Universal Cross-Prompt Adversarial Attacks on Promptable Concept Segmentation

arXiv:2609.39265 · cs.CV · Submitted 2026-09-30 · Read on arXiv

cs.CV

Submitted: 2026-09-30

Updated: 2026-09-30

Code: https://github.com/alphanull-cqu/AdvPCS

Terminology

• Transferability — 26× in this paper · explained in 4 episodes
• Adversarial Examples — 13× in this paper · explained in 2 episodes
• Adversarial Attacks — 11× in this paper · explained in 1 episode
• Segment Anything Model — 11× in this paper
• Consistency — 9× in this paper · explained in 3 episodes
• Pruning — 9× in this paper · explained in 4 episodes
• Robustness — 9× in this paper · explained in 5 episodes
• Benchmark — 8× in this paper · explained in 2 episodes
• Promptable Concept Segmentation — 6× in this paper
• Foundation Model — 3× in this paper · explained in 3 episodes
• Segment Anything Model (SAM) — 3× in this paper · explained in 2 episodes
• Ablation — 2× in this paper · explained in 1 episode
• Adversarial Robustness — 2× in this paper · explained in 3 episodes
• Cosine Similarity — 2× in this paper · explained in 3 episodes
• Fine-Tuning — 2× in this paper · explained in 5 episodes
• Foundation Models — 2× in this paper · explained in 7 episodes
• Grounding — 2× in this paper · explained in 3 episodes
• Segmentation Masks — 2× in this paper · explained in 2 episodes
• Ablation study — 1× in this paper · explained in 1 episode
• Adversarial Training — 1× in this paper · explained in 1 episode
• Computational overhead — 1× in this paper · explained in 2 episodes
• Contrastive Learning — 1× in this paper · explained in 5 episodes
• Distillation — 1× in this paper · explained in 2 episodes
• Downstream Tasks — 1× in this paper · explained in 2 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Mask Generation — 1× in this paper · explained in 2 episodes
• Regularization — 1× in this paper · explained in 3 episodes
• Temporal consistency — 1× in this paper · explained in 2 episodes
• Transformer — 1× in this paper · explained in 2 episodes
• Unified Framework — 1× in this paper · explained in 5 episodes

Sources

• AD-SAM: Adapting the Segment Anything Model for Semantic Segmentation in Autonomous Driving
• SAM-Med2D
• SAM Meets UAP: Attacking Segment Anything Model With Universal Adversarial Perturbation
• The 2017 DAVIS Challenge on Video Object Segmentation
• Robustness of SAM: Segment Anything Under Corruptions and Beyond
• YouTube-VOS: A Large-Scale Video Object Segmentation Benchmark
• EfficientSAM3: Progressive Hierarchical Distillation for Video Concept Segmentation from SAM1, 2, and 3
• Attack-SAM: Towards Attacking Segment Anything Model With Adversarial Examples
• To prune, or not to prune: exploring the efficacy of pruning for model compression

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