Copertina

Robustness as Architecture: Designing IQA Models to Withstand Adversarial Perturbations

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Meleshin, Igor, Chistyakova, Anna, Antsiferova, Anastasia, Vatolin, Dmitriy
Natura:	Preprint
Pubblicazione:	2025
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

Adversarial purification for no-reference image-quality metrics: applicability study and new methods
di: Gushchin, Aleksandr, et al.
Pubblicazione: (2024)

FS-IQA: Certified Feature Smoothing for Robust Image Quality Assessment
di: Shumitskaya, Ekaterina, et al.
Pubblicazione: (2025)

Cross-Modal Transferable Image-to-Video Attack on Video Quality Metrics
di: Gotin, Georgii, et al.
Pubblicazione: (2025)

BiRQA: Bidirectional Robust Quality Assessment for Images
di: Gushchin, Aleksandr, et al.
Pubblicazione: (2026)

Exploring adversarial robustness of JPEG AI: methodology, comparison and new methods
di: Kovalev, Egor, et al.
Pubblicazione: (2024)

IOI: Invisible One-Iteration Adversarial Attack on No-Reference Image- and Video-Quality Metrics
di: Shumitskaya, Ekaterina, et al.
Pubblicazione: (2024)

IQA-Adapter: Exploring Knowledge Transfer from Image Quality Assessment to Diffusion-based Generative Models
di: Abud, Khaled, et al.
Pubblicazione: (2024)

Ti-Patch: Tiled Physical Adversarial Patch for no-reference video quality metrics
di: Leonenkova, Victoria, et al.
Pubblicazione: (2024)

LEHA-CVQAD: Dataset To Enable Generalized Video Quality Assessment of Compression Artifacts
di: Gushchin, Aleksandr, et al.
Pubblicazione: (2025)

TIQA: Human-Aligned Perceptual Text Quality Assessment in Generated Images
di: Koltsov, Kirill, et al.
Pubblicazione: (2026)

From Pixels to Reality: Physical-Digital Patch Attacks on Real-World Camera
di: Leonenkova, Victoria, et al.
Pubblicazione: (2026)

Stochastic BIQA: Median Randomized Smoothing for Certified Blind Image Quality Assessment
di: Shumitskaya, Ekaterina, et al.
Pubblicazione: (2024)

Guardians of Image Quality: Benchmarking Defenses Against Adversarial Attacks on Image Quality Metrics
di: Gushchin, Alexander, et al.
Pubblicazione: (2024)

RandMark: On Random Watermarking of Visual Foundation Models
di: Chistyakova, Anna, et al.
Pubblicazione: (2026)

Comparing the Robustness of Modern No-Reference Image- and Video-Quality Metrics to Adversarial Attacks
di: Antsiferova, Anastasia, et al.
Pubblicazione: (2023)

ActiveMark: on watermarking of visual foundation models via massive activations
di: Chistyakova, Anna, et al.
Pubblicazione: (2025)

MEMFOF: High-Resolution Training for Memory-Efficient Multi-Frame Optical Flow Estimation
di: Bargatin, Vladislav, et al.
Pubblicazione: (2025)

NIC-RobustBench: A Comprehensive Open-Source Toolkit for Neural Image Compression and Robustness Analysis
di: Bychkov, Georgii, et al.
Pubblicazione: (2025)

JPEG AI Image Compression Visual Artifacts: Detection Methods and Dataset
di: Tsereh, Daria, et al.
Pubblicazione: (2024)

Machine vision-aware quality metrics for compressed image and video assessment
di: Dremin, Mikhail, et al.
Pubblicazione: (2024)

From Global to Granular: Revealing IQA Model Performance via Correlation Surface
di: Chen, Baoliang, et al.
Pubblicazione: (2026)

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

MedIQA: A Scalable Foundation Model for Prompt-Driven Medical Image Quality Assessment
di: Xun, Siyi, et al.
Pubblicazione: (2025)

LMM-IQA: Image Quality Assessment for Low-Dose CT Imaging
di: Celik, Kagan, et al.
Pubblicazione: (2025)

A Comparative Study of Adversarial Robustness in CNN and CNN-ANFIS Architectures
di: Shankar, Kaaustaaub, et al.
Pubblicazione: (2026)

ClimateIQA: A New Dataset and Benchmark to Advance Vision-Language Models in Meteorology Anomalies Analysis
di: Chen, Jian, et al.
Pubblicazione: (2024)

Refine-IQA: Multi-Stage Reinforcement Finetuning for Perceptual Image Quality Assessment
di: Jia, Ziheng, et al.
Pubblicazione: (2025)

DP-IQA: Utilizing Diffusion Prior for Blind Image Quality Assessment in the Wild
di: Fu, Honghao, et al.
Pubblicazione: (2024)

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

SA-IQA: Redefining Image Quality Assessment for Spatial Aesthetics with Multi-Dimensional Rewards
di: Gao, Yuan, et al.
Pubblicazione: (2025)

Dog-IQA: Standard-guided Zero-shot MLLM for Mix-grained Image Quality Assessment
di: Liu, Kai, et al.
Pubblicazione: (2024)

GeoShield: Safeguarding Geolocation Privacy from Vision-Language Models via Adversarial Perturbations
di: Liu, Xinwei, et al.
Pubblicazione: (2025)

AEGIS: Preserving privacy of 3D Facial Avatars with Adversarial Perturbations
di: Wolkiewicz, Dawid, et al.
Pubblicazione: (2025)

Generative Adversarial Perturbations with Cross-paradigm Transferability on Localized Crowd Counting
di: Anisha, Alabi Mehzabin, et al.
Pubblicazione: (2026)

APLA: Additional Perturbation for Latent Noise with Adversarial Training Enables Consistency
di: Yao, Yupu, et al.
Pubblicazione: (2023)

Adversarial Training with OCR Modality Perturbation for Scene-Text Visual Question Answering
di: Shen, Zhixuan, et al.
Pubblicazione: (2024)

Interpreting Global Perturbation Robustness of Image Models using Axiomatic Spectral Importance Decomposition
di: Luo, Róisín, et al.
Pubblicazione: (2024)

Fight Perturbations with Perturbations: Defending Adversarial Attacks via Neuron Influence
di: Chen, Ruoxi, et al.
Pubblicazione: (2021)

Perturb a Model, Not an Image: Towards Robust Privacy Protection via Anti-Personalized Diffusion Models
di: Lee, Tae-Young, et al.
Pubblicazione: (2025)

IAP: Invisible Adversarial Patch Attack through Perceptibility-Aware Localization and Perturbation Optimization
di: Dutta, Subrat Kishore, et al.
Pubblicazione: (2025)