Image de couverture de livre

CLIP is Strong Enough to Fight Back: Test-time Counterattacks towards Zero-shot Adversarial Robustness of CLIP

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Xing, Songlong, Zhao, Zhengyu, Sebe, Nicu
Format:	Preprint
Publié:	2025
Sujets:	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

Finetune Like You Pretrain: Boosting Zero-shot Adversarial Robustness in Vision-language Models
par: Xing, Songlong, et autres
Publié: (2026)

PoInit-of-View: Poisoning Initialization of Views Transfers Across Multiple 3D Reconstruction Systems
par: Wang, Weijie, et autres
Publié: (2026)

Diversifying Counterattacks: Orthogonal Exploration for Robust CLIP Inference
par: Jiang, Chengze, et autres
Publié: (2025)

Contrastive Spectral Rectification: Test-Time Defense towards Zero-shot Adversarial Robustness of CLIP
par: Nie, Sen, et autres
Publié: (2026)

Partial CLIP is Enough: Chimera-Seg for Zero-shot Semantic Segmentation
par: Chen, Jialei, et autres
Publié: (2025)

GenCLIP: Generalizing CLIP Prompts for Zero-shot Anomaly Detection
par: Kim, Donghyeong, et autres
Publié: (2025)

MV-CLIP: Multi-View CLIP for Zero-shot 3D Shape Recognition
par: Song, Dan, et autres
Publié: (2023)

SPECIAL: Zero-shot Hyperspectral Image Classification With CLIP
par: Pang, Li, et autres
Publié: (2025)

CLIP-driven Zero-shot Learning with Ambiguous Labels
par: Fan, Jinfu, et autres
Publié: (2026)

Explaining CLIP Zero-shot Predictions Through Concepts
par: Ozdemir, Onat, et autres
Publié: (2026)

AA-CLIP: Enhancing Zero-shot Anomaly Detection via Anomaly-Aware CLIP
par: Ma, Wenxin, et autres
Publié: (2025)

MadCLIP: Few-shot Medical Anomaly Detection with CLIP
par: Shiri, Mahshid, et autres
Publié: (2025)

Self-Supervised and Generalizable Tokenization for CLIP-Based 3D Understanding
par: Mei, Guofeng, et autres
Publié: (2025)

MediCLIP: Adapting CLIP for Few-shot Medical Image Anomaly Detection
par: Zhang, Ximiao, et autres
Publié: (2024)

TokenCLIP: Token-wise Prompt Learning for Zero-shot Anomaly Detection
par: Zhou, Qihang, et autres
Publié: (2025)

AnomalyCLIP: Object-agnostic Prompt Learning for Zero-shot Anomaly Detection
par: Zhou, Qihang, et autres
Publié: (2023)

Unseen No More: Unlocking the Potential of CLIP for Generative Zero-shot HOI Detection
par: Guo, Yixin, et autres
Publié: (2024)

Adversarial Backdoor Defense in CLIP
par: Kuang, Junhao, et autres
Publié: (2024)

ATAC: Augmentation-Based Test-Time Adversarial Correction for CLIP
par: Su, Linxiang, et autres
Publié: (2025)

Exploring the Adversarial Robustness of CLIP for AI-generated Image Detection
par: De Rosa, Vincenzo, et autres
Publié: (2024)

FLEX-CLIP: Feature-Level GEneration Network Enhanced CLIP for X-shot Cross-modal Retrieval
par: Xie, Jingyou, et autres
Publié: (2024)

CardiacCLIP: Video-based CLIP Adaptation for LVEF Prediction in a Few-shot Manner
par: Du, Yao, et autres
Publié: (2025)

Building a Multi-modal Spatiotemporal Expert for Zero-shot Action Recognition with CLIP
par: Yu, Yating, et autres
Publié: (2024)

CLIPure: Purification in Latent Space via CLIP for Adversarially Robust Zero-Shot Classification
par: Zhang, Mingkun, et autres
Publié: (2025)

CRoF: CLIP-based Robust Few-shot Learning on Noisy Labels
par: Deng, Shizhuo, et autres
Publié: (2024)

APC: Transferable and Efficient Adversarial Point Counterattack for Robust 3D Point Cloud Recognition
par: Jung, Geunyoung, et autres
Publié: (2026)

CLIP-guided Prototype Modulating for Few-shot Action Recognition
par: Wang, Xiang, et autres
Publié: (2023)

SuperCLIP: CLIP with Simple Classification Supervision
par: Zhao, Weiheng, et autres
Publié: (2025)

AF-CLIP: Zero-Shot Anomaly Detection via Anomaly-Focused CLIP Adaptation
par: Fang, Qingqing, et autres
Publié: (2025)

CLIP-Decoder : ZeroShot Multilabel Classification using Multimodal CLIP Aligned Representation
par: Ali, Muhammad, et autres
Publié: (2024)

AdaCLIP: Adapting CLIP with Hybrid Learnable Prompts for Zero-Shot Anomaly Detection
par: Cao, Yunkang, et autres
Publié: (2024)

GlocalCLIP: Object-agnostic Global-Local Prompt Learning for Zero-shot Anomaly Detection
par: Ham, Jiyul, et autres
Publié: (2024)

Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation
par: Li, Jinlong, et autres
Publié: (2025)

Test-Time Adaptation with SaLIP: A Cascade of SAM and CLIP for Zero shot Medical Image Segmentation
par: Aleem, Sidra, et autres
Publié: (2024)

Test-Time Adaptation with CLIP Reward for Zero-Shot Generalization in Vision-Language Models
par: Zhao, Shuai, et autres
Publié: (2023)

Semantic-aware Adversarial Fine-tuning for CLIP
par: Zhang, Jiacheng, et autres
Publié: (2026)

IQE-CLIP: Instance-aware Query Embedding for Zero-/Few-shot Anomaly Detection in Medical Domain
par: Huang, Hong, et autres
Publié: (2025)

CLIP-AD: A Language-Guided Staged Dual-Path Model for Zero-shot Anomaly Detection
par: Chen, Xuhai, et autres
Publié: (2023)

un$^2$CLIP: Improving CLIP's Visual Detail Capturing Ability via Inverting unCLIP
par: Li, Yinqi, et autres
Publié: (2025)

Self-Calibrated Consistency can Fight Back for Adversarial Robustness in Vision-Language Models
par: Liu, Jiaxiang, et autres
Publié: (2025)