When Efficiency Backfires: Cascading LLMs Trigger Cascade Failure under Adversarial Attack

Computer Science > Cryptography and Security [Submitted on 17 May 2026] When Efficiency Backfires: Cascading LLMs Trigger Cascade Failure under Adversarial Attack Zehan Sun, Dingfan Chen, Songze Li Large Language Model (LLM) cascade systems are designed to balance efficiency and performance by processing queries with lightweight models while selectively escalating complex cases to more powerful ones. Such systems seek to reduces computational cost and latency while maintaining task performance, making it an appealing choice for large-scale deployment. However, the cascade design introduces new vulnerabilities through an expanded attack surface: the inclusion of lightweight front-end models and internal decision mechanisms introduces new weaknesses. In this work, we present the first study demonstrating that LLM cascade systems are susceptible to targeted adversarial manipulation, which disrupts both performance objectives and the intended cost advantages of the cascade design. We propose a novel attack framework that employs constrained sequential collaborative optimization of adversarial suffix under cascade dependencies, enabling simultaneous exploitation of lightweight models and decision mechanisms. This framework adapts to adversaries with varying capabilities, inducing controllable degradation in both cost-efficiency and accuracy. Unlike prior attacks targeting standalone models, our approach strategically leverages the cascade structure to achieve significantly stronger impact. Extensive experiments across diverse datasets and representative LLM cascade systems validate the practicality and severity of this attack. Our findings highlight the urgent need to rigorously scrutinize the security of LLM cascade systems and call for broader attention to the systemic risks inherent in such designs. Comments: under review Subjects: Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI) Cite as: arXiv:2605.17288 [cs.CR]   (or arXiv:2605.17288v1 [cs.CR] for this version)   https://doi.org/10.48550/arXiv.2605.17288 Focus to learn more Submission history From: Zehan Sun [view email] [v1] Sun, 17 May 2026 06:59:43 UTC (1,319 KB) Access Paper: HTML (experimental) view license Current browse context: cs.CR < prev   |   next > new | recent | 2026-05 Change to browse by: cs cs.AI 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?)