Publications (13)
AI Security Beyond Core Domains: Resume Screening as a Case Study of Adversarial Vulnerabilities in Specialized LLM Applications
Honglin Mu, Jinghao Liu, Kaiyang Wan +4
Large Language Models (LLMs) excel at text comprehension and generation, making them ideal for automated tasks like code review and content moderation. However, our research identi…
Control Illusion: The Failure of Instruction Hierarchies in Large Language Models
Yilin Geng, Haonan Li, Honglin Mu +5
Large language models (LLMs) are increasingly deployed with hierarchical instruction schemes, where certain instructions (e.g., system-level directives) are expected to take preced…
Beyond Static Evaluation: A Dynamic Approach to Assessing AI Assistants' API Invocation Capabilities
Honglin Mu, Yang Xu, Yunlong Feng +4
With the rise of Large Language Models (LLMs), AI assistants' ability to utilize tools, especially through API calls, has advanced notably. This progress has necessitated more accu…
Improving Domain Generalization for Sound Classification with Sparse Frequency-Regularized Transformer
Honglin Mu, Wentian Xia, Wanxiang Che
Sound classification models' performance suffers from generalizing on out-of-distribution (OOD) data. Numerous methods have been proposed to help the model generalize. However, mos…
Self-Constructed Context Decompilation with Fined-grained Alignment Enhancement
Yunlong Feng, Dechuan Teng, Yang Xu +5
Decompilation transforms compiled code back into a high-level programming language for analysis when source code is unavailable. Previous work has primarily focused on enhancing de…
Against The Achilles' Heel: A Survey on Red Teaming for Generative Models
Lizhi Lin, Honglin Mu, Zenan Zhai +9
Generative models are rapidly gaining popularity and being integrated into everyday applications, raising concerns over their safe use as various vulnerabilities are exposed. In li…