4 citations · 11 across the 12 of their papers we have counts for
13 papers
Reward-Aligned Distillation
Yilan Chen, Zian Su, Manish Prajapat +4
Reinforcement learning with verifiable rewards improves the reasoning capabilities of large language models, but remains computationally expensive and sample inefficient. On-policy…
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…
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…
LLM Agents Should Employ Security Principles
Kaiyuan Zhang, Zian Su, Pin-Yu Chen +3
Large Language Model (LLM) agents show considerable promise for automating complex tasks using contextual reasoning; however, interactions involving multiple agents and the system'…
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…
RepoAudit: An Autonomous LLM-Agent for Repository-Level Code Auditing
Jinyao Guo, Chengpeng Wang, Xiangzhe Xu +2
Code auditing is the process of reviewing code with the aim of identifying bugs. Large Language Models (LLMs) have demonstrated promising capabilities for this task without requiri…
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…
Source Code Foundation Models are Transferable Binary Analysis Knowledge Bases
Zian Su, Xiangzhe Xu, Ziyang Huang +2
Human-Oriented Binary Reverse Engineering (HOBRE) lies at the intersection of binary and source code, aiming to lift binary code to human-readable content relevant to source code,…
CodeArt: Better Code Models by Attention Regularization When Symbols Are Lacking
Zian Su, Xiangzhe Xu, Ziyang Huang +4
Transformer based code models have impressive performance in many software engineering tasks. However, their effectiveness degrades when symbols are missing or not informative. The…
LLMDFA: Analyzing Dataflow in Code with Large Language Models
Chengpeng Wang, Wuqi Zhang, Zian Su +3
Dataflow analysis is a fundamental code analysis technique that identifies dependencies between program values. Traditional approaches typically necessitate successful compilation…
Symbol Preference Aware Generative Models for Recovering Variable Names from Stripped Binary
Xiangzhe Xu, Zhuo Zhang, Zian Su +8
Decompilation aims to recover the source code form of a binary executable. It has many security applications, such as malware analysis, vulnerability detection, and code hardening.…