NeurIPS16~19のadversarial examples関連論文リンク集
目視で判断したので、間違っていたり抜けてたりするかもしれませんが、ご容赦ください。
19
[1910.07629] A New Defense Against Adversarial Images: Turning a Weakness into a Strength
Adversarial Examples are not Bugs, they are Features
[1906.04948] Tight Certificates of Adversarial Robustness for Randomly Smoothed Classifiers
[1904.12843] Adversarial Training for Free!
[1910.14356] Certifiable Robustness to Graph Perturbations
[1809.03113] Certified Adversarial Robustness with Additive Noise
[1905.12202] Empirically Measuring Concentration: Fundamental Limits on Intrinsic Robustness
[1907.10764] Defense Against Adversarial Attacks Using Feature Scattering-based Adversarial Training
[1906.04392] Subspace Attack: Exploiting Promising Subspaces for Query-Efficient Black-box Attacks
[1811.10745] ResNets Ensemble via the Feynman-Kac Formalism to Improve Natural and Robust Accuracies
[1910.06513] ZO-AdaMM: Zeroth-Order Adaptive Momentum Method for Black-Box Optimization
[1902.03538] Model Compression with Adversarial Robustness: A Unified Optimization Framework
[1905.00877] You Only Propagate Once: Accelerating Adversarial Training via Maximal Principle
[1905.12784] Intrinsic dimension of data representations in deep neural networks
[1902.02041] Fooling Neural Network Interpretations via Adversarial Model Manipulation
[1908.01517] Adversarial Self-Defense for Cycle-Consistent GANs
[1909.05822] On the Hardness of Robust Classification
[1905.13021] Robustness to Adversarial Perturbations in Learning from Incomplete Data
[1905.13736] Unlabeled Data Improves Adversarial Robustness
[1909.00900] Metric Learning for Adversarial Robustness
Cross-Modal Learning with Adversarial Samples
[1904.13000] Adversarial Training and Robustness for Multiple Perturbations
[1911.00126] Adversarial Music: Real World Audio Adversary Against Wake-word Detection System
[1906.04584] Provably Robust Deep Learning via Adversarially Trained Smoothed Classifiers
[1905.09768] Zero-shot Knowledge Transfer via Adversarial Belief Matching
[1907.02610] Adversarial Robustness through Local Linearization
[1905.13725] Are Labels Required for Improving Adversarial Robustness?
[1906.06919] Improving Black-box Adversarial Attacks with a Transfer-based Prior
[1906.00001] Functional Adversarial Attacks
[1905.11736] Cross-Domain Transferability of Adversarial Perturbations
Certifying Geometric Robustness of Neural Networks
[1906.03526] Provably Robust Boosted Decision Stumps and Trees against Adversarial Attacks
[1910.05821] Policy Poisoning in Batch Reinforcement Learning and Control
[1911.04681] On Robustness to Adversarial Examples and Polynomial Optimization
[1905.09027] Learning to Confuse: Generating Training Time Adversarial Data with Auto-Encoder
[1906.03849] Robustness Verification of Tree-based Models
[1905.09957] Robust Attribution Regularization
[1909.12272] Lower Bounds on Adversarial Robustness from Optimal Transport
[1906.07916] Convergence of Adversarial Training in Overparametrized Neural Networks
[1902.01148] Theoretical evidence for adversarial robustness through randomization
On Relating Explanations and Adversarial Examples
Image Synthesis with a Single (Robust) Classifier
18
Hessian-based Analysis of Large Batch Training and Robustness to Adversaries
Deep Defense: Training DNNs with Improved Adversarial Robustness
Adversarial Examples that Fool both Computer Vision and Time-Limited Humans
With Friends Like These, Who Needs Adversaries?
Scaling provable adversarial defenses
Thwarting Adversarial Examples: An $L_0$-Robust Sparse Fourier Transform
A Spectral View of Adversarially Robust Features
Adversarially Robust Generalization Requires More Data
Towards Robust Detection of Adversarial Examples
Attacks Meet Interpretability: Attribute-steered Detection of Adversarial Samples
Towards Robust Interpretability with Self-Explaining Neural Networks
Semidefinite relaxations for certifying robustness to adversarial examples
Adversarial Attacks on Stochastic Bandits
Adversarial vulnerability for any classifier
Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networks
Adversarial Risk and Robustness: General Definitions and Implications for the Uniform Distribution
Constructing Unrestricted Adversarial Examples with Generative Models
Robust Detection of Adversarial Attacks by Modeling the Intrinsic Properties of Deep Neural Networks
Sparse DNNs with Improved Adversarial Robustness
A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks
17
Certified Defenses for Data Poisoning Attacks
Lower bounds on the robustness to adversarial perturbations
Houdini: Fooling Deep Structured Visual and Speech Recognition Models with Adversarial Examples
[1712.09665] Adversarial Patch
