8 citations · 18 across the 12 of their papers we have counts for
12 papers
When Context Gets Root: Privilege Escalation in LLM Harnesses
Xingbang He, Yuanwei Chen, Yi Qian +6
Instruction hierarchy is a model-side defense that assigns instructions different levels of privilege according to their sources. These levels constrain which content may direct mo…
Knowledge-Enhanced Agentic Vulnerability Repair
Sicong Cao, Hao Ma, Le Yu +8
Frontier foundation models have changed the math on vulnerability discovery, but the bigger challenge is how the remediation side keeps up. Despite recent progresses in Automated V…
FeatureFuzz: Treating Bug-prone Features as Core Primitives for Compiler Fuzzing
Xingbang He, Yuanwei Chen, Hao Wu +9
CI/CD pipelines often execute build and test tasks with high privileges, making the compilation stage security-sensitive. In this setting, malicious pull requests may exploit caref…
Mind the Gap: Action Rebinding Attacks against Android GUI Agents
Yi Qian, Kunwei Qian, Xingbang He +7
Large multimodal model powered GUI agents are emerging as high-privilege operators on mobile platforms, entrusted to perceive screen content and inject inputs across application bo…
Unleashing the Power of LLM to Infer State Machine from the Protocol Implementation
Haiyang Wei, Ligeng Chen, Zhengjie Du +7
State machines are essential for enhancing protocol analysis to identify vulnerabilities. However, inferring state machines from network protocol implementations is challenging due…
Finding Cross-rule Optimization Bugs in Datalog Engines
Chi Zhang, Linzhang Wang, Manuel Rigger
Datalog is a popular and widely-used declarative logic programming language. Datalog engines apply many cross-rule optimizations; bugs in them can cause incorrect results. To detec…
Automatic Detection, Validation and Repair of Race Conditions in Interrupt-Driven Embedded Software
Yu Wang, Fengjuan Gao, Linzhang Wang +4
Interrupt-driven programs are widely deployed in safety-critical embedded systems to perform hardware and resource dependent data operation tasks. The frequent use of interrupts in…
Infrared: A Meta Bug Detector
Chi Zhang, Yu Wang, Linzhang Wang
The recent breakthroughs in deep learning methods have sparked a wave of interest in learning-based bug detectors. Compared to the traditional static analysis tools, these bug dete…
WheaCha: A Method for Explaining the Predictions of Models of Code
Yu Wang, Ke Wang, Linzhang Wang
Attribution methods have emerged as a popular approach to interpreting model predictions based on the relevance of input features. Although the feature importance ranking can provi…
Learning Semantic Program Embeddings with Graph Interval Neural Network
Yu Wang, Fengjuan Gao, Linzhang Wang +1
Learning distributed representations of source code has been a challenging task for machine learning models. Earlier works treated programs as text so that natural language methods…
Learning a Static Bug Finder from Data
Yu Wang, Fengjuan Gao, Linzhang Wang +1
We present an alternative approach to creating static bug finders. Instead of relying on human expertise, we utilize deep neural networks to train static analyzers directly from da…
Online Verification of Control Parameter Calculations in Communication Based Train Control System
Lei Bu, Xin Chen, Linzhang Wang +1
Communication Based Train Control (CBTC) system is the state-of-the-art train control system. In a CBTC system, to guarantee the safety of train operation, trains communicate with…