Sep 2026· Proceedings of the ACM SIGOPS 32nd Symposium on Operating Systems Principles· 0 citations· 104 references
Computer Science
TL;DR
The StateLens framework is presented, a framework that employs Large Language Models (LLM) to automate the discovery of deep internal states and significantly outperforms state-of-the-art fuzzers and uncovers 68 new bugs.
Abstract
The security of the modern web depends on the correctness of JavaScript (JS) engines, yet these complex systems remain vulnerable to high-impact bugs. A critical limitation of state-of-the-art fuzzers is the coverage plateau: once a fuzzer saturates the control-flow graph, edge coverage loses its ability to guide discovery. Because complex engine behaviors, such as JIT optimization tiers and hidden class transitions, often share identical edge coverage, standard coverage metrics are blind to the distinct internal states required to trigger deep errors. To bridge this gap, we present StateLens, a framework that employs Large Language Models (LLM) to automate the discovery of deep internal states. Blindly placing instrumentation probes at all states is infeasible due to the vast state space and the high runtime overhead. State-Lens introduces a novel agent-based reasoning pipeline that emulates the intuition of a security researcher. By iteratively traversing code and developer comments, our agents intelligently select high-value instrumentation targets, effectively separating logic-driving states from irrelevant data. This results in synthesizable, high-signal feedback probes that map the engine's hidden configurations. This instrumentation feeds a dual-feedback mechanism, effectively guiding the fuzzer toward unexplored engine semantics. Our evaluation confirms that StateLens significantly outperforms state-of-the-art fuzzers and uncovers 68 new bugs.
Compiler fuzzing is critical for ensuring the reliability of modern optimizing compilers. However, traditional generators and raw Large Language Model (LLM) outputs often yield syntactically invalid or low-value programs, incurring significant computational overhead. In this paper, we present BanditFuzz, an end-to-end...
Dong-Hui Li, Ying-Ying Li, Jin-Long Xu et al.· Proceedings of the 41st IEEE...· 0 citations
Rust's type system protects safe code, but many low-level abstractions depend on internal unsafe operations whose correctness rests on memory and logical invariants. In struct-based abstractions, a sibling method may legally modify internal fields while invalidating a precondition required by another method's unsafe op...
Zi-Hao Rao, Yi-Lin Chen, Cheng-Jun Chen et al.· Proceedings of the 41st IEEE...· 0 citations
LANTERN, a specification-guided dynamic conformance testing framework that mutates CTS tests using constraints extracted from the WebGPU specification, is introduced, demonstrating that syntactically seeded, semantics-aware mutation of conformance tests provides a way to uncover browser bugs during WebGPU testing.
A security assessment on 75 FastAPI backends generated by three contemporary LLMs revealed a disconnect between functional correctness and secure logic, which is interpreted as a review-risk pattern, which is called the human-in-the-loop paradox.
Abdul Ali Khan, S. Rauti, T. Mäkilä· IEEE Access· 0 citations
Automatically generating high-coverage unit tests for complex Java methods remains a formidable challenge, particularly when execution paths are guarded by intricate control-flow nesting and cross-class state dependencies. Existing LLM-based approaches predominantly follow a goal-driven paradigm, relying on unguided co...
Rui-Guo Yu, Rui-Qi Dong, Xi Xiao et al.· Proceedings of the ACM on So...· 0 citations
This work introduces Path2Spec, a divide-and-conquer framework that leverages LLMs to extract all execution paths from an input program, generates path-specific specifications for each, and merges them into a comprehensive overall specification.
Dan Huang, Zhensu Sun, Hui-Hui Huang et al.· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.