2020

Exploring the Vulnerability of Deep Neural Networks: A Study of Parameter Corruption

Sun, Xu, Zhang, Zhiyuan, Ren, Xuancheng et al.

Understand

We argue that the vulnerability of model parameters is of crucial value to the study of model robustness and generalization but little research has been devoted to understanding this matter.

In this work, we propose an indicator to measure the robustness of neural network parameters by exploiting their vulnerability via parameter corruption.
The proposed indicator describes the maximum loss variation in the non-trivial worst-case scenario under parameter corruption.
For practical purposes, we give a gradient-based estimation, which is far more effective than random corruption trials that can hardly induce the worst accuracy degradation.

Built on

fairseq: A fast, extensible toolkit for sequence modeling
Original
Ott, M.; Edunov, S.; Baevski, A.; Fan, A.; Gross, S.; Ng, N.; Grangier, D.; and Auli, M. 2019 · 1904
Earlier work this paper cites.
FreeLB: Enhanced Adversarial Training for Language Understanding
Original
Zhu, C.; Cheng, Y.; Gan, Z.; Sun, S.; Goldstein, T.; and Liu, J. 2019 · 1909
Earlier work this paper cites.
80 million tiny images: A large data set for nonparametric object and scene recognition
Torralba, A.; Fergus, R.; and Freeman, W. T. 2008 · 1970
Earlier work this paper cites.
Building a Large Annotated Corpus of English: The Penn Treebank
Marcus, M. P.; Santorini, B.; and Marcinkiewicz, M. A. 1993 · 1993
Earlier work this paper cites.
Weight Poisoning Attacks on Pre-trained Models
Original
Kurita, K.; Michel, P.; and Neubig, G. 2020 · 2004
Earlier work this paper cites.
Artificial neural networks in hardware: A survey of two decades of progress
Misra, J.; and Saha, I. 2010 · 2010
Earlier work this paper cites.
A Fast and Accurate Dependency Parser using Neural Networks
Chen, D.; and Manning, C. D. 2014 · 2014
Earlier work this paper cites.
Generative Adversarial Networks
Original
Goodfellow, I. J.; Pouget-Abadie, J.; Mirza, M.; Xu, B.; Warde-Farley, D.; Ozair, S.; Courville, A. C.; and Bengio, Y. 2014 · 2014
Earlier work this paper cites.
Glove: Global Vectors for Word Representation
Pennington, J.; Socher, R.; and Manning, C. D. 2014 · 2014
Earlier work this paper cites.
Intriguing properties of neural networks
Szegedy, C.; Zaremba, W.; Sutskever, I.; Bruna, J.; Erhan, D.; Goodfellow, I. J.; and Fergus, R. 2014 · 2014
Earlier work this paper cites.
How transferable are features in deep neural networks?
Yosinski, J.; Clune, J.; Bengio, Y.; and Lipson, H. 2014 · 2014
Earlier work this paper cites.
Explaining and Harnessing Adversarial Examples
Goodfellow, I. J.; Shlens, J.; and Szegedy, C. 2015 · 2015
Earlier work this paper cites.
ImageNet Large Scale Visual Recognition Challenge
Russakovsky, O.; Deng, J.; Su, H.; Krause, J.; Satheesh, S.; Ma, S.; Huang, Z.; Karpathy, A.; Khosla, A.; Bernstein, M. S.; Berg, A. C.; and Li, F. 2015 · 2015
Earlier work this paper cites.
Understanding Adversarial Training: Increasing Local Stability of Neural Nets through Robust Optimization
Original
Shaham, U.; Yamada, Y.; and Negahban, S. 2015 · 2015
Earlier work this paper cites.
Deep residual learning for image recognition
He, K.; Zhang, X.; Ren, S.; and Sun, J. 2016 · 2016
Earlier work this paper cites.

Similar

DeepFool: A Simple and Accurate Method to Fool Deep Neural Networks
Moosavi-Dezfooli, S.; Fawzi, A.; and Frossard, P. 2016 · 2016
Cited alongside, same era.
Sequence Level Training with Recurrent Neural Networks
Ranzato, M.; Chopra, S.; Auli, M.; and Zaremba, W. 2016 · 2016
Cited alongside, same era.
Generating Videos with Scene Dynamics
Vondrick, C.; Pirsiavash, H.; and Torralba, A. 2016 · 2016
Cited alongside, same era.
Sequence-to-Sequence Learning as Beam-Search Optimization
Wiseman, S.; and Rush, A. M. 2016 · 2016
Cited alongside, same era.
Towards Evaluating the Robustness of Neural Networks
Carlini, N.; and Wagner, D. A. 2017 · 2017
Cited alongside, same era.
Entropy-SGD: Biasing Gradient Descent Into Wide Valleys
Chaudhari, P.; Choromanska, A.; Soatto, S.; LeCun, Y.; Baldassi, C.; Borgs, C.; Chayes, J. T.; Sagun, L.; and Zecchina, R. 2017 · 2017
Cited alongside, same era.
Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning
Original
Chen, X.; Liu, C.; Li, B.; Lu, K.; and Song, D. 2017 · 2017
Cited alongside, same era.
Good Semi-supervised Learning That Requires a Bad GAN
Dai, Z.; Yang, Z.; Yang, F.; Cohen, W. W.; and Salakhutdinov, R. 2017 · 2017
Cited alongside, same era.
Real-valued (Medical) Time Series Generation with Recurrent Conditional GANs
Original
Esteban, C.; Hyland, S. L.; and Rätsch, G. 2017 · 2017
Cited alongside, same era.
On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima
Keskar, N. S.; Mudigere, D.; Nocedal, J.; Smelyanskiy, M.; and Tang, P. T. P. 2017 · 2017
Cited alongside, same era.
Adversarial examples in the physical world
Kurakin, A.; Goodfellow, I. J.; and Bengio, S. 2017 · 2017
Cited alongside, same era.
Pose Guided Person Image Generation
Ma, L.; Jia, X.; Sun, Q.; Schiele, B.; Tuytelaars, T.; and Gool, L. V. 2017 · 2017
Cited alongside, same era.

Then

Stronger Generalization Bounds for Deep Nets via a Compression Approach
Arora, S.; Ge, R.; Neyshabur, B.; and Zhang, Y. 2018 · 2018
Later among the works it cites.
Synthesizing Audio with Generative Adversarial Networks
Original
Donahue, C.; McAuley, J. J.; and Puckette, M. S. 2018 · 2018
Later among the works it cites.
Towards Deep Learning Models Resistant to Adversarial Attacks
Madry, A.; Makelov, A.; Schmidt, L.; Tsipras, D.; and Vladu, A. 2018 · 2018
Later among the works it cites.
An Analysis of Neural Language Modeling at Multiple Scales
Original
Merity, S.; Keskar, N. S.; and Socher, R. 2018 · 2018
Later among the works it cites.
A Scalable Network-on-Chip Based Neural Network Implementation on FPGAs
Bui, T. T. T.; and Phillips, B. 2019 · 2019
Later among the works it cites.
A Backdoor Attack Against LSTM-Based Text Classification Systems
Dai, J.; Chen, C.; and Li, Y. 2019 · 2019
Later among the works it cites.
All-optical spiking neurosynaptic networks with self-learning capabilities
Feldmann, J.; Youngblood, N.; Wright, C. D.; Bhaskaran, H.; and Pernice, W. 2019 · 2019
Later among the works it cites.
BadNets: Evaluating Backdooring Attacks on Deep Neural Networks
Gu, T.; Liu, K.; Dolan-Gavitt, B.; and Garg, S. 2019 · 2019
Later among the works it cites.
LCA: Loss Change Allocation for Neural Network Training
Lan, J.; Liu, R.; Zhou, H.; and Yosinski, J. 2019 · 2019
Later among the works it cites.
Data-Free Quantization Through Weight Equalization and Bias Correction
Nagel, M.; van Baalen, M.; Blankevoort, T.; and Welling, M. 2019 · 2019
Later among the works it cites.
A Digital Hardware System for Spiking Network of Tactile Afferents
Salimi-Nezhad, N.; Ilbeigi, E.; Amiri, M.; Falotico, E.; and Laschi, C. 2019 · 2019
Later among the works it cites.
Amplifier-based MOS Analog Neural Network Implementation and Weights Optimization
Weber, T. O.; da Silva Labres, D.; and Cabrera, F. L. 2019 · 2019
Later among the works it cites.
Gradient $\ell_1$ Regularization for Quantization Robustness
Alizadeh, M.; Behboodi, A.; van Baalen, M.; Louizos, C.; Blankevoort, T.; and Welling, M. 2020 · 2020
Closest in time.
TBT: Targeted Neural Network Attack With Bit Trojan
Rakin, A. S.; He, Z.; and Fan, D. 2020 · 2020
Closest in time.
Towards Certificated Model Robustness Against Weight Perturbations
Weng, T.; Zhao, P.; Liu, S.; Chen, P.; Lin, X.; and Daniel, L. 2020 · 2020
Closest in time.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…

Reading the bibliography…