Adversarial Machine Learning: A Taxonomy and Terminology of Attacks and Mitigation

preview_player
Показать описание

This week, Apostol Vassilev from National Institute of Standards and Technology (NIST) will discuss a taxonomy of adversarial machine learning (AML) from the National Institute of Standards and Technology (NIST) Trustworthy and Responsible AI report. It explores types of attacks, attacker goals and capabilities, and mitigation methods, providing a structured understanding of AML concepts and challenges in securing AI systems. Key Takeaways: -Overview of AML attacks (evasion, data poisoning, trojans) and their impact on AI systems. -Insights into attacker objectives and knowledge levels, crucial for developing defense strategies. -Practical methods for mitigating adversarial attacks and managing AI security risks. -Identification of open challenges in AML, guiding future practices for robust AI systems.
  1. QuantUniversity Channel
Рекомендации по теме
Adversarial Machine Learning: 1:17:59

Adversarial Machine Learning: A Taxonomy and Terminology of Attacks and Mitigation

Overview of Adversarial 0:08:10

Overview of Adversarial Machine Learning

Adversarial Machine Learning: 0:32:43

Adversarial Machine Learning: A Taxonomy and Terminology of Attacks and Mitigations | DSS 2024

The Evolved Adversarial 0:30:31

The Evolved Adversarial Machine Learning Landscape | The MLSecOps Podcast

Explaining Vulnerabilities to 0:04:59

Explaining Vulnerabilities to Adversarial Machine Learning through Visual Analytics

Security in Machine 0:19:50

Security in Machine Learning: Taxonomy and Applied Counterstrategies, Flavio Clesio

DEF CON 26 0:16:15

DEF CON 26 AI VILLAGE - infosecanon - The Current State of Adversarial Machine Learning

#040 - Adversarial 1:36:16

#040 - Adversarial Examples (Dr. Nicholas Carlini, Dr. Wieland Brendel, Florian Tramèr)

Part 36: graph 0:15:18

Part 36: graph pooling for graph neural networks: progress, challenges, and opportunities

DEF CON 24 0:44:13

DEF CON 24 - Clarence Chio - Machine Duping 101: Pwning Deep Learning Systems

Crack The Code: 0:10:10

Crack The Code: NIST's Adversarial Machine Learning (AML) Explained

Adversarial Machine Learning 0:44:08

Adversarial Machine Learning and Its Impacts on Cybersecurity

What does the 0:01:01

What does the transparency of open source ML mean for the security of AI? #MLSecOps #airisks #ai

Generating Adversarial Examples 0:18:56

Generating Adversarial Examples & Defense Methods For Online Fraud Detection

Part2: Taxonomy of 0:44:19

Part2: Taxonomy of Adversarial ML Attacks (Tutorial on Security and Robustness of ML)

Secure Machine Learning: 0:38:54

Secure Machine Learning: Overcoming Algorithmic Bias, Adversarial ML in the Wild West of AI

Making Sense of 0:40:01

Making Sense of the Landscape of Attacks and Defenses Against AI

Tutorial on Adversarial 1:14:32

Tutorial on Adversarial Deep Learning for Cyber Security

DSI | Adversarial 1:05:46

DSI | Adversarial Machine Learning: Categories, Concepts, and Current Landscape

Unveiling the Secrets 1:15:56

Unveiling the Secrets of Adversarial Machine Learning: Part 7 (Evasion Multiclass Classifiers)

Adversarial Detection with 0:03:08

Adversarial Detection with Model Interpretation

Holistic Adversarial Robustness, 0:27:50

Holistic Adversarial Robustness, Pin Yu Chen

Adversarial Machine Learning 0:59:16

Adversarial Machine Learning in Information Security

Adversarial Machine Learning 1:41:07

Adversarial Machine Learning - Part 1 - Winter School ICTP Trieste, Nov 15-16, 2018