu, Chenyu, et al.
Pubblicazione: (2025)

UniPixel: Unified Object Referring and Segmentation for Pixel-Level Visual Reasoning
di: Liu, Ye, et al.
Pubblicazione: (2025)

StableSketcher: Enhancing Diffusion Model for Pixel-based Sketch Generation via Visual Question Answering Feedback
di: Park, Jiho, et al.
Pubblicazione: (2025)

DeCo: Frequency-Decoupled Pixel Diffusion for End-to-End Image Generation
di: Ma, Zehong, et al.
Pubblicazione: (2025)

MIMIR: Masked Image Modeling for Mutual Information-based Adversarial Robustness
di: Xu, Xiaoyun, et al.
Pubblicazione: (2023)

Securing Vision-Language Models with a Robust Encoder Against Jailbreak and Adversarial Attacks
di: Hossain, Md Zarif, et al.
Pubblicazione: (2024)

On the Adversarial Robustness of Discrete Image Tokenizers
di: Bhagwatkar, Rishika, et al.
Pubblicazione: (2026)

Watermark-embedded Adversarial Examples for Copyright Protection against Diffusion Models
di: Zhu, Peifei, et al.
Pubblicazione: (2024)