Cover Image

Mechanistic Understandings of Representation Vulnerabilities and Engineering Robust Vision Transformers

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Islam, Chashi Mahiul, Chacko, Samuel Jacob, Nishino, Mao, Liu, Xiuwen
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

DeepSeek on a Trip: Inducing Targeted Visual Hallucinations via Representation Vulnerabilities
by: Islam, Chashi Mahiul, et al.
Published: (2025)

Malicious Path Manipulations via Exploitation of Representation Vulnerabilities of Vision-Language Navigation Systems
by: Islam, Chashi Mahiul, et al.
Published: (2024)

Spatial-ViLT: Enhancing Visual Spatial Reasoning through Multi-Task Learning
by: Islam, Chashi Mahiul, et al.
Published: (2025)

Are Vision Transformer Representations Semantically Meaningful? A Case Study in Medical Imaging
by: Shams, Montasir, et al.
Published: (2025)

Adversarial Attacks on Large Language Models Using Regularized Relaxation
by: Chacko, Samuel Jacob, et al.
Published: (2024)

Numerical Instability and Chaos: Quantifying the Unpredictability of Large Language Models
by: Islam, Chashi Mahiul, et al.
Published: (2026)

Intriguing Equivalence Structures of the Embedding Space of Vision Transformers
by: Salman, Shaeke, et al.
Published: (2024)

When Skills Don't Help: A Negative Result on Procedural Knowledge for Tool-Grounded Agents in Offensive Cybersecurity
by: Chacko, Samuel Jacob, et al.
Published: (2026)

Adversarial Attack on Large Language Models using Exponentiated Gradient Descent
by: Biswas, Sajib, et al.
Published: (2025)

Intriguing Differences Between Zero-Shot and Systematic Evaluations of Vision-Language Transformer Models
by: Salman, Shaeke, et al.
Published: (2024)

Leveraging Registers in Vision Transformers for Robust Adaptation
by: Yellapragada, Srikar, et al.
Published: (2025)

Approximate Nullspace Augmented Finetuning for Robust Vision Transformers
by: Liu, Haoyang, et al.
Published: (2024)

A Manifold Representation of the Key in Vision Transformers
by: Meng, Li, et al.
Published: (2024)

Dynamic Scene Understanding from Vision-Language Representations
by: Pruss, Shahaf, et al.
Published: (2025)

Robust Asymmetric Heterogeneous Federated Learning with Corrupted Clients
by: Fang, Xiuwen, et al.
Published: (2025)

Beyond ImageNet: Understanding Cross-Dataset Robustness of Lightweight Vision Models
by: Zhang, Weidong, et al.
Published: (2025)

GeoViSTA: Geospatial Vision-Tabular Transformer for Multimodal Environment Representation
by: Liu, Yuhao, et al.
Published: (2026)

Universal and Transferable Adversarial Attack on Large Language Models Using Exponentiated Gradient Descent
by: Biswas, Sajib, et al.
Published: (2025)

SATA: Spatial Autocorrelation Token Analysis for Enhancing the Robustness of Vision Transformers
by: Nikzad, Nick, et al.
Published: (2024)

Artificial intelligence application in lymphoma diagnosis: from Convolutional Neural Network to Vision Transformer
by: Rivera, Daniel, et al.
Published: (2025)

Robust Data Clustering with Outliers via Transformed Tensor Low-Rank Representation
by: Wu, Tong
Published: (2023)

Understanding the Effect of using Semantically Meaningful Tokens for Visual Representation Learning
by: Kalibhat, Neha, et al.
Published: (2024)

Garbage Vulnerable Point Monitoring using IoT and Computer Vision
by: Kumar, R., et al.
Published: (2025)

Explainable Concept Generation through Vision-Language Preference Learning for Understanding Neural Networks' Internal Representations
by: Taparia, Aditya, et al.
Published: (2024)

DPL: Decoupled Prototype Learning for Enhancing Robustness of Vision-Language Transformers to Missing Modalities
by: Lu, Jueqing, et al.
Published: (2025)

Positional Encodings Anchor Spatial Structure in Vision Transformers: A Geometric Perspective on Robustness
by: Mannes, Mahmoud
Published: (2026)

SpecFormer: Guarding Vision Transformer Robustness via Maximum Singular Value Penalization
by: Hu, Xixu, et al.
Published: (2024)

Right Predictions, Misleading Explanations: On the Vulnerability of Vision-Language Model Explanations
by: Babadi, Narges, et al.
Published: (2026)

PatchGuard: Adversarially Robust Anomaly Detection and Localization through Vision Transformers and Pseudo Anomalies
by: Nafez, Mojtaba, et al.
Published: (2025)

STR-Cert: Robustness Certification for Deep Text Recognition on Deep Learning Pipelines and Vision Transformers
by: Shao, Daqian, et al.
Published: (2023)

URRL-IMVC: Unified and Robust Representation Learning for Incomplete Multi-View Clustering
by: Teng, Ge, et al.
Published: (2024)

GNN-ViTCap: GNN-Enhanced Multiple Instance Learning with Vision Transformers for Whole Slide Image Classification and Captioning
by: Raju, S M Taslim Uddin, et al.
Published: (2025)

Diffusion Transformers with Representation Autoencoders
by: Zheng, Boyang, et al.
Published: (2025)

Mechanistic Interpretability for Learning Assurance of a Vision-Based Landing System
by: Valentin, Romeo, et al.
Published: (2026)

Native Segmentation Vision Transformers
by: Brasó, Guillem, et al.
Published: (2025)

If CLIP Could Talk: Understanding Vision-Language Model Representations Through Their Preferred Concept Descriptions
by: Esfandiarpoor, Reza, et al.
Published: (2024)

Learning Topological Representations for Deep Image Understanding
by: Hu, Xiaoling
Published: (2024)

Robust Representation Learning in Masked Autoencoders
by: Shrivastava, Anika, et al.
Published: (2026)

Data-Driven Fairness Generalization for Deepfake Detection
by: Ezeakunne, Uzoamaka, et al.
Published: (2024)

Understanding Task Transfer in Vision-Language Models
by: Sachdeva, Bhuvan, et al.
Published: (2025)