4 papers
Beyond Visual Safety: Jailbreaking Multimodal Large Language Models for Harmful Image Generation via Semantic-Agnostic Inputs
Mingyu Yu, Lana Liu, Zhehao Zhao +2
The rapid advancement of Multimodal Large Language Models (MLLMs) has introduced complex security challenges, particularly at the intersection of textual and visual safety. While e…
SeeWasm: An Efficient and Fully-Functional Symbolic Execution Engine for WebAssembly Binaries
Ningyu He, Zhehao Zhao, Hanqin Guan +6
WebAssembly (Wasm), as a compact, fast, and isolation-guaranteed binary format, can be compiled from more than 40 high-level programming languages. However, vulnerabilities in Wasm…
Eunomia: Enabling User-specified Fine-Grained Search in Symbolically Executing WebAssembly Binaries
Ningyu He, Zhehao Zhao, Jikai Wang +7
Although existing techniques have proposed automated approaches to alleviate the path explosion problem of symbolic execution, users still need to optimize symbolic execution by ap…
Precise Learning of Source Code Contextual Semantics via Hierarchical Dependence Structure and Graph Attention Networks
Zhehao Zhao, Bo Yang, Ge Li +2
Deep learning is being used extensively in a variety of software engineering tasks, e.g., program classification and defect prediction. Although the technique eliminates the requir…