Adversarial Attacks Courses and Certifications

VinAI

Robust Multivariate Time-Series Forecasting: Adversarial Attacks and Defense Mechanisms

Explore adversarial attacks on multivariate forecasting models and learn effective defense strategies, including randomized smoothing and adversarial training, to enhance robustness in time-series predictions.

• YouTube
• 1 hour 10 minutes
• Self-Paced
• Free Video

USENIX

Securing AI at Scale - Practical Defenses against Prompt Injection, Adversarial Attacks, and Model Poisoning

Discover practical AI security defenses including prompt injection prevention, adversarial attack mitigation, and model poisoning protection for scalable systems.

• YouTube
• 39 minutes
• Self-Paced
• Free Video

Board Infinity

AI Risk and Compliance: Audit and Governance Foundations

Red team AI systems with Giskard, classify them under the EU AI Act and NIST AI RMF, apply SHAP and LIME, and deploy guardrails and Presidio.

• Coursera
• 4 weeks, 4 hours a week
• Self-Paced
• Paid Course

Black Hat

The Devil is in the GAN - Defending Deep Generative Models Against Adversarial Attacks

Examines training-time backdoor attacks on deep generative models and defenses for detecting compromised models.

• YouTube
• 39 minutes
• Self-Paced
• Conference Talk

Defending Against Adversarial Model Attacks Using Kubeflow

Learn to protect AI models from adversarial attacks using Kubeflow. Explore threats, defenses, and practical implementations in this comprehensive presentation by IBM experts.

• YouTube
• 43 minutes
• Self-Paced
• Free Video

Trusted and Responsible AI - Explainability, Adversarial Attacks, Bias, and Fairness

Explore key aspects of responsible AI: explainability, adversarial challenges, bias mitigation, and fairness. Learn strategies for building trustworthy and ethical AI systems in real-world applications.

• YouTube
• 37 minutes
• Self-Paced
• Free Video

Defending Against Adversarial Model Attacks Using Kubeflow

Shows how to build adversarially robust Kubeflow pipelines and check a deployed model with logged serving payloads.

• YouTube
• 21 minutes
• Self-Paced
• Conference Talk

Navigating AI/ML Challenges in Medical Software Development - 11.6

Explore AI/ML challenges in medical software development, covering risk assessment, training data quality, and robust system design for clinical applications.

• YouTube
• 16 minutes
• Self-Paced
• Free Video

Advanced Computer Vision - Spring 2021

Dive into adversarial machine learning, explainable AI, and robust neural network architectures through cutting-edge research papers and advanced computer vision techniques.

• YouTube
• 12 hours 40 minutes
• Self-Paced
• Free Video

RSA Conference

Attacking Machine Learning - On the Security and Privacy of Neural Networks

Explore how adversarial examples fool neural network classifiers and how trained models can leak private training data.

• YouTube
• 48 minutes
• Self-Paced
• Conference Talk

Black Hat

Zen and the Art of Adversarial Machine Learning

Operational guidance for attacking machine-learning models through extraction, evasion, inversion, membership inference, poisoning, and adversarial ML assessment.

• YouTube
• 44 minutes
• Self-Paced
• Conference Talk

Black Hat

Bypassing NGAV for Fun and Profit

An explainability-guided adversarial attack modifies PE features to make malware evade next-generation antivirus classifiers while preserving functionality.

• YouTube
• 35 minutes
• Self-Paced
• Conference Talk

Black Hat

Hiding Objects from Computer Vision by Exploiting Correlation Biases

Explores how correlation biases in computer vision can be exploited to automatically generate adversarial images that confuse object detectors.

• YouTube
• 27 minutes
• Self-Paced
• Conference Talk

NDC Conferences

How AI is Impacting Cybersecurity - Does It?

A technical look at how AI changes cybersecurity, from securing AI systems to attacks on models and code.

• YouTube
• 53 minutes
• Self-Paced
• Conference Talk

Google TechTalks

Robust Design Discovery and Exploration in Bayesian Optimization

Explore data-driven methods for robust design discovery and optimization, focusing on Bayesian techniques that efficiently handle uncertainties and adversarial scenarios in various scientific domains.

• YouTube
• 53 minutes
• Self-Paced
• Free Video