paper-with-me

Papers

Explaining Vulnerabilities to Adversarial Machine Learning through Visual Analytics

2019-07-17 · Yuxin Ma, Tiankai Xie, Jundong Li, Ross Maciejewski

Machine learning models are currently being deployed in a variety of real-world applications where model predictions are used to make decisions about healthcare, bank loans, and numerous other critical tasks. As the deployment of artificial intelligence technologies becomes ubiquitous, it is unsurprising that adversaries have begun developing methods to manipulate machine learning models to their advantage. While the visual analytics community has developed methods for opening the black box of machine learning models, little work has focused on helping the user understand their model vulnerabilities in the context of adversarial attacks. In this paper, we present a visual analytics framework for explaining and exploring model vulnerabilities to adversarial attacks. Our framework employs a multi-faceted visualization scheme designed to support the analysis of data poisoning attacks from the perspective of models, data instances, features, and local structures. We demonstrate our framework through two case studies on binary classifiers and illustrate model vulnerabilities with respect to varying attack strategies.

📄 PDF Abstract BibTeX arXiv:1907.07296

Code (1)

VADERASU/visual-analytics-adversarial-attacks 공식 구현

Tasks

BIG-bench Machine LearningData Poisoning

Similar Papers 제목 키워드 기반

Snowball Adversarial Attack on Traffic Sign Classification

2025-02-27 · Anthony Etim, Jakub Szefer

Adversarial attacks on machine learning models often rely on small, imperceptible perturbations to mislead classifiers. Such strategy focuses on minimizing the visual perturbation for humans so they are not confused, and…

Adversarial AttackClassificationTraffic Sign Recognition

Mitigating Adversarial Vulnerability through Causal Parameter Estimation by Adversarial Double Machine Learning

2023-07-14 · ICCV 2023 1 · Byung-Kwan Lee, Junho Kim, Yong Man Ro

Adversarial examples derived from deliberately crafted perturbations on visual inputs can easily harm decision process of deep neural networks. To prevent potential threats, various adversarial training-based defense met…

Adversarial Robustnessparameter estimation

As Firm As Their Foundations: Can open-sourced foundation models be used to create adversarial examples for downstream tasks?

2024-03-19 · Anjun Hu, Jindong Gu, Francesco Pinto, Konstantinos Kamnitsas 외

Foundation models pre-trained on web-scale vision-language data, such as CLIP, are widely used as cornerstones of powerful machine learning systems. While pre-training offers clear advantages for downstream learning, it …

Adversarial AttackImage Captioningobject-detectionObject Detection+3

A reading survey on adversarial machine learning: Adversarial attacks and their understanding

2023-08-07 · Shashank Kotyan

Deep Learning has empowered us to train neural networks for complex data with high performance. However, with the growing research, several vulnerabilities in neural networks have been exposed. A particular branch of res…

Unveiling Hidden Visual Information: A Reconstruction Attack Against Adversarial Visual Information Hiding

2024-08-08 · Jonggyu Jang, Hyeonsu Lyu, Seongjin Hwang, Hyun Jong Yang

This paper investigates the security vulnerabilities of adversarial-example-based image encryption by executing data reconstruction (DR) attacks on encrypted images. A representative image encryption method is the advers…

Reconstruction Attack