14 citations · 35 across the 13 of their papers we have counts for
15 papers
Weaponizing the Exit: Input Privacy Leakage via Exit Routing Manipulation in Multi-Exit Networks
Yulong Tian, Lei Wang, Jincan Yang +4
Multi-exit networks improve inference efficiency by allowing inputs to terminate early at intermediate exits. We identify a privacy vulnerability in cloud deployments of these netw…
Usability as a Weapon: Attacking the Safety of LLM-Based Code Generation via Usability Requirements
Yue Li, Xiao Li, Hao Wu +5
Large Language Models (LLMs) are increasingly used for automated software development, making their ability to preserve secure coding practices critical. In practice, however, many…
A Systematic Study of Code Obfuscation Against LLM-based Vulnerability Detection
Xiao Li, Yue Li, Hao Wu +4
As large language models (LLMs) are increasingly adopted for code vulnerability detection, their reliability and robustness across diverse vulnerability types have become a pressin…
ConneX: Automatically Resolving Transaction Opacity of Cross-Chain Bridges for Security Analysis
Hanzhong Liang, Yue Duan, Xing Su +5
As the Web3 ecosystem evolves toward a multi-chain architecture, cross-chain bridges have become critical infrastructure for enabling interoperability between diverse blockchain ne…
Revealing Adversarial Smart Contracts through Semantic Interpretation and Uncertainty Estimation
Yating Liu, Xing Su, Hao Wu +4
Adversarial smart contracts, mostly on EVM-compatible chains like Ethereum and BSC, are deployed as EVM bytecode to exploit vulnerable smart contracts for financial gain. Detecting…
LLM-based Human-like Traffic Simulation for Self-driving Tests
Wendi Li, Hao Wu, Han Gao +3
Ensuring realistic traffic dynamics is a prerequisite for simulation platforms to evaluate the reliability of self-driving systems before deployment in the real world. Because most…
When LLMs Copy to Think: Uncovering Copy-Guided Attacks in Reasoning LLMs
Yue Li, Xiao Li, Hao Wu +4
Large Language Models (LLMs) have become integral to automated code analysis, enabling tasks such as vulnerability detection and code comprehension. However, their integration intr…
Everything You Wanted to Know About LLM-based Vulnerability Detection But Were Afraid to Ask
Yue Li, Xiao Li, Hao Wu +5
Large Language Models are a promising tool for automated vulnerability detection, thanks to their success in code generation and repair. However, despite widespread adoption, a cri…
Privacy-Preserving Federated Learning via Dataset Distillation
ShiMao Xu, Xiaopeng Ke, Xing Su +4
Federated Learning (FL) allows users to share knowledge instead of raw data to train a model with high accuracy. Unfortunately, during the training, users lose control over the kno…
If LLMs Would Just Look: Simple Line-by-line Checking Improves Vulnerability Localization
Yue Li, Xiao Li, Hao Wu +5
The rapid expansion of software systems and the growing number of reported vulnerabilities have emphasized the importance of accurately identifying vulnerable code segments. Tradit…
CoAst: Validation-Free Contribution Assessment for Federated Learning based on Cross-Round Valuation
Hao Wu, Likun Zhang, Shucheng Li +2
In the federated learning (FL) process, since the data held by each participant is different, it is necessary to figure out which participant has a higher contribution to the model…
Automation Slicing and Testing for in-App Deep Learning Models
Hao Wu, Yuhang Gong, Xiaopeng Ke +5
Intelligent Apps (iApps), equipped with in-App deep learning (DL) models, are emerging to offer stable DL inference services. However, App marketplaces have trouble auto testing iA…
Self-supervised Incremental Deep Graph Learning for Ethereum Phishing Scam Detection
Shucheng Li, Fengyuan Xu, Runchuan Wang +1
In recent years, phishing scams have become the crime type with the largest money involved on Ethereum, the second-largest blockchain platform. Meanwhile, graph neural network (GNN…
LEAP: TrustZone Based Developer-Friendly TEE for Intelligent Mobile Apps
Lizhi Sun, Shuocheng Wang, Hao Wu +5
ARM TrustZone is widely deployed on commercial-off-the-shelf mobile devices for secure execution. However, many Apps cannot enjoy this feature because it brings many constraints to…
Graph-to-Tree Neural Networks for Learning Structured Input-Output Translation with Applications to Semantic Parsing and Math Word Problem
Shucheng Li, Lingfei Wu, Shiwei Feng +3
The celebrated Seq2Seq technique and its numerous variants achieve excellent performance on many tasks such as neural machine translation, semantic parsing, and math word problem s…