2 citations · 5 across the 22 of their papers we have counts for
23 papers
OLMo-Detect: A Multi-Stage, Confounder-Controlled Benchmark for Membership Inference on Large Language Models
Tao Shi, Chaoyi Xiang, Qiongkai Xu +1
Membership inference on large language models (LLMs) aims to determine whether a given text sample was included in an LLM's training data, without access to its training corpus. De…
Adaptive Cost-Efficient Evaluation for Reliable Patent Claim Generation
Yongmin Yoo, Qiongkai Xu, Longbing Cao
Automated patent claim validation demands low error tolerance. However, existing approaches face a rigidity-resource dilemma: lightweight encoders cannot track long-range legal dep…
Heterogeneous Dependency Graph-Guided Attentionfor Patent Representation Learning
Yongmin Yoo, Qiongkai Xu, Zhangkai Wu +1
Pre-trained language models advance patent classification and retrieval by encoding claims as flat token sequences, but they overlook the dependency hierarchy among claims. Incorpo…
Beyond Theoretical Bounds: Empirical Privacy Loss Calibration for Text Rewriting Under Local Differential Privacy
Weijun Li, Arnaud Grivet Sébert, Qiongkai Xu +2
The growing use of large language models has increased interest in sharing textual data in a privacy-preserving manner. One prominent line of work addresses this challenge through…
Who Wrote the Book? Detecting and Attributing LLM Ghostwriters
Anudeex Shetty, Qiongkai Xu, Olga Ohrimenko +1
In this paper, we introduce GhostWriteBench, a dataset for LLM authorship attribution. It comprises long-form texts (50K+ words per book) generated by frontier LLMs, and is designe…
Fault-Tolerant Evaluation for Sample-Efficient Model Performance Estimators
Zihan Zhu, Yanqiu Wu, Qiongkai Xu
In the era of Model-as-a-Service, organizations increasingly rely on third-party AI models for rapid deployment. However, the dynamic nature of emerging AI applications, the contin…
Semantic Leakage from Image Embeddings
Yiyi Chen, Qiongkai Xu, Desmond Elliott +2
Image embeddings are generally assumed to pose limited privacy risk. We challenge this assumption by formalizing semantic leakage as the ability to recover semantic structures from…
PatentMind: A Multi-Aspect Reasoning Graph for Patent Similarity Evaluation
Yongmin Yoo, Qiongkai Xu, Longbing Cao
Patent similarity evaluation plays a critical role in intellectual property analysis. However, existing methods often overlook the intricate structure of patent documents, which in…
PatentScore: Multi-dimensional Evaluation of LLM-Generated Patent Claims
Yongmin Yoo, Qiongkai Xu, Longbing Cao
High-stakes texts such as patent claims, medical records, and technical reports are structurally complex and demand a high degree of reliability and precision. While large language…
GRADA: Graph-based Reranking against Adversarial Documents Attack
Jingjie Zheng, Aryo Pradipta Gema, Giwon Hong +4
Retrieval Augmented Generation (RAG) frameworks improve the accuracy of large language models (LLMs) by integrating external knowledge from retrieved documents, thereby overcoming…
Defending against Backdoor Attacks via Module Switching
Weijun Li, Ansh Arora, Xuanli He +2
Backdoor attacks pose a serious threat to deep neural networks (DNNs), allowing adversaries to implant triggers for hidden behaviors in inference. Defending against such vulnerabil…
ALGEN: Few-shot Inversion Attacks on Textual Embeddings using Alignment and Generation
Yiyi Chen, Qiongkai Xu, Johannes Bjerva
With the growing popularity of Large Language Models (LLMs) and vector databases, private textual data is increasingly processed and stored as numerical embeddings. However, recent…
Overview of the 2024 ALTA Shared Task: Detect Automatic AI-Generated Sentences for Human-AI Hybrid Articles
Diego Mollá, Qiongkai Xu, Zijie Zeng +1
The ALTA shared tasks have been running annually since 2010. In 2024, the purpose of the task is to detect machine-generated text in a hybrid setting where the text may contain por…
Cut the Deadwood Out: Backdoor Purification via Guided Module Substitution
Yao Tong, Weijun Li, Xuanli He +2
Model NLP models are commonly trained (or fine-tuned) on datasets from untrusted platforms like HuggingFace, posing significant risks of data poisoning attacks. A practical yet und…
WET: Overcoming Paraphrasing Vulnerabilities in Embeddings-as-a-Service with Linear Transformation Watermarks
Anudeex Shetty, Qiongkai Xu, Jey Han Lau
Embeddings-as-a-Service (EaaS) is a service offered by large language model (LLM) developers to supply embeddings generated by LLMs. Previous research suggests that EaaS is prone t…
IDT: Dual-Task Adversarial Attacks for Privacy Protection
Pedro Faustini, Shakila Mahjabin Tonni, Annabelle McIver +2
Natural language processing (NLP) models may leak private information in different ways, including membership inference, reconstruction or attribute inference attacks. Sensitive in…
Seeing the Forest through the Trees: Data Leakage from Partial Transformer Gradients
Weijun Li, Qiongkai Xu, Mark Dras
Recent studies have shown that distributed machine learning is vulnerable to gradient inversion attacks, where private training data can be reconstructed by analyzing the gradients…
SEEP: Training Dynamics Grounds Latent Representation Search for Mitigating Backdoor Poisoning Attacks
Xuanli He, Qiongkai Xu, Jun Wang +2
Modern NLP models are often trained on public datasets drawn from diverse sources, rendering them vulnerable to data poisoning attacks. These attacks can manipulate the model's beh…
Backdoor Attack on Multilingual Machine Translation
Jun Wang, Qiongkai Xu, Xuanli He +2
While multilingual machine translation (MNMT) systems hold substantial promise, they also have security vulnerabilities. Our research highlights that MNMT systems can be susceptibl…
TuBA: Cross-Lingual Transferability of Backdoor Attacks in LLMs with Instruction Tuning
Xuanli He, Jun Wang, Qiongkai Xu +4
The implications of backdoor attacks on English-centric large language models (LLMs) have been widely examined - such attacks can be achieved by embedding malicious behaviors durin…
WARDEN: Multi-Directional Backdoor Watermarks for Embedding-as-a-Service Copyright Protection
Anudeex Shetty, Yue Teng, Ke He +1
Embedding as a Service (EaaS) has become a widely adopted solution, which offers feature extraction capabilities for addressing various downstream tasks in Natural Language Process…
Boot and Switch: Alternating Distillation for Zero-Shot Dense Retrieval
Fan Jiang, Qiongkai Xu, Tom Drummond +1
Neural 'dense' retrieval models are state of the art for many datasets, however these models often exhibit limited domain transfer ability. Existing approaches to adaptation are un…
Fingerprint Attack: Client De-Anonymization in Federated Learning
Qiongkai Xu, Trevor Cohn, Olga Ohrimenko
Federated Learning allows collaborative training without data sharing in settings where participants do not trust the central server and one another. Privacy can be further improve…