paper-with-me

Papers

SkeletonVis: Interactive Visualization for Understanding Adversarial Attacks on Human Action Recognition Models

2021-01-26 · Haekyu Park, Zijie J. Wang, Nilaksh Das, Anindya S. Paul, Pruthvi Perumalla, Zhiyan Zhou, Duen Horng Chau

Skeleton-based human action recognition technologies are increasingly used in video based applications, such as home robotics, healthcare on aging population, and surveillance. However, such models are vulnerable to adversarial attacks, raising serious concerns for their use in safety-critical applications. To develop an effective defense against attacks, it is essential to understand how such attacks mislead the pose detection models into making incorrect predictions. We present SkeletonVis, the first interactive system that visualizes how the attacks work on the models to enhance human understanding of attacks.

📄 PDF Abstract BibTeX arXiv:2101.10586

Code (0)

등록된 구현이 없습니다.

Tasks

Action RecognitionTemporal Action Localization

Similar Papers 제목 키워드 기반

Panda or not Panda? Understanding Adversarial Attacks with Interactive Visualization

2023-11-22 · Yuzhe You, Jarvis Tse, Jian Zhao

Adversarial machine learning (AML) studies attacks that can fool machine learning algorithms into generating incorrect outcomes as well as the defenses against worst-case attacks to strengthen model robustness. Specifica…

image-classificationImage Classification

TA3: Testing Against Adversarial Attacks on Machine Learning Models

2024-10-06 · Yuanzhe Jin, Min Chen

Adversarial attacks are major threats to the deployment of machine learning (ML) models in many applications. Testing ML models against such attacks is becoming an essential step for evaluating and improving ML models. I…

DetectorDetective: Investigating the Effects of Adversarial Examples on Object Detectors

2022-01-01 · CVPR 2022 1 · Sivapriya Vellaichamy, Matthew Hull, Zijie J. Wang, Nilaksh Das 외

With deep learning based systems performing exceedingly well in many vision-related tasks, a major concern with their widespread deployment especially in safety-critical applications is their susceptibility to advers…

Objectobject-detectionObject DetectionRegion Proposal

Bluff: Interactively Deciphering Adversarial Attacks on Deep Neural Networks

2020-09-05 · Nilaksh Das, Haekyu Park, Zijie J. Wang, Fred Hohman 외

Deep neural networks (DNNs) are now commonly used in many domains. However, they are vulnerable to adversarial attacks: carefully crafted perturbations on data inputs that can fool a model into making incorrect predictio…

NeuralDivergence: Exploring and Understanding Neural Networks by Comparing Activation Distributions

2019-06-02 · Haekyu Park, Fred Hohman, Duen Horng Chau

As deep neural networks are increasingly used in solving high-stake problems, there is a pressing need to understand their internal decision mechanisms. Visualization has helped address this problem by assisting with int…