11 citations · 52 across the 19 of their papers we have counts for
19 papers
From Passive Metric to Active Signal: The Evolving Role of Uncertainty Quantification in Large Language Models
Jiaxin Zhang, Wendi Cui, Zhuohang Li +4
While Large Language Models (LLMs) show remarkable capabilities, their unreliability remains a critical barrier to deployment in high-stakes domains. This survey charts a functiona…
SCE: Scalable Consistency Ensembles Make Blackbox Large Language Model Generation More Reliable
Jiaxin Zhang, Zhuohang Li, Wendi Cui +3
Large language models (LLMs) have demonstrated remarkable performance, yet their diverse strengths and weaknesses prevent any single LLM from achieving dominance across all tasks.…
A Survey of Automatic Prompt Optimization with Instruction-focused Heuristic-based Search Algorithm
Wendi Cui, Zhuohang Li, Hao Sun +5
Recent advances in Large Language Models have led to remarkable achievements across a variety of Natural Language Processing tasks, making prompt engineering increasingly central t…
Exploring User-level Gradient Inversion with a Diffusion Prior
Zhuohang Li, Andrew Lowy, Jing Liu +4
We explore user-level gradient inversion as a new attack surface in distributed learning. We first investigate existing attacks on their ability to make inferences about private in…
Analyzing Inference Privacy Risks Through Gradients in Machine Learning
Zhuohang Li, Andrew Lowy, Jing Liu +4
In distributed learning settings, models are iteratively updated with shared gradients computed from potentially sensitive user data. While previous work has studied various privac…
Why Does Differential Privacy with Large Epsilon Defend Against Practical Membership Inference Attacks?
Andrew Lowy, Zhuohang Li, Jing Liu +3
For small privacy parameter , -differential privacy (DP) provides a strong worst-case guarantee that no membership inference attack (MIA) can succeed at determining whether a…
SEE: Strategic Exploration and Exploitation for Cohesive In-Context Prompt Optimization
Wendi Cui, Zhuohang Li, Hao Sun +5
Designing optimal prompts for Large Language Models (LLMs) is a complicated and resource-intensive task, often requiring substantial human expertise and effort. Existing approaches…
DCR-Consistency: Divide-Conquer-Reasoning for Consistency Evaluation and Improvement of Large Language Models
Wendi Cui, Jiaxin Zhang, Zhuohang Li +4
Evaluating the quality and variability of text generated by Large Language Models (LLMs) poses a significant, yet unresolved research challenge. Traditional evaluation methods, suc…
SAC3: Reliable Hallucination Detection in Black-Box Language Models via Semantic-aware Cross-check Consistency
Jiaxin Zhang, Zhuohang Li, Kamalika Das +2
Hallucination detection is a critical step toward understanding the trustworthiness of modern language models (LMs). To achieve this goal, we re-examine existing detection approach…
Interactive Multi-fidelity Learning for Cost-effective Adaptation of Language Model with Sparse Human Supervision
Jiaxin Zhang, Zhuohang Li, Kamalika Das +1
Large language models (LLMs) have demonstrated remarkable capabilities in various tasks. However, their suitability for domain-specific tasks, is limited due to their immense scale…
Split Learning for Distributed Collaborative Training of Deep Learning Models in Health Informatics
Zhuohang Li, Chao Yan, Xinmeng Zhang +4
Deep learning continues to rapidly evolve and is now demonstrating remarkable potential for numerous medical prediction tasks. However, realizing deep learning models that generali…
Reconstruction Distortion of Learned Image Compression with Imperceptible Perturbations
Yang Sui, Zhuohang Li, Ding Ding +4
Learned Image Compression (LIC) has recently become the trending technique for image transmission due to its notable performance. Despite its popularity, the robustness of LIC with…
RecUP-FL: Reconciling Utility and Privacy in Federated Learning via User-configurable Privacy Defense
Yue Cui, Syed Irfan Ali Meerza, Zhuohang Li +3
Federated learning (FL) provides a variety of privacy advantages by allowing clients to collaboratively train a model without sharing their private data. However, recent studies ha…
Speech Privacy Leakage from Shared Gradients in Distributed Learning
Zhuohang Li, Jiaxin Zhang, Jian Liu
Distributed machine learning paradigms, such as federated learning, have been recently adopted in many privacy-critical applications for speech analysis. However, such frameworks a…
RIBAC: Towards Robust and Imperceptible Backdoor Attack against Compact DNN
Huy Phan, Cong Shi, Yi Xie +7
Recently backdoor attack has become an emerging threat to the security of deep neural network (DNN) models. To date, most of the existing studies focus on backdoor attack against t…
Auditing Privacy Defenses in Federated Learning via Generative Gradient Leakage
Zhuohang Li, Jiaxin Zhang, Luyang Liu +1
Federated Learning (FL) framework brings privacy benefits to distributed learning systems by allowing multiple clients to participate in a learning task under the coordination of a…
Byzantine-robust Federated Learning through Spatial-temporal Analysis of Local Model Updates
Zhuohang Li, Luyang Liu, Jiaxin Zhang +1
Federated Learning (FL) enables multiple distributed clients (e.g., mobile devices) to collaboratively train a centralized model while keeping the training data locally on the clie…
Real-time, Universal, and Robust Adversarial Attacks Against Speaker Recognition Systems
Yi Xie, Cong Shi, Zhuohang Li +3
As the popularity of voice user interface (VUI) exploded in recent years, speaker recognition system has emerged as an important medium of identifying a speaker in many security-re…
Enabling Fast and Universal Audio Adversarial Attack Using Generative Model
Yi Xie, Zhuohang Li, Cong Shi +3
Recently, the vulnerability of DNN-based audio systems to adversarial attacks has obtained the increasing attention. However, the existing audio adversarial attacks allow the adver…