A comprehensive summary in this direction!
✅ 000.Machine Learning in Adversarial Settings-PPT
✅ 0603.Can Machine Learning Be Secure
✅ 1100.Adversarial Machine Learning
✅ 1610.Accessorize to a Crime : Real and Stealthy Attacks on State-of-the-Art Face Recognition
✅ 1707.NO Need to Worry about Adversarial Examples in Object Detection in Autonomous Vehicles
✅ 1710.Standard detectors aren't (currently) fooled by physical adversarial stop signs
✅ 1500.Fundamental limits on adversarial robustness
✅ 1503.Explaining and Harnessing Adversarial Examples
✅ 1608.A Boundary Tilting Persepective on the Phenomenon of Adversarial Examples
✅ 1608.Robustness of classifiers:from adversarial to random noise
✅ 1705.Analysis of universal adversarial perturbations
✅ 1801.High Dimensional Spaces, Deep Learning and Adversarial Examples
✅ 1400.Evasion attacks against machine learning at test time
✅ 1402.Intriguing properties of neural networks
✅ 1503.Explaining and Harnessing Adversarial Examples
✅ 1504.Deep neural networks are easily fooled High confidence predictions for unrecognizable images
✅ 1507.Distributional Smoothing with Virtual Adversarial Training
✅ 1507.Manitest-Are classifiers really invariant
✅ 1510.Exploring the space of adversarial images
✅ 1510.The Limitations of Deep Learning in Adversarial Settings
✅ 1601.Adversarial Perturbations Against Deep Neural Networks for Malware Classification
✅ 1602.Practical Black-Box Attacks against Deep Learning Systems using Adversarial Examples
✅ 1605.Transferability in Machine Learning from Phenomena to Black-Box Attacks using Adversarial Samples
✅ 1607.DeepFool_ A Simple and Accurate Method to Fool Deep Neural Networks
✅ 1608.Stealing Machine Learning Models via Prediction APIs
✅ 1610.DeepDGA-Adversarially Tuned Domain Generation and Detection
✅ 1611.Delving into Transferable Adversarial Examples and Black-box Attacks
✅ 1612.Simple Black-Box Adversarial Perturbations for Deep Networks
✅ 1700.Concrete Problems for Autonomous Vehicle Safety_ Advantages of Bayesian Deep Learning
✅ 1701.Vulnerability of Deep Reinforcement Learning to Policy Induction Attacks
✅ 1702.Adversarial Attacks on Neural Network Policies
✅ 1702.Adversarial examples for generative models
✅ 1702.Adversarial examples in the physical world
✅ 1702.Adversarial machine learning at scale
✅ 1702.Generating Adversarial Malware Examples for Black-Box Attacks Based on GAN
✅ 1702.Towards Deep Learning Models Resistant to Adversarial Attacks
✅ 1703.Adversarial Transformation Networks: Learning to Generate Adversarial Examples
✅ 1703.Generative Poisoning Attack Method Against Neural Networks
✅ 1703.Notes on Adversarial Examples
✅ 1703.Tactics of Adversarial Attack on Deep Reinforcement Learning Agents
✅ 1703.Towards Evaluating the Robustness of Neural Networks
✅ 1703.Universal adversarial perturbations
✅ 1705.Analysis of universal adversarial perturbations
✅ 1705.Ensemble Adversarial Training Attacks and Defenses
✅ 1705.Generative Adversarial Trainer Defense to Adversarial Perturbations with GAN
✅ 1705.Stabilizing Adversarial Nets With Prediction Methods
✅ 1707.APE-GAN-- Adversarial Perturbation Elimination with GAN
✅ 1707.Evading Machine Learning Malware Detection
✅ 1707.Fast Feature Fool-A data independent approach to universal adversarial perturbations
✅ 1707.Robust Physical-World Attacks on Machine Learning Models
✅ 1707.Robust Physical-World Attacks on Deep Learning Visual Classification
✅ 1707.Synthesizing Robust Adversarial Examples
✅ 1708.Machine Learning as an Adversarial Service Learning Black-Box Adversarial Examples
✅ 1708.Proof of Work Without All the Work
✅ 1709.Can you fool AI with adversarial examples on a visual Turing test
✅ 1709.EAD Elastic Net Attacks to Deep Neural Networks via Adversarial Examples
✅ 1709.Ground-Truth Adversarial Examples
✅ 1710.One pixel attack for fooling deep neural networks
✅ 1711.Security Risks in Deep Learning Implementations
✅ 1712.Adversarial Patch
✅ 1712.Robust Deep Reinforcement Learning with Adversarial Attacks
✅ 1712.Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning
✅ 1712.Where Classification Fails, Interpretation Rises
✅ 1801.Learning to Evade Static PE Machine Learning Malware Models via Reinforcement Learning
✅ 1801.LaVAN-Localized and Visible Adversarial Noise
✅ 1803.Improving Transferability of Adversarial Examples with Input Diversity
✅ 1603.Distillation as a Defense to Adversarial Perturbations against Deep Neural Networks
✅ 1604.Improving the robustness of deep neural networks via stability training
✅ 1605.Adversarial Training Methods for Semi-Supervised Text Classification
✅ 1607.Defensive Distillation is Not Robust to Adversarial Examples
✅ 1608.A study of the effect of JPG compression on adversarial images
✅ 1610.Adversary Resistant Deep Neural Networks with an Application to Malware Detection
✅ 1703.Biologically inspired protection of deep networks from adversarial attacks
✅ 1704.Enhancing Robustness of Machine Learning Systems via Data Transformations
✅ 1704.Feature Squeezing Detecting Adversarial Examples in Deep Neural Networks
✅ 1705.Detecting Adversarial Examples in Deep Neural Networks
✅ 1705.Extending Defensive Distillation
✅ 1705.Feature Squeezing Mitigates and Detects Carlini Wagner Adversarial Examples
✅ 1705.Generative Adversarial Trainer Defense to Adversarial Perturbations with GAN
✅ 1705.MagNet-a Two-Pronged Defense against Adversarial Examples
✅ 1706.Adversarial Example Defenses ：Ensembles of Weak Defenses are not Strong
✅ 1707.AE-GAN adversarial eliminating with GAN
✅ 1707.APE-GAN-- Adversarial Perturbation Elimination with GAN
✅ 1709.Mitigating Evasion Attacks to Deep Neural Networks via Region-based Classification
✅ 1711.Mitigating adversarial effects through randomization
✅ 1805.Defense-GAN: Protecting Classifiers Against Adversarial Attacks Using Generative Models
✅ 1606.Concrete Problems in AI Safety
✅ 1610.SoK Towards the Science of Security and Privacy in Machine Learning
✅ 1611.Towards the Science of Security and Privacy in Machine Learning
✅ 1707.A Survey on Resilient Machine Learning
✅ 1712.Adversarial Examples-Attacks and Defenses for Deep Learning
✅ 1801.Threat of Adversarial Attacks on Deep Learning in Computer Vision-A Survey
✅ 1802.Adversarial Risk and the Dangers of Evaluating Against Weak Attacks
✅ 1612.Adversarial Examples Detection in Deep Networks with Convolutional Filter Statistics
✅ 1702.On Detecting Adversarial Perturbations
✅ 1702.On the (Statistical) Detection of Adversarial Examples
✅ 1703.Blocking Transferability of Adversarial Examples in Black-Box Learning Systems
✅ 1703.Detecting Adversarial Samples from Artifacts
✅ 1704.SafetyNet-Detecting and Rejecting Adversarial Examples Robustly
✅ 1705.Adversarial Examples Are Not Easily Detected-Bypassing Ten Detection Methods
✅ 1712.Defense against Adversarial Attacks Using High-Level Representation Guided Denoiser
✅ 1803.Detecting Adversarial Examples via Neural Fingerprinting
✅ 1600.Accessorize to a Crime: Real and Stealthy Attacks on State-of-the-Art Face Recognition
✅ 1702.Adversarial examples in the physical world
✅ 1707.Robust Physical-World Attacks on Machine Learning Models
✅ 1707.NO Need to Worry about Adversarial Examples in Object Detection in Autonomous Vehicles
✅ 1707.Synthesizing Robust Adversarial Examples
✅ 1707.Robust Physical-World Attacks on Deep Learning Visual Classification
✅ 1710.Standard detectors aren’t (currently) fooled by physical adversarial stop signs
✅ 1801.Audio Adversarial Examples: Targeted Attacks on Speech-to-Text
✅ 1606.Adversarial Perturbations Against Deep Neural Networks for Malware Classificationc
✅ 1705.Black-Box Attacks against RNN based Malware Detection Algorithms
✅ 1706.Automated Poisoning Attacks and Defenses in Malware Detection Systems:An Adversarial Machine Learning Approach
✅ 1707.Evading Machine Learning Malware Detection
✅ 1710.Malware Detection by Eating a Whole EXE
✅ 1712.Attack and Defense of Dynamic Analysis-Based, Adversarial Neural Malware Classification Models
✅ 1801.Learning to Evade Static PE Machine Learning Malware Models via Reinforcement Learning
✅ 1803.Adversarial Malware Binaries_ Evading Deep Learning for Malware Detection in Executables
✅ 1803.Malytics_ A Malware Detection Scheme
✅ 1804.Generic Black-Box End-to-End Attack against RNNs and Other API Calls Based Malware Classifiers
✅ 1805.Adversarial Attacks on Neural Networks for Graph Data
✅ 1810.Exploring Adversarial Examples in Malware Detection
✅ 1811.rsarial Examples for Malware Detection
✅ 1812.earning under Attack_ Vulnerability Exploitation and Security Measures