Image de couverture de livre

GRILL: Restoring Gradient Signal in Ill-Conditioned Layers for More Effective Adversarial Attacks on Autoencoders

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Ramanaik, Chethan Krishnamurthy, Roy, Arjun, Callies, Tobias, Ntoutsi, Eirini
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Adversarial Robustness of VAEs across Intersectional Subgroups
par: Ramanaik, Chethan Krishnamurthy, et autres
Publié: (2024)

Exploring Fusion Techniques in Multimodal AI-Based Recruitment: Insights from FairCVdb
par: Swati, Swati, et autres
Publié: (2024)

Sum of Group Error Differences: A Critical Examination of Bias Evaluation in Biometric Verification and a Dual-Metric Measure
par: Elobaid, Alaa, et autres
Publié: (2024)

Rethinking Gradient-based Adversarial Attacks on Point Cloud Classification
par: Chen, Jun, et autres
Publié: (2025)

Enhancing Object Detection Robustness: Detecting and Restoring Confidence in the Presence of Adversarial Patch Attacks
par: Kazoom, Roie, et autres
Publié: (2024)

Autoencoder-based Denoising Defense against Adversarial Attacks on Object Detection
par: Song, Min Geun, et autres
Publié: (2025)

Diffusion Autoencoder for Unsupervised Artifact Restoration in Handheld Fundus Images
par: Palani, Mathumetha, et autres
Publié: (2026)

Sparse Autoencoders as Plug-and-Play Firewalls for Adversarial Attack Detection in VLMs
par: Wang, Hao, et autres
Publié: (2026)

Synthetic Tabular Data Generation for Class Imbalance and Fairness: A Comparative Study
par: Panagiotou, Emmanouil, et autres
Publié: (2024)

Theoretical Analysis of Relative Errors in Gradient Computations for Adversarial Attacks with CE Loss
par: Yu, Yunrui, et autres
Publié: (2025)

Gradient-Guided Conditional Diffusion Models for Private Image Reconstruction: Analyzing Adversarial Impacts of Differential Privacy and Denoising
par: Huang, Tao, et autres
Publié: (2024)

Adversarial Attack Against Images Classification based on Generative Adversarial Networks
par: Yang, Yahe
Publié: (2024)

Beyond the Known: Adversarial Autoencoders in Novelty Detection
par: Asad, Muhammad, et autres
Publié: (2024)

ALA: Naturalness-aware Adversarial Lightness Attack
par: Huang, Yihao, et autres
Publié: (2022)

Improving Visual Quality and Transferability of Adversarial Attacks on Face Recognition Simultaneously with Adversarial Restoration
par: Zhou, Fengfan, et autres
Publié: (2023)

Towards Effective and Sparse Adversarial Attack on Spiking Neural Networks via Breaking Invisible Surrogate Gradients
par: Lun, Li, et autres
Publié: (2025)

Multi-Task Adversarial Variational Autoencoder for Estimating Biological Brain Age with Multimodal Neuroimaging
par: Usman, Muhammad, et autres
Publié: (2024)

Emotion Loss Attacking: Adversarial Attack Perception for Skeleton based on Multi-dimensional Features
par: Liu, Feng, et autres
Publié: (2024)

Downstream Transfer Attack: Adversarial Attacks on Downstream Models with Pre-trained Vision Transformers
par: Zheng, Weijie, et autres
Publié: (2024)

Progressive Image Restoration via Text-Conditioned Video Generation
par: Kang, Peng, et autres
Publié: (2025)

Concept-based Adversarial Attack: a Probabilistic Perspective
par: Zhang, Andi, et autres
Publié: (2025)

Transferable Adversarial Face Attack with Text Controlled Attribute
par: Li, Wenyun, et autres
Publié: (2024)

MeLIAD: Interpretable Few-Shot Anomaly Detection with Metric Learning and Entropy-based Scoring
par: Cholopoulou, Eirini, et autres
Publié: (2024)

Taught Well Learned Ill: Towards Distillation-conditional Backdoor Attack
par: Chen, Yukun, et autres
Publié: (2025)

A Novel Defense Against Poisoning Attacks on Federated Learning: LayerCAM Augmented with Autoencoder
par: Zheng, Jingjing, et autres
Publié: (2024)

Biological Brain Age Estimation using Sex-Aware Adversarial Variational Autoencoder with Multimodal Neuroimages
par: Rehman, Abd Ur, et autres
Publié: (2024)

Masked Autoencoders Are Effective Tokenizers for Diffusion Models
par: Chen, Hao, et autres
Publié: (2025)

PB-UAP: Hybrid Universal Adversarial Attack For Image Segmentation
par: Song, Yufei, et autres
Publié: (2024)

Adversarial Attack for RGB-Event based Visual Object Tracking
par: Chen, Qiang, et autres
Publié: (2025)

Iterative Adversarial Attack on Image-guided Story Ending Generation
par: Wang, Youze, et autres
Publié: (2023)

Fooling Neural Networks for Motion Forecasting via Adversarial Attacks
par: Medina, Edgar, et autres
Publié: (2024)

Adversarial Evasion Attacks on Computer Vision using SHAP Values
par: Mollard, Frank, et autres
Publié: (2026)

Adversarial Prompt Injection Attack on Multimodal Large Language Models
par: Ding, Meiwen, et autres
Publié: (2026)

Are Conditional Latent Diffusion Models Effective for Image Restoration?
par: Yuan, Yunchen, et autres
Publié: (2024)

Gradient as Conditions: Rethinking HOG for All-in-one Image Restoration
par: Wu, Jiawei, et autres
Publié: (2025)

Steal Now and Attack Later: Evaluating Robustness of Object Detection against Black-box Adversarial Attacks
par: Chen, Erh-Chung, et autres
Publié: (2024)

Reconstructing the Invisible: Video Frame Restoration through Siamese Masked Conditional Variational Autoencoder
par: Zhou, Yongchen, et autres
Publié: (2024)

On Inherent Adversarial Robustness of Active Vision Systems
par: Mukherjee, Amitangshu, et autres
Publié: (2024)

Pixel is a Barrier: Diffusion Models Are More Adversarially Robust Than We Think
par: Xue, Haotian, et autres
Publié: (2024)

Conditional Unscented Autoencoders for Trajectory Prediction
par: Janjoš, Faris, et autres
Publié: (2023)