arXiv (All)
open access
Region-Level Black-Box Defense Against Stealthy Embedding-Space Backdoors in CLIP
Contrastive Language--Image Pretraining (CLIP) has emerged as a dominant vision backbone due to its strong transferability and zero-shot capabilities. However, recent studies reveal a critical vulnerability: embedding-space backdoor attacks. By poisoning only a tiny fraction of image--text pairs, ad
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- Improving Generalizability and Undetectability for Targeted Adversarial Attacks on Multimodal Pre-trained Models#972958
- Hearing the Unspoken: Language Model Priors for Acoustic Adversarial Attacks#266128
- Render Before Reading: Visual Rendering as a Prompt Injection Defense#1130963
- Render Before Reading: Visual Rendering as a Prompt Injection Defense#1122234
- Backdoor as Probe: Test-Time Adversarial Defense for CLIP#1128903
Record · ID 1106257
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive