Syed Md Mukit Rashid, Abdullah Al Ishtiaq, Kai Tu, Yilu Dong, Tianwei Wu, Ali Ranjbar, Tianchang Yang, Najrin Sultana, Shagufta Mehnaz, Syed Rafiul Hussain. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Baseband firmware plays a critical role in cellular communication, yet its proprietary, closed-source nature and complex, stateful processing logic make systematic security testing challenging. Existing methods often fail to account for the interdependencies between baseband tasks and the statefulness of input processing logic, limiting their scope and effectiveness. We present Loris, a stateful fuzz testing frame-work designed to explore and analyze baseband firmware implementations effectively. We employ iterative symbolic analysis to progressively identify state variables and the predicates over them that define different protocol states, while alleviating the state explosion problem. It enables Loris to perform targeted exploration and fuzzing of program regions with high potential for vulnerabilities. We evaluated Loris across 5 commercial devices from two major vendors, covering both 4G Long-Term Evolution (LTE) and 5G New Radio (NR), demonstrating its broad applicability. Our testing revealed 7 new vulnerabilities exploitable by over-the-air attackers, potentially leading to baseband crashes, remote code execution, and denial of service.

We present 5GCVerif, a model-based testing framework designed to formally analyze the access control framework of the 5G Core. With its modular design, 5GCVerif employs various abstraction techniques to craft an abstract model that captures the intricate details of the 5G Core's access control mechanism. This approach offers customizability and extensibility in constructing the abstract model and addresses the state explosion problem in model checking. 5GCVerif also sidesteps the challenge of exhaustively generating models for all possible core network configurations by restricting the model checker to explore policy violations only within the valid network configurations. Using 5GCVerif, we evaluated 55 security properties, leading to the discovery of five new vulnerabilities in 5G Core's access control mechanism. The uncovered vulnerabilities can result in multiple attacks including unauthorized entry to sensitive information, illegitimate access to services, and denial-of-services.

Cryptographic misuse affects a sizeable portion of Android applications. However, there is only an empirical study that has been made about this problem. In this paper, we perform a systematic analysis on the cryptographic misuse, build the cryptographic misuse vulnerability model and implement a prototype tool Crypto Misuse Analyser (CMA). The CMA can perform static analysis on Android apps and select the branches that invoke the cryptographic API. Then it runs the app following the target branch and records the cryptographic API calls. At last, the CMA identifies the cryptographic API misuse vulnerabilities from the records based on the pre-defined model. We also analyze dozens of Android apps with the help of CMA and find that more than a half of apps are affected by such vulnerabilities.