Explaining and Harnessing Adversarial Examples

Ian Goodfellow; Jonathon Shlens; Christian Szegedy

doi:https://doi.org/10.48550/arxiv.1412.6572

Explaining and Harnessing Adversarial Examples

2014 · arXiv (Cornell University) · 8,146 citations · 18 from inside this corpus

Ian Goodfellow, Jonathon Shlens, Christian Szegedy

The source holds an abstract for this work, but its best open-access copy is under no open licence, which does not permit us to republish the text. Read it at the source below.

22 of 22 neighbouring works in this corpus. Blue is what this paper cites; orange is what cites it, and a dashed line is one neighbour citing another. Only the largest labels are drawn — every node carries its full title on hover.

this paper works it cites works citing it node size = global citations · hover for the full title

Citation edge evidence

Each row is directed from the citing work to the cited work. Source status remains readable without the interactive graph.

Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities and challe…→Explaining and Harnessing Adversarial ExamplesLegacy edge — source detail unavailable
DeepFool: A Simple and Accurate Method to Fool Deep Neural Networks→Explaining and Harnessing Adversarial ExamplesLegacy edge — source detail unavailable
The Limitations of Deep Learning in Adversarial Settings→Explaining and Harnessing Adversarial ExamplesLegacy edge — source detail unavailable
Boosting Adversarial Attacks with Momentum→Explaining and Harnessing Adversarial ExamplesLegacy edge — source detail unavailable
Explainable AI: A Review of Machine Learning Interpretability Methods→Explaining and Harnessing Adversarial ExamplesLegacy edge — source detail unavailable
Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised …→Explaining and Harnessing Adversarial ExamplesLegacy edge — source detail unavailable
Universal Adversarial Perturbations→Explaining and Harnessing Adversarial ExamplesLegacy edge — source detail unavailable
A survey on semi-supervised learning→Explaining and Harnessing Adversarial ExamplesLegacy edge — source detail unavailable
Robust Physical-World Attacks on Deep Learning Visual Classification→Explaining and Harnessing Adversarial ExamplesLegacy edge — source detail unavailable
Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey→Explaining and Harnessing Adversarial ExamplesLegacy edge — source detail unavailable
Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networks→Explaining and Harnessing Adversarial ExamplesLegacy edge — source detail unavailable
Adversarial Examples in the Physical World→Explaining and Harnessing Adversarial ExamplesLegacy edge — source detail unavailable
Adversarial Examples: Attacks and Defenses for Deep Learning→Explaining and Harnessing Adversarial ExamplesLegacy edge — source detail unavailable
ZOO→Explaining and Harnessing Adversarial ExamplesLegacy edge — source detail unavailable
Accessorize to a Crime→Explaining and Harnessing Adversarial ExamplesLegacy edge — source detail unavailable
Deep Learning--based Text Classification→Explaining and Harnessing Adversarial ExamplesLegacy edge — source detail unavailable
Adversarial Examples Are Not Easily Detected→Explaining and Harnessing Adversarial ExamplesLegacy edge — source detail unavailable
Explaining Deep Neural Networks and Beyond: A Review of Methods and Applications→Explaining and Harnessing Adversarial ExamplesLegacy edge — source detail unavailable
Explaining and Harnessing Adversarial Examples→Long Short-Term MemoryLegacy edge — source detail unavailable
Explaining and Harnessing Adversarial Examples→Dropout: a simple way to prevent neural networks from overfittingLegacy edge — source detail unavailable
Explaining and Harnessing Adversarial Examples→Multilayer feedforward networks are universal approximatorsLegacy edge — source detail unavailable
Explaining and Harnessing Adversarial Examples→Intriguing properties of neural networksLegacy edge — source detail unavailable
The Limitations of Deep Learning in Adversarial Settings→Intriguing properties of neural networksLegacy edge — source detail unavailable
The Limitations of Deep Learning in Adversarial Settings→Multilayer feedforward networks are universal approximatorsLegacy edge — source detail unavailable
DeepFool: A Simple and Accurate Method to Fool Deep Neural Networks→Intriguing properties of neural networksLegacy edge — source detail unavailable
Adversarial Examples in the Physical World→Accessorize to a CrimeLegacy edge — source detail unavailable
Accessorize to a Crime→The Limitations of Deep Learning in Adversarial SettingsLegacy edge — source detail unavailable
Universal Adversarial Perturbations→Intriguing properties of neural networksLegacy edge — source detail unavailable
Universal Adversarial Perturbations→DeepFool: A Simple and Accurate Method to Fool Deep Neural NetworksLegacy edge — source detail unavailable
Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networks→Intriguing properties of neural networksLegacy edge — source detail unavailable
Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networks→The Limitations of Deep Learning in Adversarial SettingsLegacy edge — source detail unavailable
Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networks→DeepFool: A Simple and Accurate Method to Fool Deep Neural NetworksLegacy edge — source detail unavailable
Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networks→Adversarial Examples in the Physical WorldLegacy edge — source detail unavailable
Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networks→Universal Adversarial PerturbationsLegacy edge — source detail unavailable
ZOO→Intriguing properties of neural networksLegacy edge — source detail unavailable
ZOO→The Limitations of Deep Learning in Adversarial SettingsLegacy edge — source detail unavailable
ZOO→DeepFool: A Simple and Accurate Method to Fool Deep Neural NetworksLegacy edge — source detail unavailable
ZOO→Adversarial Examples in the Physical WorldLegacy edge — source detail unavailable
ZOO→Universal Adversarial PerturbationsLegacy edge — source detail unavailable
ZOO→Feature Squeezing: Detecting Adversarial Examples in Deep Neural NetworksLegacy edge — source detail unavailable
Boosting Adversarial Attacks with Momentum→Intriguing properties of neural networksLegacy edge — source detail unavailable
Boosting Adversarial Attacks with Momentum→Adversarial Examples in the Physical WorldLegacy edge — source detail unavailable
Boosting Adversarial Attacks with Momentum→Universal Adversarial PerturbationsLegacy edge — source detail unavailable
Robust Physical-World Attacks on Deep Learning Visual Classification→Intriguing properties of neural networksLegacy edge — source detail unavailable
Robust Physical-World Attacks on Deep Learning Visual Classification→The Limitations of Deep Learning in Adversarial SettingsLegacy edge — source detail unavailable
Robust Physical-World Attacks on Deep Learning Visual Classification→DeepFool: A Simple and Accurate Method to Fool Deep Neural NetworksLegacy edge — source detail unavailable
Robust Physical-World Attacks on Deep Learning Visual Classification→Adversarial Examples in the Physical WorldLegacy edge — source detail unavailable
Robust Physical-World Attacks on Deep Learning Visual Classification→Accessorize to a CrimeLegacy edge — source detail unavailable
Robust Physical-World Attacks on Deep Learning Visual Classification→Universal Adversarial PerturbationsLegacy edge — source detail unavailable
Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey→Intriguing properties of neural networksLegacy edge — source detail unavailable
Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey→Long Short-Term MemoryLegacy edge — source detail unavailable
Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey→The Limitations of Deep Learning in Adversarial SettingsLegacy edge — source detail unavailable
Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey→DeepFool: A Simple and Accurate Method to Fool Deep Neural NetworksLegacy edge — source detail unavailable
Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey→Adversarial Examples in the Physical WorldLegacy edge — source detail unavailable
Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey→Accessorize to a CrimeLegacy edge — source detail unavailable
Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey→Universal Adversarial PerturbationsLegacy edge — source detail unavailable
Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey→Feature Squeezing: Detecting Adversarial Examples in Deep Neural NetworksLegacy edge — source detail unavailable
Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey→ZOOLegacy edge — source detail unavailable
Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey→Boosting Adversarial Attacks with MomentumLegacy edge — source detail unavailable
Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey→Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised …Legacy edge — source detail unavailable
Adversarial Examples: Attacks and Defenses for Deep Learning→Intriguing properties of neural networksLegacy edge — source detail unavailable
Adversarial Examples: Attacks and Defenses for Deep Learning→The Limitations of Deep Learning in Adversarial SettingsLegacy edge — source detail unavailable
Adversarial Examples: Attacks and Defenses for Deep Learning→DeepFool: A Simple and Accurate Method to Fool Deep Neural NetworksLegacy edge — source detail unavailable
Adversarial Examples: Attacks and Defenses for Deep Learning→Adversarial Examples in the Physical WorldLegacy edge — source detail unavailable
Adversarial Examples: Attacks and Defenses for Deep Learning→Accessorize to a CrimeLegacy edge — source detail unavailable
Adversarial Examples: Attacks and Defenses for Deep Learning→Universal Adversarial PerturbationsLegacy edge — source detail unavailable
Adversarial Examples: Attacks and Defenses for Deep Learning→ZOOLegacy edge — source detail unavailable
Adversarial Examples: Attacks and Defenses for Deep Learning→Boosting Adversarial Attacks with MomentumLegacy edge — source detail unavailable
Adversarial Examples: Attacks and Defenses for Deep Learning→Adversarial Examples Are Not Easily DetectedLegacy edge — source detail unavailable
Adversarial Examples Are Not Easily Detected→Dropout: a simple way to prevent neural networks from overfittingLegacy edge — source detail unavailable
Adversarial Examples Are Not Easily Detected→The Limitations of Deep Learning in Adversarial SettingsLegacy edge — source detail unavailable
Adversarial Examples Are Not Easily Detected→DeepFool: A Simple and Accurate Method to Fool Deep Neural NetworksLegacy edge — source detail unavailable
Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised …→Intriguing properties of neural networksLegacy edge — source detail unavailable
Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised …→Dropout: a simple way to prevent neural networks from overfittingLegacy edge — source detail unavailable
Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities and challe…→Intriguing properties of neural networksLegacy edge — source detail unavailable
Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities and challe…→Robust Physical-World Attacks on Deep Learning Visual ClassificationLegacy edge — source detail unavailable
Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities and challe…→Adversarial Examples: Attacks and Defenses for Deep LearningLegacy edge — source detail unavailable
A survey on semi-supervised learning→Intriguing properties of neural networksLegacy edge — source detail unavailable
A survey on semi-supervised learning→Dropout: a simple way to prevent neural networks from overfittingLegacy edge — source detail unavailable
A survey on semi-supervised learning→Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised …Legacy edge — source detail unavailable
Explainable AI: A Review of Machine Learning Interpretability Methods→The Limitations of Deep Learning in Adversarial SettingsLegacy edge — source detail unavailable
Explainable AI: A Review of Machine Learning Interpretability Methods→DeepFool: A Simple and Accurate Method to Fool Deep Neural NetworksLegacy edge — source detail unavailable
Explainable AI: A Review of Machine Learning Interpretability Methods→Accessorize to a CrimeLegacy edge — source detail unavailable
Explainable AI: A Review of Machine Learning Interpretability Methods→Universal Adversarial PerturbationsLegacy edge — source detail unavailable
Explainable AI: A Review of Machine Learning Interpretability Methods→ZOOLegacy edge — source detail unavailable
Explainable AI: A Review of Machine Learning Interpretability Methods→Boosting Adversarial Attacks with MomentumLegacy edge — source detail unavailable
Explainable AI: A Review of Machine Learning Interpretability Methods→Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities and challe…Legacy edge — source detail unavailable
Explaining Deep Neural Networks and Beyond: A Review of Methods and Applications→Intriguing properties of neural networksLegacy edge — source detail unavailable
Explaining Deep Neural Networks and Beyond: A Review of Methods and Applications→Long Short-Term MemoryLegacy edge — source detail unavailable

What this paper cites, inside the corpus

Paper	Year	Cited
Long Short-Term Memory	1997	101,359
Dropout: a simple way to prevent neural networks from overfitting	2014	34,236
Multilayer feedforward networks are universal approximators	1989	9,357
Intriguing properties of neural networks	2013	5,739

What cites it, inside the corpus

Paper	Year	Cited
Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities and challe…	2019	9,796
DeepFool: A Simple and Accurate Method to Fool Deep Neural Networks	2016	5,392
The Limitations of Deep Learning in Adversarial Settings	2016	3,980
Boosting Adversarial Attacks with Momentum	2018	3,040
Explainable AI: A Review of Machine Learning Interpretability Methods	2020	2,907
Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised …	2018	2,873
Universal Adversarial Perturbations	2017	2,744
A survey on semi-supervised learning	2019	2,636
Robust Physical-World Attacks on Deep Learning Visual Classification	2018	2,154
Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey	2018	2,090
Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networks	2018	1,882
Adversarial Examples in the Physical World	2018	1,842
Adversarial Examples: Attacks and Defenses for Deep Learning	2019	1,786
ZOO	2017	1,779
Accessorize to a Crime	2016	1,596
Deep Learning--based Text Classification	2021	1,525
Adversarial Examples Are Not Easily Detected	2017	1,428
Explaining Deep Neural Networks and Beyond: A Review of Methods and Applications	2021	1,424

Links

Download BibTeX · Download RIS · DOI · Open access copy · OpenAlex record

Topics

Adversarial Robustness in Machine Learning	Computer Science
Explainable Artificial Intelligence (XAI)	Computer Science
Anomaly Detection Techniques and Applications	Computer Science

Is this record sound?

complete

Nothing in this record contradicts itself and no field we check is missing.

supports3 author record(s) attached.
supports14 reference(s) recorded.
neutralThe DOI carries no year to check against.
supportsA title is present.

Provenance

Everything above was read from one stored OpenAlex payload, fetched 2026-09-04T03:58:43+00:00.

sha256 5cad55ac5d4d41e1…