Beyond Native Success: Auditing Deployment-Interface Exposure of CLIP Backdoors

Computer Science > Cryptography and Security [Submitted on 16 Jun 2026] Beyond Native Success: Auditing Deployment-Interface Exposure of CLIP Backdoors Kunlan Xiang, Haomiao Yang, Wenbo Jiang Contrastive Language-Image Pre-training models are widely reused across downstream interfaces, including feature extraction, retrieval, reranking, and selection. Existing CLIP backdoor, however, usually validate attacks on a small attack-native task, leaving unclear whether the same poisoned checkpoint remains exposed, weakens, or becomes not applicable when reused through other interfaces. We introduce DIFE, a Deployment-Interface Footprint Evaluation framework that audits backdoored CLIP checkpoints across deployment interfaces. DIFE makes various evaluations comparable by specifying each interface's component readout, trigger channel, target event, reference condition, and metric. DIFE also introduces effective-footprint diagnosis to identify the reusable CLIP component or component combination that carries exposure and explains where risk transfers. Auditing reproduced CLIP backdoors with DIFE reveals a structured landscape: native success is not a checkpoint-level risk certificate, exposure follows component footprints, text-side poisoning does not yield textual-encoder control, and some coupled attacks remain mechanism-bound. This audit reveals a import gapin existing CLIP backdoors: a textual encoder that itself becomes a reusable carrier of adversarial behavior. We therefore introduce BadTextTower to fill this gap. BadTextTower produces strong text-conditioned retrieval, reranking, and selection exposure while leaving visual-only reuse nearly clean. Subjects: Cryptography and Security (cs.CR); Computation and Language (cs.CL) Cite as: arXiv:2606.17815 [cs.CR]   (or arXiv:2606.17815v1 [cs.CR] for this version)   https://doi.org/10.48550/arXiv.2606.17815 Focus to learn more Submission history From: Kunlan Xiang [view email] [v1] Tue, 16 Jun 2026 11:41:53 UTC (16,982 KB) Access Paper: HTML (experimental) view license Current browse context: cs.CR < prev   |   next > new | recent | 2026-06 Change to browse by: cs cs.CL References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)