Search Results for author: Shuhan Yuan

Found 20 papers, 8 papers with code

Backdoor Attack against One-Class Sequential Anomaly Detection Models

no code implementations15 Feb 2024 He Cheng, Shuhan Yuan

In this paper, we explore compromising deep sequential anomaly detection models by proposing a novel backdoor attack strategy.

Anomaly Detection Backdoor Attack

Algorithmic Recourse for Anomaly Detection in Multivariate Time Series

no code implementations28 Sep 2023 Xiao Han, Lu Zhang, Yongkai Wu, Shuhan Yuan

Anomaly detection in multivariate time series has received extensive study due to the wide spectrum of applications.

Anomaly Detection Time Series +1

LogGPT: Log Anomaly Detection via GPT

1 code implementation25 Sep 2023 Xiao Han, Shuhan Yuan, Mohamed Trabelsi

However, there is a gap between language modeling and anomaly detection as the objective of training a sequential model via a language modeling loss is not directly related to anomaly detection.

Anomaly Detection Language Modelling

Robust Fraud Detection via Supervised Contrastive Learning

no code implementations19 Aug 2023 Vinay M. S., Shuhan Yuan, Xintao Wu

In many real-world scenarios, only a few labeled malicious and a large amount of normal sessions are available.

Contrastive Learning Data Augmentation +1

Achieving Counterfactual Fairness for Anomaly Detection

1 code implementation4 Mar 2023 Xiao Han, Lu Zhang, Yongkai Wu, Shuhan Yuan

Ensuring fairness in anomaly detection models has received much attention recently as many anomaly detection applications involve human beings.

Anomaly Detection counterfactual +1

On Root Cause Localization and Anomaly Mitigation through Causal Inference

1 code implementation8 Dec 2022 Xiao Han, Lu Zhang, Yongkai Wu, Shuhan Yuan

After that, we further propose an anomaly mitigation approach that aims to recommend mitigation actions on abnormal features to revert the abnormal outcomes such that the counterfactuals guided by the causal mechanism are normal.

Anomaly Detection Causal Inference

Generating Textual Adversaries with Minimal Perturbation

1 code implementation12 Nov 2022 Xingyi Zhao, Lu Zhang, Depeng Xu, Shuhan Yuan

Many word-level adversarial attack approaches for textual data have been proposed in recent studies.

Adversarial Attack

Fine-grained Anomaly Detection in Sequential Data via Counterfactual Explanations

no code implementations9 Oct 2022 He Cheng, Depeng Xu, Shuhan Yuan, Xintao Wu

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.

Anomaly Detection counterfactual +1

Trustworthy Anomaly Detection: A Survey

no code implementations15 Feb 2022 Shuhan Yuan, Xintao Wu

Anomaly detection has a wide range of real-world applications, such as bank fraud detection and cyber intrusion detection.

Anomaly Detection Fairness +2

Deep Learning for Insider Threat Detection: Review, Challenges and Opportunities

no code implementations25 May 2020 Shuhan Yuan, Xintao Wu

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.

BIG-bench Machine Learning Feature Engineering

On the Convergence of the Monte Carlo Exploring Starts Algorithm for Reinforcement Learning

no code implementations ICLR 2022 Che Wang, Shuhan Yuan, Kai Shao, Keith Ross

A simple and natural algorithm for reinforcement learning (RL) is Monte Carlo Exploring Starts (MCES), where the Q-function is estimated by averaging the Monte Carlo returns, and the policy is improved by choosing actions that maximize the current estimate of the Q-function.

reinforcement-learning Reinforcement Learning (RL)

Achieving Differential Privacy in Vertically Partitioned Multiparty Learning

no code implementations11 Nov 2019 Depeng Xu, Shuhan Yuan, Xintao Wu

Evaluation on real-world and synthetic datasets for linear and logistic regressions shows the effectiveness of our proposed method.

Privacy Preserving

SAFE: A Neural Survival Analysis Model for Fraud Early Detection

3 code implementations12 Sep 2018 Panpan Zheng, Shuhan Yuan, Xintao Wu

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.

Survival Analysis

FairGAN: Fairness-aware Generative Adversarial Networks

no code implementations28 May 2018 Depeng Xu, Shuhan Yuan, Lu Zhang, Xintao Wu

In this paper, we focus on fair data generation that ensures the generated data is discrimination free.

Fairness General Classification

One-Class Adversarial Nets for Fraud Detection

1 code implementation5 Mar 2018 Panpan Zheng, Shuhan Yuan, Xintao Wu, Jun Li, Aidong Lu

Currently, most of the fraud detection approaches require a training dataset that contains records of both benign and malicious users.

Fraud Detection One-Class Classification

Task-specific Word Identification from Short Texts Using a Convolutional Neural Network

no code implementations3 Jun 2017 Shuhan Yuan, Xintao Wu, Yang Xiang

The other case study on fake review detection shows that our approach can identify the fake-review words/phrases.

Wikipedia Vandal Early Detection: from User Behavior to User Embedding

1 code implementation3 Jun 2017 Shuhan Yuan, Panpan Zheng, Xintao Wu, Yang Xiang

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.

Spectrum-based deep neural networks for fraud detection

no code implementations3 Jun 2017 Shuhan Yuan, Xintao Wu, Jun Li, Aidong Lu

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.

Fraud Detection

Cannot find the paper you are looking for? You can Submit a new open access paper.