Adversarial-DL

Papers

• MetaAdvDet: Towards Robust Detection of Evolving Adversarial Attacks
• Connecting Lyapunov Control Theory to Adversarial Attacks
• Enhancing Adversarial Example Transferability with an Intermediate Level Attack
• advPattern: Physical-World Attacks on Deep Person Re-Identification via Adversarially Transformable Patterns
• On the Robustness of Semantic Segmentation Models to Adversarial Attacks
• The Attack Generator: A Systematic Approach Towards Constructing Adversarial Attacks
• Copy and Paste: A Simple But Effective Initialization Method for Black-Box Adversarial Attacks
• AdvHat: Real-world adversarial attack on ArcFace Face ID system
• Adversarial Attacks on Neural Networks for Graph Data
• Adversarial Attack on Graph Structured Data

CCS

• Attacking Graph-based Classification via Manipulating the Graph Structure
• Adversarial Sensor Attack on LiDAR-based Perception in Autonomous Driving

Arxiv

• Adversarial learning
• On Evaluating Adversarial Robustness
• Customizing an Adversarial Example Generator with Class-Conditional GANs
• Generating Adversarial Examples with Adversarial Networks
• Defending Against Adversarial Attacks by Leveraging an Entire GAN
• Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning Models
• Evasion Attacks against Machine Learning at Test Time
• Exploiting Excessive Invariance caused by Norm-Bounded Adversarial Robustness
• SentiNet: Detecting Physical Attacks Against Deep Learning Systems
• Sitatapatra: Blocking the Transfer of Adversarial Samples
• Adversarial Examples Are Not Bugs, They Are Features
• Wasserstein Adversarial Examples via Projected Sinkhorn Iterations
• Real-Time Adversarial Attacks
• Defense-GAN: Protecting Classifiers Against Adversarial Attacks Using Generative Models
• Robust Graph Neural Network Against Poisoning Attacks via Transfer Learning
• AdvFaces: Adversarial Face Synthesis
• Adversarial Examples on Graph Data: Deep Insights into Attack and Defense
• Data Poisoning against Differentially-Private Learners: Attacks and Defenses
• Data Poisoning Attack against Knowledge Graph Embedding
• Robust Audio Adversarial Example for a Physical Attack
• Adversarial Defense Framework for Graph Neural Network
• The General Black-box Attack Method for Graph Neural Networks
• Adversarial Attack and Defense on Graph Data: A Survey
• Open DNN Box by Power Side-Channel Attack
• Transferable Adversarial Attacks for Image and Video Object Detection
• Exploring Connections Between Active Learning and Model Extraction
• A framework for the extraction of Deep Neural Networks by leveraging public data
• Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey
• [Explaining and harnessing adversarial examples]
• [Adversarial Edit Attacks for Tree Data]
• [Model Extraction and Active Learning]
• [High-Fidelity Extraction of Neural Network Models]
• [LASSIFIERS A GAINST A DVERSARIAL EXAMPLES]

USENIX

• Hybrid Batch Attacks: Finding Black-box Adversarial Examples with Limited Queries
• TreeHuggr: Discovering Where Tree-based Classifiers are Vulnerable to Adversarial Attack
• Local Model Poisoning Attacks to Byzantine-Robust Federated Learning