Qi Li

Ensuring Security and Privacy Preservation for Cloud Data Services

2016 · ACM Computing Surveys

With the rapid development of cloud computing, more and more enterprises/individuals are starting to outsource local data to the cloud servers. However, under open networks and not fully trusted cloud environments, they face enormous security …

Data verification in information-centric networking with efficient revocable certificateless signature

2017

Information-centric networking (ICN), a strong candidate for future internet architecture, consists of two kinds of packets, interest and data packets, both of which carry the name of data content to be requested (or delivered). The …

Interface-Based Side Channel Attack Against Intel SGX

2018 · arXiv (Cornell University)

Intel has introduced a trusted computing technology, Intel Software Guard Extension (SGX), which provides an isolated and secure execution environment called enclave for a user program without trusting any privilege software (e.g., an operating system …

Joint Extraction of Entities and Relations for Chinese Text of Tea

2020

In view of the problems of polysemy and overlapping relations of Chinese tea text. In this paper, we present a joint model BERT-LCM-Tea for extraction of entities and relations, which combines the Bidirectional Encoder Representations …

Contrastive Learning for Cold-Start Recommendation

2021 · arXiv (Cornell University)

Recommending cold-start items is a long-standing and fundamental challenge in recommender systems. Without any historical interaction on cold-start items, CF scheme fails to use collaborative signals to infer user preference on these items. To solve …

Effective and Robust Physical-World Attacks on Deep Learning Face Recognition Systems

2021 · IEEE Transactions on Information Forensics and Security

Deep neural networks (DNNs) have been increasingly used in face recognition (FR) systems. Recent studies, however, show that DNNs are vulnerable to adversarial examples, which potentially mislead DNN-based FR systems in the physical world. Existing …

Automatic Generation of Adversarial Readable Chinese Texts

2022 · IEEE Transactions on Dependable and Secure Computing

Natural language processing (NLP) models are known vulnerable to adversarial examples, similar to image processing models. Studying adversarial texts is an essential step to improve the robustness of NLP models. However, existing studies mainly focus …

Distantly Supervised Named Entity Recognition via Confidence-Based Multi-Class Positive and Unlabeled Learning

2022 · arXiv (Cornell University)

In this paper, we study the named entity recognition (NER) problem under distant supervision. Due to the incompleteness of the external dictionaries and/or knowledge bases, such distantly annotated training data usually suffer from a high …

Hijacking Attacks against Neural Networks by Analyzing Training Data

2024 · arXiv (Cornell University)

Backdoors and adversarial examples are the two primary threats currently faced by deep neural networks (DNNs). Both attacks attempt to hijack the model behaviors with unintended outputs by introducing (small) perturbations to the inputs. Backdoor …

Retrieval Augmented Instruction Tuning for Open NER with Large Language Models

2024 · arXiv (Cornell University)

The strong capability of large language models (LLMs) has been applied to information extraction (IE) through either retrieval augmented prompting or instruction tuning (IT). However, the best way to incorporate information with LLMs for IE …

Tackling Feature Skew in Heterogeneous Federated Learning with Semantic Enhancement

2024

A critical challenge in federated learning is data heterogeneity, compounded by varying local data distribution, thereby significantly impacting the performance of both local and global models. Prior works struggle to effectively address data heterogeneity but …

Discrete Diffusion in Large Language and Multimodal Models: A Survey

2025 · arXiv (Cornell University)

In this work, we provide a systematic survey of Discrete Diffusion Language Models (dLLMs) and Discrete Diffusion Multimodal Language Models (dMLLMs). Unlike autoregressive (AR) models, dLLMs and dMLLMs adopt a multi-token, parallel decoding paradigm using …

TrafficLLM: Enhancing Large Language Models for Network Traffic Analysis with Generic Traffic Representation

2025 · arXiv (Cornell University)

Machine learning (ML) powered network traffic analysis has been widely used for the purpose of threat detection. Unfortunately, their generalization across different tasks and unseen data is very limited. Large language models (LLMs), known for …