5 citations · 8 across the 18 of their papers we have counts for
19 papers
Vision Token Manipulation Attacks on Cloud-Edge Inference of Large Vision-Language Models
Zikai Zhang, Rui Hu, Olivera Kotevska +1
Cloud-edge Large Vision-Language Model (LVLM) inference enables efficient deployment by splitting computation between edge devices and cloud servers. In this process, intermediate…
VeriDrive: Verifiable Counterfactual Supervision for Cost-Efficient Vision-Language Planning
Zikai Zhang, Hubert P. H. Shum, Toby P. Breckon
Vision-language driving models increasingly use reasoning supervision to bridge perception, prediction, and planning, but existing driving rationales are often free-form and expens…
SelfGrader: LLM Jailbreak Detection via Anchored Token-Level Logits
Zikai Zhang, Rui Hu, Olivera Kotevska +1
Large Language Models (LLMs) are powerful tools for answering user queries, yet they remain highly vulnerable to jailbreak attacks. Existing guardrail methods typically rely on int…
XMark: Reliable Multi-Bit Watermarking for LLM-Generated Texts
Jiahao Xu, Rui Hu, Olivera Kotevska +1
Multi-bit watermarking has emerged as a promising solution for embedding imperceptible binary messages into Large Language Model (LLM)-generated text, enabling reliable attribution…
FedUTR: Federated Recommendation with Augmented Universal Textual Representation for Sparse Interaction Scenarios
Kang Fu, Honglei Zhang, Zikai Zhang +5
Federated recommendations (FRs) have emerged as an on-device privacy-preserving paradigm, attracting considerable attention driven by rising demands for data security. Existing FRs…
Heterogeneous Federated Fine-Tuning with Parallel One-Rank Adaptation
Zikai Zhang, Rui Hu, Jiahao Xu
Large Language Models (LLMs) have demonstrated remarkable effectiveness in adapting to downstream tasks through fine-tuning. Federated Learning (FL) extends this capability by enab…
On the Out-of-Distribution Backdoor Attack for Federated Learning
Jiahao Xu, Zikai Zhang, Rui Hu
Traditional backdoor attacks in federated learning (FL) operate within constrained attack scenarios, as they depend on visible triggers and require physical modifications to the ta…
Majority Bit-Aware Watermarking For Large Language Models
Jiahao Xu, Rui Hu, Olivera Kotevska +1
The growing deployment of Large Language Models (LLMs) has raised concerns about their misuse in generating harmful or deceptive content. To address this issue, watermarking method…
Fed-HeLLo: Efficient Federated Foundation Model Fine-Tuning with Heterogeneous LoRA Allocation
Zikai Zhang, Ping Liu, Jiahao Xu +1
Federated Learning has recently been utilized to collaboratively fine-tune foundation models across multiple clients. Notably, federated low-rank adaptation LoRA-based fine-tuning…
FlowerTune: A Cross-Domain Benchmark for Federated Fine-Tuning of Large Language Models
Yan Gao, Massimo Roberto Scamarcia, Javier Fernandez-Marques +18
Large Language Models (LLMs) have achieved state-of-the-art results across diverse domains, yet their development remains reliant on vast amounts of publicly available data, raisin…
Traceable Black-box Watermarks for Federated Learning
Jiahao Xu, Rui Hu, Olivera Kotevska +1
Due to the distributed nature of Federated Learning (FL) systems, each local client has access to the global model, which poses a critical risk of model leakage. Existing works hav…
Detecting Backdoor Attacks in Federated Learning via Direction Alignment Inspection
Jiahao Xu, Zikai Zhang, Rui Hu
The distributed nature of training makes Federated Learning (FL) vulnerable to backdoor attacks, where malicious model updates aim to compromise the global model's performance on s…
ROMA: a Read-Only-Memory-based Accelerator for QLoRA-based On-Device LLM
Wenqiang Wang, Yijia Zhang, Zikai Zhang +4
As large language models (LLMs) demonstrate powerful capabilities, deploying them on edge devices has become increasingly crucial, offering advantages in privacy and real-time inte…
Identify Backdoored Model in Federated Learning via Individual Unlearning
Jiahao Xu, Zikai Zhang, Rui Hu
Backdoor attacks present a significant threat to the robustness of Federated Learning (FL) due to their stealth and effectiveness. They maintain both the main task of the FL system…
Fed-pilot: Optimizing LoRA Allocation for Efficient Federated Fine-Tuning with Heterogeneous Clients
Zikai Zhang, Rui Hu, Ping Liu +1
Federated Learning enables the fine-tuning of foundation models (FMs) across distributed clients for specific tasks; however, its scalability is limited by the heterogeneity of cli…
Achieving Byzantine-Resilient Federated Learning via Layer-Adaptive Sparsified Model Aggregation
Jiahao Xu, Zikai Zhang, Rui Hu
Federated Learning (FL) enables multiple clients to collaboratively train a model without sharing their local data. Yet the FL system is vulnerable to well-designed Byzantine attac…
Federated Learning for Smart Grid: A Survey on Applications and Potential Vulnerabilities
Zikai Zhang, Suman Rath, Jiahao Xu +1
The Smart Grid (SG) is a critical energy infrastructure that collects real-time electricity usage data to forecast future energy demands using information and communication technol…
Byzantine-Robust Federated Learning with Variance Reduction and Differential Privacy
Zikai Zhang, Rui Hu
Federated learning (FL) is designed to preserve data privacy during model training, where the data remains on the client side (i.e., IoT devices), and only model updates of clients…
Distractor-Aware Fast Tracking via Dynamic Convolutions and MOT Philosophy
Zikai Zhang, Bineng Zhong, Shengping Zhang +3
A practical long-term tracker typically contains three key properties, i.e. an efficient model design, an effective global re-detection strategy and a robust distractor awareness m…