Search Results for author:
Found 56 papers, 12 papers with code
Privacy Preserving Prompt Engineering: A Survey
As a result, the sizes of these models have notably expanded in recent years, persuading researchers to adopt the term large language models (LLMs) to characterize the larger-sized PLMs.
Robust Influence-based Training Methods for Noisy Brain MRI
In this work, we study a difficult but realistic setting of training a deep learning model on noisy MR images to classify brain tumors.
DP-TabICL: In-Context Learning with Differentially Private Tabular Data
In-context learning (ICL) enables large language models (LLMs) to adapt to new tasks by conditioning on demonstrations of question-answer pairs and it has been shown to have comparable performance to costly model retraining and fine-tuning.
On Large Visual Language Models for Medical Imaging Analysis: An Empirical Study
Visual language models (VLMs), such as LLaVA, Flamingo, or CLIP, have demonstrated impressive performance on various visio-linguistic tasks.
In-Context Learning Demonstration Selection via Influence Analysis
Despite its multiple benefits, ICL generalization performance is sensitive to the selected demonstrations.
Dynamic Environment Responsive Online Meta-Learning with Fairness Awareness
Theoretical analysis yields sub-linear upper bounds for both loss regret and the cumulative violation of fairness constraints.
Supervised Algorithmic Fairness in Distribution Shifts: A Survey
Supervised fairness-aware machine learning under distribution shifts is an emerging field that addresses the challenge of maintaining equitable and unbiased predictions when faced with changes in data distributions from source to target domains.
Robustly Improving Bandit Algorithms with Confounded and Selection Biased Offline Data: A Causal Approach
A major obstacle in this setting is the existence of compound biases from the observational data.
Fairness-Aware Domain Generalization under Covariate and Dependence Shifts
Achieving the generalization of an invariant classifier from source domains to shifted target domains while simultaneously considering model fairness is a substantial and complex challenge in machine learning.
Detecting and Correcting Hate Speech in Multimodal Memes with Large Visual Language Model
In this work, we study the ability of VLMs on hateful meme detection and hateful meme correction tasks with zero-shot prompting.
From Identifiable Causal Representations to Controllable Counterfactual Generation: A Survey on Causal Generative Modeling
Deep generative models have shown tremendous success in data density estimation and data generation from finite samples.
HINT: Healthy Influential-Noise based Training to Defend against Data Poisoning Attacks
While numerous defense methods have been proposed to prohibit potential poisoning attacks from untrusted data sources, most research works only defend against specific attacks, which leaves many avenues for an adversary to exploit.
Evaluating the Impact of Local Differential Privacy on Utility Loss via Influence Functions
How to properly set the privacy parameter in differential privacy (DP) has been an open question in DP research since it was first proposed in 2006.
Local Differential Privacy in Graph Neural Networks: a Reconstruction Approach
We focus on a decentralized notion of Differential Privacy, namely Local Differential Privacy, and apply randomization mechanisms to perturb both feature and label data at the node level before the data is collected by a central server for model training.
On Prediction Feature Assignment in the Heckman Selection Model
This paper focuses on one classic instance of MNAR sample selection bias where a subset of samples have non-randomly missing outcomes.
Robust Fraud Detection via Supervised Contrastive Learning
In many real-world scenarios, only a few labeled malicious and a large amount of normal sessions are available.
Learning Causally Disentangled Representations via the Principle of Independent Causal Mechanisms
We propose ICM-VAE, a framework for learning causally disentangled representations supervised by causally related observed labels.
Towards Fair Disentangled Online Learning for Changing Environments
To this end, in this paper, we propose a novel algorithm under the assumption that data collected at each time can be disentangled with two representations, an environment-invariant semantic factor and an environment-specific variation factor.
A Robust Classifier Under Missing-Not-At-Random Sample Selection Bias
In this paper, we propose BiasCorr, an algorithm that improves on Greene's method by modifying the original training set in order for a classifier to learn under MNAR sample selection bias.
Heterogeneous Randomized Response for Differential Privacy in Graph Neural Networks
Graph neural networks (GNNs) are susceptible to privacy inference attacks (PIAs), given their ability to learn joint representation from features and edges among nodes in graph data.
Fine-grained Anomaly Detection in Sequential Data via Counterfactual Explanations
Given a sequence that is detected as anomalous, we can consider anomalous entry detection as an interpretable machine learning task because identifying anomalous entries in the sequence is to provide an interpretation to the detection result.
Adaptive Fairness-Aware Online Meta-Learning for Changing Environments
Furthermore, to determine a good model parameter at each round, we propose a novel adaptive fairness-aware online meta-learning algorithm, namely FairSAOML, which is able to adapt to changing environments in both bias control and model precision.
Trustworthy Anomaly Detection: A Survey
Anomaly detection has a wide range of real-world applications, such as bank fraud detection and cyber intrusion detection.
How to Backdoor HyperNetwork in Personalized Federated Learning?
This paper explores previously unknown backdoor risks in HyperNet-based personalized federated learning (HyperNetFL) through poisoning attacks.
The Fairness Field Guide: Perspectives from Social and Formal Sciences
Over the past several years, a slew of different methods to measure the fairness of a machine learning model have been proposed.
Poisoning Attacks on Fair Machine Learning
Our framework enables attackers to flexibly adjust the attack's focus on prediction accuracy or fairness and accurately quantify the impact of each candidate point to both accuracy loss and fairness violation, thus producing effective poisoning samples.
Achieving Counterfactual Fairness for Causal Bandit
In online recommendation, customers arrive in a sequential and stochastic manner from an underlying distribution and the online decision model recommends a chosen item for each arriving individual based on some strategy.
MathBERT: A Pre-trained Language Model for General NLP Tasks in Mathematics Education
Due to the nature of mathematical texts, which often use domain specific vocabulary along with equations and math symbols, we posit that the development of a new BERT model for mathematics would be useful for many mathematical downstream tasks.
Robust Fairness-aware Learning Under Sample Selection Bias
However, the assumption is often violated in real world due to the sample selection bias between the training and test data.
InfoFair: Information-Theoretic Intersectional Fairness
The vast majority of the existing works on group fairness, with a few exceptions, primarily focus on debiasing with respect to a single sensitive attribute, despite the fact that the co-existence of multiple sensitive attributes (e. g., gender, race, marital status, etc.)
Classifying Math KCs via Task-Adaptive Pre-Trained BERT
Educational content labeled with proper knowledge components (KCs) are particularly useful to teachers or content organizers.
Fair Multiple Decision Making Through Soft Interventions
Previous research in fair classification mostly focuses on a single decision model.
Achieving User-Side Fairness in Contextual Bandits
Personalized recommendation based on multi-arm bandit (MAB) algorithms has shown to lead to high utility and efficiency as it can dynamically adapt the recommendation strategy based on feedback.
Fairness-aware Agnostic Federated Learning
In this paper, we develop a fairness-aware agnostic federated learning framework (AgnosticFair) to deal with the challenge of unknown testing distribution.
Deep Learning for Insider Threat Detection: Review, Challenges and Opportunities
We then discuss such challenges and suggest future research directions that have the potential to address challenges and further boost the performance of deep learning for insider threat detection.
Removing Disparate Impact of Differentially Private Stochastic Gradient Descent on Model Accuracy
In this work, we analyze the inequality in utility loss by differential privacy and propose a modified differentially private stochastic gradient descent (DPSGD), called DPSGD-F, to remove the potential disparate impact of differential privacy on the protected group.
Identifying Hidden Buyers in Darknet Markets via Dirichlet Hawkes Process
The key challenge is that the buyers are anonymized in darknet markets.
Achieving Differential Privacy in Vertically Partitioned Multiparty Learning
Evaluation on real-world and synthetic datasets for linear and logistic regressions shows the effectiveness of our proposed method.
Fairness through Equality of Effort
We develop algorithms for determining whether an individual or a group of individuals is discriminated in terms of equality of effort.
PC-Fairness: A Unified Framework for Measuring Causality-based Fairness
A recent trend of fair machine learning is to define fairness as causality-based notions which concern the causal connection between protected attributes and decisions.
Heterogeneous Gaussian Mechanism: Preserving Differential Privacy in Deep Learning with Provable Robustness
In this paper, we propose a novel Heterogeneous Gaussian Mechanism (HGM) to preserve differential privacy in deep neural networks, with provable robustness against adversarial examples.
Fairness-aware Classification: Criterion, Convexity, and Bounds
In this paper, we propose a general framework for learning fair classifiers which addresses previous limitations.
SAFE: A Neural Survival Analysis Model for Fraud Early Detection
However, there is usually a gap between the time that a user commits a fraudulent action and the time that the user is suspended by the platform.
FairGAN: Fairness-aware Generative Adversarial Networks
In this paper, we focus on fair data generation that ensures the generated data is discrimination free.
One-Class Adversarial Nets for Fraud Detection
Currently, most of the fraud detection approaches require a training dataset that contains records of both benign and malicious users.
On Discrimination Discovery and Removal in Ranked Data using Causal Graph
Existing methods in fairness-aware ranking are mainly based on statistical parity that cannot measure the true discriminatory effect since discrimination is causal.
Adaptive Laplace Mechanism: Differential Privacy Preservation in Deep Learning
In this paper, we focus on developing a novel mechanism to preserve differential privacy in deep neural networks, such that: (1) The privacy budget consumption is totally independent of the number of training steps; (2) It has the ability to adaptively inject noise into features based on the contribution of each to the output; and (3) It could be applied in a variety of different deep neural networks.
Preserving Differential Privacy in Convolutional Deep Belief Networks
However, only a few scientific studies on preserving privacy in deep learning have been conducted.
Wikipedia Vandal Early Detection: from User Behavior to User Embedding
In particular, we develop a multi-source long-short term memory network (M-LSTM) to model user behaviors by using a variety of user edit aspects as inputs, including the history of edit reversion information, edit page titles and categories.
Task-specific Word Identification from Short Texts Using a Convolutional Neural Network
The other case study on fake review detection shows that our approach can identify the fake-review words/phrases.
Spectrum-based deep neural networks for fraud detection
Due to the small dimension of spectral coordinates (compared with the dimension of the adjacency matrix derived from a graph), training deep neural networks becomes feasible.
Achieving non-discrimination in prediction
Based on the results, we develop a two-phase framework for constructing a discrimination-free classifier with a theoretical guarantee.
On Spectral Analysis of Directed Signed Graphs
It has been shown that the adjacency eigenspace of a network contains key information of its underlying structure.
A causal framework for discovering and removing direct and indirect discrimination
In this paper, we investigate the problem of discovering both direct and indirect discrimination from the historical data, and removing the discriminatory effects before the data is used for predictive analysis (e. g., building classifiers).
Achieving non-discrimination in data release
Discrimination discovery and prevention/removal are increasingly important tasks in data mining.
