IG
Ian Goodfellow
cs.LGstat.MLcs.CRcs.CVcs.AIcs.NEAlgorithmsArtificial IntelligenceBrainCompetition
On Valency
published · living versionsW_9msk58k4·v1 · currentpublished
Intriguing properties of neural networks
with Christian Szegedy, Wojciech Zaremba, Ilya Sutskever, Joan Bruna +2
1 version
Preprints & journals
62 papers in the corpus · 2012–2025MONA: Myopic Optimization with Non-myopic Approval Can Mitigate Multi-step Reward Hacking2501.13011v2 · Sebastian Farquhar, Vikrant Varma, David Lindner et al.2025 · 0 citationsarXiv
Author Correction: Subtle adversarial image manipulations influence both human and machine perception.38228579 · Veerabadran, Vijay, Goldman, Josh, Shankar, Shreya et al.2024 · 0 citationsNature communications. 2024;15(1):543
Subtle adversarial image manipulations influence both human and machine perception.37582834 · Veerabadran, Vijay, Goldman, Josh, Shankar, Shreya et al.2023 · 16 citationsNature communications. 2023;14(1):4933
Adversarial Training Methods for Semi-Supervised Text Classification1605.07725v4 · Takeru Miyato, Andrew M. Dai, Ian Goodfellow2016 · 201 citationsarXiv
Sanity Checks for Saliency Maps1810.03292v3 · Julius Adebayo, Justin Gilmer, Michael Muelly et al.2018 · 580 citationsarXiv
A domain agnostic measure for monitoring and evaluating GANs1811.05512v2 · Paulina Grnarova, Kfir Y Levy, Aurelien Lucchi et al.2018 · 24 citationsarXiv
Ensemble Adversarial Training: Attacks and Defenses1705.07204v5 · Florian Tramer, Alexey Kurakin, Nicolas Papernot et al.2017 · 2,380 citationsarXiv
Creating High Resolution Images with a Latent Adversarial Generator2003.02365v1 · David Berthelot, Peyman Milanfar, Ian Goodfellow2020 · 9 citationsarXiv
MixMatch: A Holistic Approach to Semi-Supervised Learning1905.02249v2 · David Berthelot, Nicholas Carlini, Ian Goodfellow et al.2019 · 595 citationsarXiv
Adversarial Examples that Fool both Computer Vision and Time-Limited Humans1802.08195v3 · Gamaleldin F. Elsayed, Shreya Shankar, Brian Cheung et al.2018 · 213 citationsAdvances in Neural Information Processing Systems, 2018
Adversarial Reprogramming of Neural Networks1806.11146v2 · Gamaleldin F. Elsayed, Ian Goodfellow, Jascha Sohl-Dickstein2018 · 21 citationsInternational Conference on Learning Representations 2019
Realistic Evaluation of Deep Semi-Supervised Learning Algorithms1804.09170v4 · Avital Oliver, Augustus Odena, Colin Raffel et al.2018 · 205 citationsNeurIPS 2018 Proceedings
Imperceptible, Robust, and Targeted Adversarial Examples for Automatic Speech Recognition1903.10346v2 · Yao Qin, Nicholas Carlini, Ian Goodfellow et al.2019 · 239 citationsarXiv
A Research Agenda: Dynamic Models to Defend Against Correlated Attacks1903.06293v1 · Ian Goodfellow2019 · 12 citationsarXiv
Discriminator Rejection Sampling1810.06758v3 · Samaneh Azadi, Catherine Olsson, Trevor Darrell et al.2018 · 26 citationsarXiv
On Evaluating Adversarial Robustness1902.06705v2 · Nicholas Carlini, Anish Athalye, Nicolas Papernot et al.2019 · 560 citationsarXiv
Deep Learning with Differential Privacy1607.00133v2 · Mart'in Abadi, Andy Chu, Ian Goodfellow et al.2016 · 6,377 citationsProceedings of the 2016 ACM SIGSAC Conference on Computer and Communications Security (ACM CCS), pp. 308-318, 2016on Valency
On the Protection of Private Information in Machine Learning Systems: Two Recent Approaches1708.08022v1 · Mart'in Abadi, 'Ulfar Erlingsson, Ian Goodfellow et al.2017 · 41 citationsIEEE 30th Computer Security Foundations Symposium (CSF), pages 1--6, 2017
New CleverHans Feature: Better Adversarial Robustness Evaluations with Attack Bundling1811.03685v1 · Ian Goodfellow2018 · 2 citationsarXiv
Local Explanation Methods for Deep Neural Networks Lack Sensitivity to Parameter Values1810.03307v1 · Julius Adebayo, Justin Gilmer, Ian Goodfellow et al.2018 · 87 citationsarXiv
Unrestricted Adversarial Examples1809.08352v1 · Tom B. Brown, Nicholas Carlini, Chiyuan Zhang et al.2018 · 70 citationsarXiv
Adversarial Spheres1801.02774v3 · Justin Gilmer, Luke Metz, Fartash Faghri et al.2018 · 42 citationsarXiv
Skill Rating for Generative Models1808.04888v1 · Catherine Olsson, Surya Bhupatiraju, Tom Brown et al.2018 · 23 citationsarXiv
TensorFuzz: Debugging Neural Networks with Coverage-Guided Fuzzing1807.10875v1 · Augustus Odena, Ian Goodfellow2018 · 134 citationsarXiv
Motivating the Rules of the Game for Adversarial Example Research1807.06732v2 · Justin Gilmer, Ryan P. Adams, Ian Goodfellow et al.2018 · 156 citationsarXiv
Technical Report on the CleverHans v2.1.0 Adversarial Examples Library1610.00768v6 · Nicolas Papernot, Fartash Faghri, Nicholas Carlini et al.2016 · 401 citationsarXiv
Defense Against the Dark Arts: An overview of adversarial example security research and future research directions1806.04169v1 · Ian Goodfellow2018 · 29 citationsarXiv
Is Generator Conditioning Causally Related to GAN Performance?1802.08768v2 · Augustus Odena, Jacob Buckman, Catherine Olsson et al.2018 · 48 citationsarXiv
Gradient Masking Causes CLEVER to Overestimate Adversarial Perturbation Size1804.07870v1 · Ian Goodfellow2018 · 20 citationsarXiv
MaskGAN: Better Text Generation via Filling in the______1801.07736v3 · William Fedus, Ian Goodfellow, Andrew M. Dai2018 · 354 citationsarXiv
Many Paths to Equilibrium: GANs Do Not Need to Decrease a Divergence At Every Step1710.08446v3 · William Fedus, Mihaela Rosca, Balaji Lakshminarayanan et al.2017 · 159 citationsarXivon Valency
The Space of Transferable Adversarial Examples1704.03453v2 · Florian Tramer, Nicolas Papernot, Ian Goodfellow et al.2017 · 424 citationsarXiv
NIPS 2016 Tutorial: Generative Adversarial Networks1701.00160v4 · Ian Goodfellow2016 · 1,300 citationsarXivon Valency
Practical Black-Box Attacks against Machine Learning1602.02697v4 · Nicolas Papernot, Patrick McDaniel, Ian Goodfellow et al.2016 · 3,680 citationsarXiv
Adversarial examples in the physical world1607.02533v4 · Alexey Kurakin, Ian Goodfellow, Samy Bengio2016 · 4,710 citationsarXiv
Adversarial Machine Learning at Scale1611.01236v2 · Alexey Kurakin, Ian Goodfellow, Samy Bengio2016 · 368 citationsarXiv
Adversarial Attacks on Neural Network Policies1702.02284v1 · Sandy Huang, Nicolas Papernot, Ian Goodfellow et al.2017 · 62 citationsarXiv
Unsupervised Learning for Physical Interaction through Video Prediction1605.07157v4 · Chelsea Finn, Ian Goodfellow, Sergey Levine2016 · 260 citationsarXiv
Adversarial Autoencoders1511.05644v2 · Alireza Makhzani, Jonathon Shlens, Navdeep Jaitly et al.2015 · 308 citationsarXiv
Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samples1605.07277v1 · Nicolas Papernot, Patrick McDaniel, Ian Goodfellow2016 · 1,387 citationsarXivon Valency
Net2Net: Accelerating Learning via Knowledge Transfer1511.05641v4 · Tianqi Chen, Ian Goodfellow, Jonathon Shlens2015 · 156 citationsarXiv
Improving the Robustness of Deep Neural Networks via Stability Training1604.04326v1 · Stephan Zheng, Yang Song, Thomas Leung et al.2016 · 681 citationsarXiv
TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems1603.04467v2 · Mart'in Abadi, Ashish Agarwal, Paul Barham et al.2016 · 9,713 citationsarXivon Valency
Efficient Per-Example Gradient Computations1510.01799v2 · Ian Goodfellow2015 · 31 citationsarXiv
Challenges in representation learning: a report on three machine learning contests.25613956 · Goodfellow, Ian J, Erhan, Dumitru, Luc Carrier, Pierre et al.2015 · 793 citationsNeural networks : the official journal of the International Neural Network Society. 2015;64:59-63
Qualitatively characterizing neural network optimization problems1412.6544v6 · Ian J. Goodfellow, Oriol Vinyals, Andrew M. Saxe2014 · 335 citationsarXiv
On distinguishability criteria for estimating generative models1412.6515v4 · Ian J. Goodfellow2014 · 84 citationsarXiv
An Empirical Investigation of Catastrophic Forgetting in Gradient-Based Neural Networks1312.6211v3 · Ian J. Goodfellow, Mehdi Mirza, Da Xiao et al.2013 · 885 citationsarXiv
On the Challenges of Physical Implementations of RBMs1312.5258v2 · Vincent Dumoulin, Ian J. Goodfellow, Aaron Courville et al.2013 · 55 citationsProc. AAAI 2014, pp. 1199-1205
Generative Adversarial Networks1406.2661v1 · Ian J. Goodfellow, Jean Pouget-Abadie, Mehdi Mirza et al.2014 · 4,621 citationsarXiv
Career total: 100 works. 62 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.