
Evading RealTime Person Detectors by Adversarial Tshirt
It is known that deep neural networks (DNNs) could be vulnerable to adve...
read it

One Explanation Does Not Fit All: A Toolkit and Taxonomy of AI Explainability Techniques
As artificial intelligence and machine learning algorithms make further ...
read it

An InformationTheoretic Perspective on the Relationship Between Fairness and Accuracy
Our goal is to understand the socalled tradeoff between fairness and a...
read it

Controllability, Multiplexing, and Transfer Learning in Networks using Evolutionary Learning
Networks are fundamental building blocks for representing data, and comp...
read it

Towards QueryEfficient BlackBox Adversary with ZerothOrder Natural Gradient Descent
Despite the great achievements of the modern deep neural networks (DNNs)...
read it

SignOPT: A QueryEfficient Hardlabel Adversarial Attack
We study the most practical problem setup for evaluating adversarial rob...
read it

Towards Verifying Robustness of Neural Networks Against Semantic Perturbations
Verifying robustness of neural networks given a specified threat model i...
read it

Structured Adversarial Attack: Towards General Implementation and Better Interpretability
When generating adversarial examples to attack deep neural networks (DNN...
read it

Toward A Neuroinspired Creative Decoder
Creativity, a process that generates novel and valuable ideas, involves ...
read it

When Causal Intervention Meets Image Masking and Adversarial Perturbation for Deep Neural Networks
Discovering and exploiting the causality in deep neural networks (DNNs) ...
read it

Is Robustness the Cost of Accuracy?  A Comprehensive Study on the Robustness of 18 Deep Image Classification Models
The prediction accuracy has been the longlasting and sole standard for ...
read it

CNNCert: An Efficient Framework for Certifying Robustness of Convolutional Neural Networks
Verifying robustness of neural network classifiers has attracted great i...
read it

Model Agnostic Contrastive Explanations for Structured Data
Recently, a method [7] was proposed to generate contrastive explanations...
read it

PROVEN: Certifying Robustness of Neural Networks with a Probabilistic Approach
With deep neural networks providing stateoftheart machine learning mo...
read it

Generating Contrastive Explanations with Monotonic Attribute Functions
Explaining decisions of deep neural networks is a hot research topic wit...
read it

AdvMS: A Multisource Multicost Defense Against Adversarial Attacks
Designing effective defense against adversarial attacks is a crucial top...
read it

QueryEfficient Hardlabel Blackbox Attack:An Optimizationbased Approach
We study the problem of attacking a machine learning model in the hardl...
read it

Efficient Neural Network Robustness Certification with General Activation Functions
Finding minimum distortion of adversarial examples and thus certifying r...
read it

AutoZOOM: Autoencoderbased Zeroth Order Optimization Method for Attacking Blackbox Neural Networks
Recent studies have shown that adversarial examples in stateoftheart ...
read it

Is Ordered Weighted ℓ_1 Regularized Regression Robust to Adversarial Perturbation? A Case Study on OSCAR
Many stateoftheart machine learning models such as deep neural networ...
read it

On The Utility of Conditional Generation Based Mutual Information for Characterizing Adversarial Subspaces
Recent studies have found that deep learning systems are vulnerable to a...
read it

On the Design of Blackbox Adversarial Examples by Leveraging Gradientfree Optimization and Operator Splitting Method
Robust machine learning is currently one of the most prominent topics wh...
read it

Beyond Adversarial Training: MinMax Optimization in Adversarial Attack and Defense
The worstcase training principle that minimizes the maximal adversarial...
read it

Fast Incremental von Neumann Graph Entropy Computation: Theory, Algorithm, and Applications
The von Neumann graph entropy (VNGE) facilitates the measure of informat...
read it

Topology Attack and Defense for Graph Neural Networks: An Optimization Perspective
Graph neural networks (GNNs) which apply the deep neural networks to gra...
read it

Protecting Neural Networks with Hierarchical Random Switching: Towards Better RobustnessAccuracy Tradeoff for Stochastic Defenses
Despite achieving remarkable success in various domains, recent studies ...
read it

Reinforcement Learning based Interconnection Routing for Adaptive Traffic Optimization
Applying Machine Learning (ML) techniques to design and optimize compute...
read it

CAT: Customized Adversarial Training for Improved Robustness
Adversarial training has become one of the most effective methods for im...
read it

Block Switching: A Stochastic Approach for Deep Learning Security
Recent study of adversarial attacks has revealed the vulnerability of mo...
read it

Characterizing Audio Adversarial Examples Using Temporal Dependency
Recent studies have highlighted adversarial examples as a ubiquitous thr...
read it

ZerothOrder Online Alternating Direction Method of Multipliers: Convergence Analysis and Applications
In this paper, we design and analyze a new zerothorder online algorithm...
read it

Revisiting Spectral Graph Clustering with Generative Community Models
The methodology of community detection can be divided into two principle...
read it

EAD: ElasticNet Attacks to Deep Neural Networks via Adversarial Examples
Recent studies have highlighted the vulnerability of deep neural network...
read it

ZOO: Zeroth Order Optimization based Blackbox Attacks to Deep Neural Networks without Training Substitute Models
Deep neural networks (DNNs) are one of the most prominent technologies o...
read it

Multilayer Spectral Graph Clustering via Convex Layer Aggregation: Theory and Algorithms
Multilayer graphs are commonly used for representing different relations...
read it

Can GAN Learn Topological Features of a Graph?
This paper is firstline research expanding GANs into graph topology ana...
read it

BiasVariance Tradeoff of Graph Laplacian Regularizer
This paper presents a biasvariance tradeoff of graph Laplacian regulari...
read it

Accelerated Distributed Dual Averaging over Evolving Networks of Growing Connectivity
We consider the problem of accelerating distributed optimization in mult...
read it

Multilayer Spectral Graph Clustering via Convex Layer Aggregation
Multilayer graphs are commonly used for representing different relations...
read it

AMOS: An Automated Model Order Selection Algorithm for Spectral Graph Clustering
One of the longstanding problems in spectral graph clustering (SGC) is t...
read it

ShowandFool: Crafting Adversarial Examples for Neural Image Captioning
Modern neural image captioning systems typically adopt the encoderdecod...
read it

Phase Transitions and a Model Order Selection Criterion for Spectral Graph Clustering
One of the longstanding open problems in spectral graph clustering (SGC)...
read it

Multicentrality Graph Spectral Decompositions and their Application to Cyber Intrusion Detection
Many modern datasets can be represented as graphs and hence spectral dec...
read it

Incremental Method for Spectral Clustering of Increasing Orders
The smallest eigenvalues and the associated eigenvectors (i.e., eigenpai...
read it

When Crowdsourcing Meets Mobile Sensing: A Social Network Perspective
Mobile sensing is an emerging technology that utilizes agentparticipato...
read it

Phase Transitions in Spectral Community Detection of Large Noisy Networks
In this paper, we study the sensitivity of the spectral clustering based...
read it

Attacking the Madry Defense Model with L_1based Adversarial Examples
The Madry Lab recently hosted a competition designed to test the robustn...
read it

Seq2Sick: Evaluating the Robustness of SequencetoSequence Models with Adversarial Examples
Crafting adversarial examples has become an important technique to evalu...
read it

Explanations based on the Missing: Towards Contrastive Explanations with Pertinent Negatives
In this paper we propose a novel method that provides contrastive explan...
read it

Evaluating the Robustness of Neural Networks: An Extreme Value Theory Approach
The robustness of neural networks to adversarial examples has received g...
read it
PinYu Chen
verfied profile
Research Staff Member, Trusted AI Group
Chief Scientist, RPIIBM AI Research Collaboration
PI, MITIBM Watson AI Lab
IBM Thomas J. Watson Research Center