Corrupting Attention: Evasion-Based Adversarial Attacks on Encoder Attention in Detection Transformers

arXiv:2608.06674 · cs.CV, cs.LG · Submitted 2026-08-07 · Read on arXiv

Ridma Jayasundara, Shaheer Mohamed, Tharindu Fernando, Harshala Gammulle, Basura Fernando, Sanka Rasnayake, A V Subramanyam, Sridha Sridharan, Clinton Fookes

cs.CV, cs.LG

Submitted: 2026-08-07

Updated: 2026-08-10

Comments: 8 pages, 6 figures, 6 tables

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Transformer — 39× in this paper · explained in 2 episodes
• Transformers — 24× in this paper · explained in 2 episodes
• Decoder — 9× in this paper · explained in 2 episodes
• Robustness — 8× in this paper · explained in 6 episodes
• Attention Mechanism — 6× in this paper · explained in 3 episodes
• Adversarial Robustness — 5× in this paper · explained in 4 episodes
• Transferability — 4× in this paper · explained in 5 episodes
• Adversarial Examples — 3× in this paper · explained in 2 episodes
• Accuracy — 2× in this paper · explained in 1 episode
• Core — 2× in this paper · explained in 2 episodes
• Ablation — 1× in this paper · explained in 1 episode
• Ablation Study — 1× in this paper · explained in 3 episodes
• Benchmark — 1× in this paper · explained in 2 episodes
• Distillation — 1× in this paper · explained in 2 episodes
• Embeddings — 1× in this paper · explained in 2 episodes
• Semantic Segmentation — 1× in this paper · explained in 3 episodes
• Transformer Encoder — 1× in this paper · explained in 2 episodes

Sources

• Deformable DETR: Deformable Transformers for End-to-End Object Detection
• DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection
• Patch-Fool: Are Vision Transformers Always Robust Against Adversarial Perturbations?
• Transferable Adversarial Attacks for Image and Video Object Detection
• Robust Adversarial Perturbation on Deep Proposal-based Models
• Explaining and Harnessing Adversarial Examples
• An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
• Relevance Attack on Detectors

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models