Search Results for author:
Found 27 papers, 5 papers with code
RSL-SQL: Robust Schema Linking in Text-to-SQL Generation
Text-to-SQL generation aims to translate natural language questions into SQL statements.
MC-CoT: A Modular Collaborative CoT Framework for Zero-shot Medical-VQA with LLM and MLLM Integration
In recent advancements, multimodal large language models (MLLMs) have been fine-tuned on specific medical image datasets to address medical visual question answering (Med-VQA) tasks.
Theoretical Analysis of Privacy Leakage in Trustworthy Federated Learning: A Perspective from Linear Algebra and Optimization Theory
From the optimization theory perspective, we establish an upper bound on the privacy leakage in terms of the batch size, the distortion extent, and several other factors.
A Unified Learn-to-Distort-Data Framework for Privacy-Utility Trade-off in Trustworthy Federated Learning
In this paper, we first give an introduction to the theoretical basis of the privacy-utility equilibrium in federated learning based on Bayesian privacy definitions and total variation distance privacy definitions.
VulDetectBench: Evaluating the Deep Capability of Vulnerability Detection with Large Language Models
However, sound comprehensive research on detecting program vulnerabilities, a more specific task related to code, and evaluating the performance of LLMs in this more specialized scenario is still lacking.
No Free Lunch Theorem for Privacy-Preserving LLM Inference
Therefore, it is essential to evaluate the balance between the risk of privacy leakage and loss of utility when conducting effective protection mechanisms.
Beyond ESM2: Graph-Enhanced Protein Sequence Modeling with Efficient Clustering
Proteins are essential to life's processes, underpinning evolution and diversity.
Deciphering the Interplay between Local Differential Privacy, Average Bayesian Privacy, and Maximum Bayesian Privacy
The swift evolution of machine learning has led to emergence of various definitions of privacy due to the threats it poses to privacy, including the concept of local differential privacy (LDP).
Reinforcement Learning as a Catalyst for Robust and Fair Federated Learning: Deciphering the Dynamics of Client Contributions
Recent advancements in federated learning (FL) have produced models that retain user privacy by training across multiple decentralized devices or systems holding local data samples.
CauESC: A Causal Aware Model for Emotional Support Conversation
Emotional Support Conversation aims at reducing the seeker's emotional distress through supportive response.
K-ESConv: Knowledge Injection for Emotional Support Dialogue Systems via Prompt Learning
Automatic psychological counseling requires mass of professional knowledge that can be found in online counseling forums.
Toward the Tradeoffs between Privacy, Fairness and Utility in Federated Learning
Researchers have struggled to design fair FL systems that ensure fairness of results.
Grounding Foundation Models through Federated Transfer Learning: A General Framework
Motivated by the strong growth in FTL-FM research and the potential impact of FTL-FM on industrial applications, we propose an FTL-FM framework that formulates problems of grounding FMs in the federated learning setting, construct a detailed taxonomy based on the FTL-FM framework to categorize state-of-the-art FTL-FM works, and comprehensively overview FTL-FM works based on the proposed taxonomy.
Privacy in Large Language Models: Attacks, Defenses and Future Directions
The advancement of large language models (LLMs) has significantly enhanced the ability to effectively tackle various downstream NLP tasks and unify these tasks into generative pipelines.
A Meta-learning Framework for Tuning Parameters of Protection Mechanisms in Trustworthy Federated Learning
Motivated by this requirement, we propose a framework that (1) formulates TFL as a problem of finding a protection mechanism to optimize the tradeoff between privacy leakage, utility loss, and efficiency reduction and (2) formally defines bounded measurements of the three factors.
Theoretically Principled Federated Learning for Balancing Privacy and Utility
We propose a general learning framework for the protection mechanisms that protects privacy via distorting model parameters, which facilitates the trade-off between privacy and utility.
Towards Achieving Near-optimal Utility for Privacy-Preserving Federated Learning via Data Generation and Parameter Distortion
The nature of the widely-adopted protection mechanisms including \textit{Randomization Mechanism} and \textit{Compression Mechanism} is to protect privacy via distorting model parameter.
A Game-theoretic Framework for Privacy-preserving Federated Learning
To address this, we propose the first game-theoretic framework that considers both FL defenders and attackers in terms of their respective payoffs, which include computational costs, FL model utilities, and privacy leakage risks.
Probably Approximately Correct Federated Learning
However, existing multi-objective optimization frameworks are very time-consuming, and do not guarantee the existence of the Pareto frontier, this motivates us to seek a solution to transform the multi-objective problem into a single-objective problem because it is more efficient and easier to be solved.
A Framework for Evaluating Privacy-Utility Trade-off in Vertical Federated Learning
We then use this framework as a guide to comprehensively evaluate a broad range of protection mechanisms against most of the state-of-the-art privacy attacks for three widely deployed VFL algorithms.
Trading Off Privacy, Utility and Efficiency in Federated Learning
In addition, it is a mandate for a federated learning system to achieve high \textit{efficiency} in order to enable large-scale model training and deployment.
No Free Lunch Theorem for Security and Utility in Federated Learning
In a federated learning scenario where multiple parties jointly learn a model from their respective data, there exist two conflicting goals for the choice of appropriate algorithms.
Variance-Dependent Best Arm Identification
Given a set of $n$ arms indexed from $1$ to $n$, each arm $i$ is associated with an unknown reward distribution supported on $[0, 1]$ with mean $\theta_i$ and variance $\sigma_i^2$.
Achieving Near Instance-Optimality and Minimax-Optimality in Stochastic and Adversarial Linear Bandits Simultaneously
In this work, we develop linear bandit algorithms that automatically adapt to different environments.
Adaptive Double-Exploration Tradeoff for Outlier Detection
We study a variant of the thresholding bandit problem (TBP) in the context of outlier detection, where the objective is to identify the outliers whose rewards are above a threshold.
Contextual Combinatorial Conservative Bandits
The problem of multi-armed bandits (MAB) asks to make sequential decisions while balancing between exploitation and exploration, and have been successfully applied to a wide range of practical scenarios.
Automatic Ensemble Learning for Online Influence Maximization
Experimental evaluation illustrates the effectiveness of the automatically adjusted hybridization of exploration algorithm with exploitation algorithm.
