10 papers
TAI3: Testing Agent Integrity in Interpreting User Intent
Shiwei Feng, Xiangzhe Xu, Xuan Chen +5
LLM agents are increasingly deployed to automate real-world tasks by invoking APIs through natural language instructions. While powerful, they often suffer from misinterpretation o…
KE: Matryoshka Unstructured Knowledge Editing of Large Language Models
Zian Su, Ziyang Huang, Kaiyuan Zhang +1
Large language models (LLMs) have emerged as powerful knowledge bases yet are limited by static training data, leading to issues such as hallucinations and safety risks. Editing a…
Position: Intelligent Coding Systems Should Write Programs with Justifications
Xiangzhe Xu, Shiwei Feng, Zian Su +2
Intelligent coding systems are transforming software development by enabling users to specify code behavior in natural language. However, the opaque decision-making of AI-driven co…
ASTRA: Autonomous Spatial-Temporal Red-teaming for AI Software Assistants
Xiangzhe Xu, Guangyu Shen, Zian Su +9
AI coding assistants like GitHub Copilot are rapidly transforming software development, but their safety remains deeply uncertain-especially in high-stakes domains like cybersecuri…
SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks
Kaiyuan Zhang, Siyuan Cheng, Hanxi Guo +8
Large language models (LLMs) have achieved remarkable success and are widely adopted for diverse applications. However, fine-tuning these models often involves private or sensitive…
ProSec: Fortifying Code LLMs with Proactive Security Alignment
Xiangzhe Xu, Zian Su, Jinyao Guo +3
While recent code-specific large language models (LLMs) have greatly enhanced their code generation capabilities, the safety of these models remains under-explored, posing potentia…