Exposing Functional Fusion: A New Class of Strategic Backdoor in Dynamic Prompt Architectures

Computer Science > Cryptography and Security [Submitted on 19 May 2026] Exposing Functional Fusion: A New Class of Strategic Backdoor in Dynamic Prompt Architectures Zeyao Liu, Zhendong Zhao, Xiaojun Chen, Xin Zhao, Yuexin Xuan, Xiaoshuang Ji Existing ViT backdoor attacks based on backbone-overwriting full-tuning are computationally expensive and inflict performance degradation. This has forced adversaries towards the Visual Parameter-Efficient Fine-Tuning (PEFT) paradigm, dominated by adapter-based (e.g., LoRA) and prompt-based (e.g., VPT) approaches. While adapter security has seen initial study, the risks of the burgeoning prompt-based ecosystem remain critically unexplored. We fill this critical gap, exposing how the evolution of VPT towards dynamic and context-aware architectures can facilitate a far more dangerous and emergent threat. This vulnerability arises even though these dynamic modules unlock superior benign performance. We propose VIPER, an attack framework built on a lightweight, dynamic Visual Prompt Generator (VPG) that demonstrates this vulnerability. Critically, this dynamic architecture enables Functional Fusion: an emergent phenomenon where malicious logic and benign task utility are tightly fused into the same sparse, high-magnitude parameter core. This fusion creates a formidable ``hostage" dilemma, as pruning the attack necessarily destroys the benign performance. Comprehensive evaluations show VIPER effectively addresses the attacker's trilemma: VIPER not only achieves state-of-the-art performance on clean data, but also maintains near-100% ASR even under 90% VPG-module pruning (where LoRA attacks collapse), while adding only an imperceptible 0.06ms (1.16%) of inference latency. VIPER's results, driven by Functional Fusion, expose a new, paradigm-level risk in dynamic prompt architectures. Subjects: Cryptography and Security (cs.CR); Computer Vision and Pattern Recognition (cs.CV) Cite as: arXiv:2605.19478 [cs.CR]   (or arXiv:2605.19478v1 [cs.CR] for this version)   https://doi.org/10.48550/arXiv.2605.19478 Focus to learn more Submission history From: Zeyao Liu [view email] [v1] Tue, 19 May 2026 07:29:34 UTC (3,437 KB) Access Paper: HTML (experimental) view license Current browse context: cs.CR < prev   |   next > new | recent | 2026-05 Change to browse by: cs cs.CV 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?)