Publications (19)
Explainer-guided Targeted Adversarial Attacks against Binary Code Similarity Detection Models
Mingjie Chen, Tiancheng Zhu, Mingxue Zhang +4
Binary code similarity detection (BCSD) serves as a fundamental technique for various software engineering tasks, e.g., vulnerability detection and classification. Attacks against…
Is "Knowing It's Malicious Enough?" Evaluating LLMs for Fine-Grained Malware Behavior Auditing
Xinran Zheng, Xingzhi Qian, Yiling He +2
Automated malware classifiers achieve strong detection performance, but auditing requires more than flagging a sample: analysts must explain malicious behaviors and justify them wi…
Retrofit: Continual Learning with Controlled Forgetting for Binary Security Detection and Analysis
Yiling He, Junchi Lei, Hongyu She +5
Binary security has increasingly relied on deep learning to reason about malware behavior and program semantics. However, the performance often degrades as threat landscapes evolve…
Boosting Illuminant Estimation in Deep Color Constancy through Enhancing Brightness Robustness
Mengda Xie, Chengzhi Zhong, Yiling He +2
Color constancy estimates illuminant chromaticity to correct color-biased images. Recently, Deep Neural Network-driven Color Constancy (DNNCC) models have made substantial advancem…
LAMD: Context-driven Android Malware Detection and Classification with LLMs
Xingzhi Qian, Xinran Zheng, Yiling He +2
The rapid growth of mobile applications has escalated Android malware threats. Although there are numerous detection methods, they often struggle with evolving attacks, dataset bia…
RetouchUAA: Unconstrained Adversarial Attack via Image Retouching
Mengda Xie, Yiling He, Meie Fang
Deep Neural Networks (DNNs) are susceptible to adversarial examples. Conventional attacks generate controlled noise-like perturbations that fail to reflect real-world scenarios and…
Malaika: Understanding Malware through Tri-Grounded Agentic Reasoning
Xingzhi Qian, Xinran Zheng, Yiling He +1
Recent LLM-based systems have shown promising capabilities for security-focused code analysis. Malware understanding, however, poses a distinct challenge: analysts must reconstruct…
TaFD: Threat-Aware Frequency Decoupling for Adversarial Robustness against Heterogeneous Attacks
Mengda Xie, Yiling He, Meie Fang
Multi-threat robustness remains a fundamental challenge in deep learning. Although joint adversarial training (JAT) is widely adopted, it suffers from negative transfer under heter…
Esim: EVM Bytecode Similarity Detection Based on Stable-Semantic Graph
Zhuo Chen, Gaoqiang Ji, Yiling He +2
Decentralized finance (DeFi) is experiencing rapid expansion. However, prevalent code reuse and limited open-source contributions have introduced significant challenges to the bloc…
FINER: Enhancing State-of-the-art Classifiers with Feature Attribution to Facilitate Security Analysis
Yiling He, Jian Lou, Zhan Qin +1
Deep learning classifiers achieve state-of-the-art performance in various risk detection applications. They explore rich semantic representations and are supposed to automatically…
Pitfalls in Language Models for Code Intelligence: A Taxonomy and Survey
Xinyu She, Yue Liu, Yanjie Zhao +5
Modern language models (LMs) have been successfully employed in source code generation and understanding, leading to a significant increase in research focused on learning-based co…
ShadowCode: Towards (Automatic) External Prompt Injection Attack against Code LLMs
Yuchen Yang, Yiming Li, Hongwei Yao +5
Recent advancements have led to the widespread adoption of code-oriented large language models (Code LLMs) for programming tasks. Despite their success in deployment, their securit…
On Benchmarking Code LLMs for Android Malware Analysis
Yiling He, Hongyu She, Xingzhi Qian +4
Large Language Models (LLMs) have demonstrated strong capabilities in various code intelligence tasks. However, their effectiveness for Android malware analysis remains underexplor…
DeUEDroid: Detecting Underground Economy Apps Based on UTG Similarity
Zhuo Chen, Jie Liu, Yubo Hu +7
In recent years, the underground economy is proliferating in the mobile system. These underground economy apps (UEware) make profits from providing non-compliant services, especial…
BrutePrint: Expose Smartphone Fingerprint Authentication to Brute-force Attack
Yu Chen, Yiling He
Fingerprint authentication has been widely adopted on smartphones to complement traditional password authentication, making it a tempting target for attackers. The smartphone indus…
Red-Teaming Agent Execution Contexts: Open-World Security Evaluation on OpenClaw
Hongwei Yao, Yiming Liu, Yiling He +1
Agentic language-model systems increasingly rely on mutable execution contexts, including files, memory, tools, skills, and auxiliary artifacts, creating security risks beyond expl…
Learning to Focus: Context Extraction for Efficient Code Vulnerability Detection with Language Models
Xinran Zheng, Xingzhi Qian, Huichi Zhou +4
Language models (LMs) show promise for vulnerability detection but struggle with long, real-world code due to sparse and uncertain vulnerability locations. These issues, exacerbate…
Explanation as a Watermark: Towards Harmless and Multi-bit Model Ownership Verification via Watermarking Feature Attribution
Shuo Shao, Yiming Li, Hongwei Yao +3
Ownership verification is currently the most critical and widely adopted post-hoc method to safeguard model copyright. In general, model owners exploit it to identify whether a giv…
Combating Concept Drift with Explanatory Detection and Adaptation for Android Malware Classification
Yiling He, Junchi Lei, Zhan Qin +2
Machine learning-based Android malware classifiers achieve high accuracy in stationary environments but struggle with concept drift. The rapid evolution of malware, especially with…