Search Results for author: Xinyang Zhang

Found 22 papers, 11 papers with code

A Tale of Evil Twins: Adversarial Inputs versus Poisoned Models

1 code implementation5 Nov 2019 Ren Pang, Hua Shen, Xinyang Zhang, Shouling Ji, Yevgeniy Vorobeychik, Xiapu Luo, Alex Liu, Ting Wang

Specifically, (i) we develop a new attack model that jointly optimizes adversarial inputs and poisoned models; (ii) with both analytical and empirical evidence, we reveal that there exist intriguing "mutual reinforcement" effects between the two attack vectors -- leveraging one vector significantly amplifies the effectiveness of the other; (iii) we demonstrate that such effects enable a large design spectrum for the adversary to enhance the existing attacks that exploit both vectors (e. g., backdoor attacks), such as maximizing the attack evasiveness with respect to various detection methods; (iv) finally, we discuss potential countermeasures against such optimized attacks and their technical challenges, pointing to several promising research directions.

AdvMind: Inferring Adversary Intent of Black-Box Attacks

1 code implementation16 Jun 2020 Ren Pang, Xinyang Zhang, Shouling Ji, Xiapu Luo, Ting Wang

Deep neural networks (DNNs) are inherently susceptible to adversarial attacks even under black-box settings, in which the adversary only has query access to the target models.

Motif-based Convolutional Neural Network on Graphs

1 code implementation15 Nov 2017 Aravind Sankar, Xinyang Zhang, Kevin Chen-Chuan Chang

This paper introduces a generalization of Convolutional Neural Networks (CNNs) to graphs with irregular linkage structures, especially heterogeneous graphs with typed nodes and schemas.

General Classification Node Classification +1

Differentially Private Releasing via Deep Generative Model (Technical Report)

2 code implementations5 Jan 2018 Xinyang Zhang, Shouling Ji, Ting Wang

Privacy-preserving releasing of complex data (e. g., image, text, audio) represents a long-standing challenge for the data mining research community.

Privacy Preserving

Inf-VAE: A Variational Autoencoder Framework to Integrate Homophily and Influence in Diffusion Prediction

2 code implementations1 Jan 2020 Aravind Sankar, Xinyang Zhang, Adit Krishnan, Jiawei Han

Recent years have witnessed tremendous interest in understanding and predicting information spread on social media platforms such as Twitter, Facebook, etc.

TwHIN-BERT: A Socially-Enriched Pre-trained Language Model for Multilingual Tweet Representations at Twitter

1 code implementation15 Sep 2022 Xinyang Zhang, Yury Malkov, Omar Florez, Serim Park, Brian McWilliams, Jiawei Han, Ahmed El-Kishky

Most existing PLMs are not tailored to the noisy user-generated text on social media, and the pre-training does not factor in the valuable social engagement logs available in a social network.

Language Modelling

Detecting Multi-Sensor Fusion Errors in Advanced Driver-Assistance Systems

3 code implementations14 Sep 2021 Ziyuan Zhong, Zhisheng Hu, Shengjian Guo, Xinyang Zhang, Zhenyu Zhong, Baishakhi Ray

We define the failures (e. g., car crashes) caused by the faulty MSF as fusion errors and develop a novel evolutionary-based domain-specific search framework, FusED, for the efficient detection of fusion errors.

Autonomous Driving Sensor Fusion

OA-Mine: Open-World Attribute Mining for E-Commerce Products with Weak Supervision

1 code implementation29 Apr 2022 Xinyang Zhang, Chenwei Zhang, Xian Li, Xin Luna Dong, Jingbo Shang, Christos Faloutsos, Jiawei Han

Most prior works on this matter mine new values for a set of known attributes but cannot handle new attributes that arose from constantly changing data.

Attribute Language Modelling

Trojaning Language Models for Fun and Profit

1 code implementation1 Aug 2020 Xinyang Zhang, Zheng Zhang, Shouling Ji, Ting Wang

Recent years have witnessed the emergence of a new paradigm of building natural language processing (NLP) systems: general-purpose, pre-trained language models (LMs) are composed with simple downstream models and fine-tuned for a variety of NLP tasks.

Question Answering Specificity +1

META: Metadata-Empowered Weak Supervision for Text Classification

1 code implementation EMNLP 2020 Dheeraj Mekala, Xinyang Zhang, Jingbo Shang

Based on seed words, we rank and filter motif instances to distill highly label-indicative ones as {``}seed motifs{''}, which provide additional weak supervision.

General Classification text-classification +2

Navigating Alignment for Non-identical Client Class Sets: A Label Name-Anchored Federated Learning Framework

1 code implementation1 Jan 2023 Jiayun Zhang, Xiyuan Zhang, Xinyang Zhang, Dezhi Hong, Rajesh K. Gupta, Jingbo Shang

Traditional federated classification methods, even those designed for non-IID clients, assume that each client annotates its local data with respect to the same universal class set.

Federated Learning

Modular Learning Component Attacks: Today's Reality, Tomorrow's Challenge

no code implementations25 Aug 2017 Xinyang Zhang, Yujie Ji, Ting Wang

Many of today's machine learning (ML) systems are not built from scratch, but are compositions of an array of {\em modular learning components} (MLCs).

EagleEye: Attack-Agnostic Defense against Adversarial Inputs (Technical Report)

no code implementations1 Aug 2018 Yujie Ji, Xinyang Zhang, Ting Wang

Deep neural networks (DNNs) are inherently vulnerable to adversarial inputs: such maliciously crafted samples trigger DNNs to misbehave, leading to detrimental consequences for DNN-powered systems.

Interpretable Deep Learning under Fire

no code implementations3 Dec 2018 Xinyang Zhang, Ningfei Wang, Hua Shen, Shouling Ji, Xiapu Luo, Ting Wang

The improved interpretability is believed to offer a sense of security by involving human in the decision-making process.

Decision Making

Provable Defenses against Spatially Transformed Adversarial Inputs: Impossibility and Possibility Results

no code implementations ICLR 2019 Xinyang Zhang, Yifan Huang, Chanh Nguyen, Shouling Ji, Ting Wang

On the possibility side, we show that it is still feasible to construct adversarial training methods to significantly improve the resilience of networks against adversarial inputs over empirical datasets.

Model-Reuse Attacks on Deep Learning Systems

no code implementations2 Dec 2018 Yujie Ji, Xinyang Zhang, Shouling Ji, Xiapu Luo, Ting Wang

By empirically studying four deep learning systems (including both individual and ensemble systems) used in skin cancer screening, speech recognition, face verification, and autonomous steering, we show that such attacks are (i) effective - the host systems misbehave on the targeted inputs as desired by the adversary with high probability, (ii) evasive - the malicious models function indistinguishably from their benign counterparts on non-targeted inputs, (iii) elastic - the malicious models remain effective regardless of various system design choices and tuning strategies, and (iv) easy - the adversary needs little prior knowledge about the data used for system tuning or inference.

Cryptography and Security

Composite Adversarial Training for Multiple Adversarial Perturbations and Beyond

no code implementations1 Jan 2021 Xinyang Zhang, Zheng Zhang, Ting Wang

One intriguing property of deep neural networks (DNNs) is their vulnerability to adversarial perturbations.

i-Algebra: Towards Interactive Interpretability of Deep Neural Networks

no code implementations22 Jan 2021 Xinyang Zhang, Ren Pang, Shouling Ji, Fenglong Ma, Ting Wang

Providing explanations for deep neural networks (DNNs) is essential for their use in domains wherein the interpretability of decisions is a critical prerequisite.

Minimally-Supervised Structure-Rich Text Categorization via Learning on Text-Rich Networks

no code implementations23 Feb 2021 Xinyang Zhang, Chenwei Zhang, Luna Xin Dong, Jingbo Shang, Jiawei Han

Specifically, we jointly train two modules with different inductive biases -- a text analysis module for text understanding and a network learning module for class-discriminative, scalable network learning.

Product Categorization Text Categorization

Patton: Language Model Pretraining on Text-Rich Networks

no code implementations20 May 2023 Bowen Jin, Wentao Zhang, Yu Zhang, Yu Meng, Xinyang Zhang, Qi Zhu, Jiawei Han

A real-world text corpus sometimes comprises not only text documents but also semantic links between them (e. g., academic papers in a bibliographic network are linked by citations and co-authorships).

Language Modelling Masked Language Modeling +1

Text2Layer: Layered Image Generation using Latent Diffusion Model

no code implementations19 Jul 2023 Xinyang Zhang, Wentian Zhao, Xin Lu, Jeff Chien

To achieve layered image generation, we train an autoencoder that is able to reconstruct layered images and train diffusion models on the latent representation.

Image Generation Image Segmentation +1

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