Region-Level Black-Box Defense Against Stealthy Embedding-Space Backdoors in CLIP

arXiv:2609.31558 · cs.CV, cs.CR · Submitted 2026-09-25 · Read on arXiv

cs.CV, cs.CR

Submitted: 2026-09-25

Updated: 2026-09-25

Code: https://github.com/wsu-cyber-security-lab-ai/CLIPGuard

Terminology

• Accuracy — 13× in this paper · explained in 1 episode
• Robustness — 11× in this paper · explained in 5 episodes
• Clean Accuracy — 10× in this paper
• Alignment — 8× in this paper · explained in 1 episode
• Embeddings — 6× in this paper · explained in 2 episodes
• Attack Success Rate — 5× in this paper
• Contrastive Learning — 5× in this paper · explained in 5 episodes
• Fine-Tuning — 5× in this paper · explained in 5 episodes
• Cosine Similarity — 3× in this paper · explained in 3 episodes
• Transferability — 3× in this paper · explained in 4 episodes
• Attack Success Rate (ASR) — 1× in this paper · explained in 2 episodes
• Benchmark — 1× in this paper · explained in 2 episodes
• Clustering — 1× in this paper · explained in 2 episodes
• Computational overhead — 1× in this paper · explained in 2 episodes
• Diffusion Model — 1× in this paper · explained in 8 episodes
• Diffusion Models — 1× in this paper · explained in 6 episodes
• Generalizability — 1× in this paper · explained in 6 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Latent Diffusion Model — 1× in this paper · explained in 2 episodes
• Latent Diffusion Models — 1× in this paper · explained in 2 episodes
• Linear Probing — 1× in this paper · explained in 2 episodes
• Model-Agnostic — 1× in this paper · explained in 2 episodes
• Regularization — 1× in this paper · explained in 3 episodes
• Stable Diffusion Inpainting — 1× in this paper

Sources

• Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning
• Backdoor Attacks and Countermeasures on Deep Learning: A Comprehensive Review
• BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain
• Adversarial Backdoor Defense in CLIP
• Generalized Out-of-Distribution Detection and Beyond in Vision Language Model Era: A Survey
• Test-Time Multimodal Backdoor Detection by Contrastive Prompting
• Perturb and Recover: Fine-tuning for Effective Backdoor Removal from CLIP
• SCAM: A Real-World Typographic Robustness Evaluation for Multimodal Foundation Models
• CleanerCLIP: Fine-grained Counterfactual Semantic Augmentation for Backdoor Defense in Contrastive Learning

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