9 citations · 17 across the 12 of their papers we have counts for
13 papers
VeriRouter: Towards Verifiable LLM Routing
Mengyu Yao, Ziqi Zhang, Shaofei Li +4
Large language model (LLM) routers are increasingly deployed to optimize quality, latency, and cost through dynamic model selection and request rewriting. However, a compromised ro…
RangeFactory: Scalable Construction of Multi-Hop Cyber Ranges
Hanlin Jiang, Puyi Wang, Jiandong Jin +10
Real-world cyberattacks often require sustained progress across multiple hosts and network segments, making multi-hop cyber ranges essential infrastructure for studying and improvi…
Connect the Dots: Knowledge Graph-Guided Crawler Attack on Retrieval-Augmented Generation Systems
Mengyu Yao, Ziqi Zhang, Ning Luo +5
Stealing attacks pose a persistent threat to the intellectual property of deployed machine-learning systems. Retrieval-augmented generation (RAG) intensifies this risk by extending…
Trustworthy and Controllable Professional Knowledge Utilization in Large Language Models with TEE-GPU Execution
Yifeng Cai, Zhida An, Yuhan Meng +5
Future improvements in large language model (LLM) services increasingly hinge on access to high-value professional knowledge rather than more generic web data. However, the data pr…
Who Grants the Agent Power? Defending Against Instruction Injection via Task-Centric Access Control
Yifeng Cai, Ziming Wang, Zhaomeng Deng +6
AI agents capable of GUI understanding and Model Context Protocol are increasingly deployed to automate mobile tasks. However, their reliance on over-privileged, static permissions…
Who Moved My Transaction? Uncovering Post-Transaction Auditability Vulnerabilities in Modern Super Apps
Junlin Liu, Zhaomeng Deng, Ziming Wang +6
Super apps are the cornerstones of modern digital life, embedding financial transactions into nearly every aspect of daily routine. The prevailing security paradigm for these platf…
Membership and Memorization in LLM Knowledge Distillation
Ziqi Zhang, Ali Shahin Shamsabadi, Hanxiao Lu +2
Recent advances in Knowledge Distillation (KD) aim to mitigate the high computational demands of Large Language Models (LLMs) by transferring knowledge from a large ''teacher'' to…
I Can Tell Your Secrets: Inferring Privacy Attributes from Mini-app Interaction History in Super-apps
Yifeng Cai, Ziqi Zhang, Mengyu Yao +8
Super-apps have emerged as comprehensive platforms integrating various mini-apps to provide diverse services. While super-apps offer convenience and enriched functionality, they ca…
Moss: Proxy Model-based Full-Weight Aggregation in Federated Learning with Heterogeneous Models
Yifeng Cai, Ziqi Zhang, Ding Li +2
Modern Federated Learning (FL) has become increasingly essential for handling highly heterogeneous mobile devices. Current approaches adopt a partial model aggregation paradigm tha…
TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models
Ding Li, Ziqi Zhang, Mengyu Yao +3
Trusted Execution Environments (TEE) are used to safeguard on-device models. However, directly employing TEEs to secure the entire DNN model is challenging due to the limited compu…
No Privacy Left Outside: On the (In-)Security of TEE-Shielded DNN Partition for On-Device ML
Ziqi Zhang, Chen Gong, Yifeng Cai +5
On-device ML introduces new security challenges: DNN models become white-box accessible to device users. Based on white-box information, adversaries can conduct effective model ste…
DistFL: Distribution-aware Federated Learning for Mobile Scenarios
Bingyan Liu, Yifeng Cai, Ziqi Zhang +5
Federated learning (FL) has emerged as an effective solution to decentralized and privacy-preserving machine learning for mobile clients. While traditional FL has demonstrated its…
TransTailor: Pruning the Pre-trained Model for Improved Transfer Learning
Bingyan Liu, Yifeng Cai, Yao Guo +1
The increasing of pre-trained models has significantly facilitated the performance on limited data tasks with transfer learning. However, progress on transfer learning mainly focus…