Created
August 13, 2023 01:35
-
-
Save csima/b5ea16b682f6117c11debee7c40fa8fc to your computer and use it in GitHub Desktop.
ML Attacks
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Acquire Public ML Artifacts | |
Obtain Capabilities | |
Develop Adversarial ML Attack Capabilities | |
Acquire Infrastructure | |
Publish Poisoned Datasets | |
Poison Training Data | |
ML Supply Chain Compromise | |
Evade ML Model | |
Exploit Public-Facing Application | |
ML Model Inference API Access | |
ML-Enabled Product or Service | |
Physical Environment Access | |
Full ML Model Access | |
User Execution | |
Command Scripting Interpreter | |
Backdoor ML Model | |
Discover ML Model Ontology | |
Discover ML Model Family | |
Discover ML Artifacts | |
ML Artifact Collection | |
Data from Information Repositories | |
Data from Local System | |
Create Proxy ML Model | |
Verify Attack | |
Craft Adversarial Data | |
Exfiltration via ML Inference API | |
Exfiltration via Cyber Means | |
Denial of ML Service | |
Spamming ML system with Chaff Data | |
Erode ML Model Integrity | |
Cost Harvesting | |
ML Intellectual Property Theft | |
System Misuse for External Effect | |
Prompt Injection | |
Insecure Output Handling | |
Supply Chain | |
Permission Issues | |
Data Leakage | |
Excessive Agency | |
Over-reliance | |
Insecure Plugins | |
Evasion Auto-Attack | |
Auto Projected Gradient Descent | |
Shadow Attack | |
Wasserstein Attack | |
PE Malware Attacks | |
Imperceptible, Robust & Targeted adversarial for speech recognition | |
Brendan & Bethge Attack | |
Targeted Universal Adversarial Perturbations | |
Targeted Attacks on Speech-to-Text | |
High Confidence Low Uncertainty Attack | |
Iterative Frame Saliency | |
DPatch | |
ShapeShifter | |
Projected Gradient Descent | |
NewtonFool | |
Elastic Net | |
Adversarial Patch | |
Decision Tree Attack | |
Caroline & Wagner attack | |
Universal Perturbation | |
Feature Adversaries | |
DeepFool | |
Virtual Adversarial Method | |
Fast Gradient Method | |
Square Attack | |
HopSkipJump Attack | |
Threshold Attack | |
Pixel Attack | |
Simple Black-box Adversarial | |
Spatial Transformation | |
Query-efficient Black-box | |
Zeroth Order Optimisation | |
Decision-based/Boundary Attack | |
Geometric Decision-based Attack | |
Adversarial Backdoor Embedding | |
Clean Label Feature Collision Attack | |
Clean-Label Backdoor Attack | |
Poisoning Attack on Support Vector Machines | |
Bullseye Polytope | |
Gradient Matching / Witches' Brew Attack | |
Sleeper Agent Attack | |
BadDet Object Generation Attack (OGA) | |
BadDet Regional Misclassification Attack (RMA) | |
BadDet Global Misclassification Attack (GMA) | |
BadDet Object Disappearance Attack (ODA) | |
Functionally Equivalent Extraction | |
Copycat CNN | |
KnockoffNets | |
Attribute Inference Black-Box | |
Attribute Inference White-Box Lifestyle Decision Tree | |
Attribute Inference White-Box Decision Tree |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment