Cover Image

Bridging the Task Gap: Multi-Task Adversarial Transferability in CLIP and Its Derivatives

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Liu, Kuanrong, Liang, Siyuan, Qian, Cheng, Zhang, Ming, Cao, Xiaochun
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Adversarial Backdoor Defense in CLIP
by: Kuang, Junhao, et al.
Published: (2024)

Efficient Backdoor Defense in Multimodal Contrastive Learning: A Token-Level Unlearning Method for Mitigating Threats
by: Liu, Kuanrong, et al.
Published: (2024)

Unlearning Backdoor Threats: Enhancing Backdoor Defense in Multimodal Contrastive Learning via Local Token Unlearning
by: Liang, Siyuan, et al.
Published: (2024)

Physical Adversarial Camouflage through Gradient Calibration and Regularization
by: Liang, Jiawei, et al.
Published: (2025)

3D Gaussian Splatting Driven Multi-View Robust Physical Adversarial Camouflage Generation
by: Lou, Tianrui, et al.
Published: (2025)

Text Adversarial Attacks with Dynamic Outputs
by: Wang, Wenqiang, et al.
Published: (2025)

BadCLIP: Dual-Embedding Guided Backdoor Attack on Multimodal Contrastive Learning
by: Liang, Siyuan, et al.
Published: (2023)

CleanerCLIP: Fine-grained Counterfactual Semantic Augmentation for Backdoor Defense in Contrastive Learning
by: Xun, Yuan, et al.
Published: (2024)

R-PGA: Robust Physical Adversarial Camouflage Generation via Relightable 3D Gaussian Splatting
by: Lou, Tianrui, et al.
Published: (2026)

CLIP-Guided Multi-Task Regression for Multi-View Plant Phenotyping
by: Warmers, Simon, et al.
Published: (2026)

DetailCLIP: Detail-Oriented CLIP for Fine-Grained Tasks
by: Monsefi, Amin Karimi, et al.
Published: (2024)

TaskCLIP: Extend Large Vision-Language Model for Task Oriented Object Detection
by: Chen, Hanning, et al.
Published: (2024)

Stealthy Multi-Task Adversarial Attacks
by: Guo, Jiacheng, et al.
Published: (2024)

Mind the Gap: Bridging Occlusion in Gait Recognition via Residual Gap Correction
by: Gupta, Ayush, et al.
Published: (2025)

CLIP-Guided Generative Networks for Transferable Targeted Adversarial Attacks
by: Fang, Hao, et al.
Published: (2024)

Poisoned Forgery Face: Towards Backdoor Attacks on Face Forgery Detection
by: Liang, Jiawei, et al.
Published: (2024)

Exploring Inconsistent Knowledge Distillation for Object Detection with Data Augmentation
by: Liang, Jiawei, et al.
Published: (2022)

CauCLIP: Bridging the Sim-to-Real Gap in Surgical Video Understanding via Causality-Inspired Vision-Language Modeling
by: He, Yuxin, et al.
Published: (2026)

Rep-MTL: Unleashing the Power of Representation-level Task Saliency for Multi-Task Learning
by: Wang, Zedong, et al.
Published: (2025)

Top-K Pairwise Ranking: Bridging the Gap Among Ranking-Based Measures for Multi-Label Classification
by: Wang, Zitai, et al.
Published: (2024)

SurgeryV2: Bridging the Gap Between Model Merging and Multi-Task Learning with Deep Representation Surgery
by: Yang, Enneng, et al.
Published: (2024)

Hide in Thicket: Generating Imperceptible and Rational Adversarial Perturbations on 3D Point Clouds
by: Lou, Tianrui, et al.
Published: (2024)

Semantic-Aligned Adversarial Evolution Triangle for High-Transferability Vision-Language Attack
by: Jia, Xiaojun, et al.
Published: (2024)

Transfer CLIP for Generalizable Image Denoising
by: Cheng, Jun, et al.
Published: (2024)

Hierarchical Invariance for Robust and Interpretable Vision Tasks at Larger Scales
by: Qi, Shuren, et al.
Published: (2024)

CLIP-Guided Adaptable Self-Supervised Learning for Human-Centric Visual Tasks
by: Luo, Mingshuang, et al.
Published: (2026)

CoLeCLIP: Open-Domain Continual Learning via Joint Task Prompt and Vocabulary Learning
by: Li, Yukun, et al.
Published: (2024)

Exposing Vulnerabilities in Visible-Infrared VLMs: A Unified Geometric Adversarial Framework with Cross-Task Transferability
by: Chen, Xiang, et al.
Published: (2026)

Efficient and Effective Weight-Ensembling Mixture of Experts for Multi-Task Model Merging
by: Shen, Li, et al.
Published: (2024)

Semantic-aware Adversarial Fine-tuning for CLIP
by: Zhang, Jiacheng, et al.
Published: (2026)

BadPart: Unified Black-box Adversarial Patch Attacks against Pixel-wise Regression Tasks
by: Cheng, Zhiyuan, et al.
Published: (2024)

Robust Anti-Backdoor Instruction Tuning in LVLMs
by: Xun, Yuan, et al.
Published: (2025)

Texture Re-scalable Universal Adversarial Perturbation
by: Huang, Yihao, et al.
Published: (2024)

Radar-Camera BEV Multi-Task Learning with Cross-Task Attention Bridge for Joint 3D Detection and Segmentation
by: İnanç, Ahmet, et al.
Published: (2026)

Multi-Task Neural Architecture Search Using Architecture Embedding and Transfer Rank
by: Zhang, TingJie, et al.
Published: (2025)

Less is More: Fewer Interpretable Region via Submodular Subset Selection
by: Chen, Ruoyu, et al.
Published: (2024)

UMDATrack: Unified Multi-Domain Adaptive Tracking Under Adverse Weather Conditions
by: Yao, Siyuan, et al.
Published: (2025)

Mind the Gap: Preserving and Compensating for the Modality Gap in CLIP-Based Continual Learning
by: Huang, Linlan, et al.
Published: (2025)

A Survey on Transferability of Adversarial Examples across Deep Neural Networks
by: Gu, Jindong, et al.
Published: (2023)

VL-Trojan: Multimodal Instruction Backdoor Attacks against Autoregressive Visual Language Models
by: Liang, Jiawei, et al.
Published: (2024)