Recent Progress in Adversarial Deep Learning

AI Security AI Village19 minOpen on YouTube ↗

An overview of recent progress and developments in adversarial deep learning attacks and defenses.

Summary

AI security: Recent Progress in Adversarial Deep Learning. At 2:00-3:00, problem statement. Around 6:00-8:00, technical approach. Later sections (12:00+) show results.

(AI summary — Claude Haiku)

Related talks

AI Village·33 min

DEF CON
AI Security
Date: Aug 2018
Location: Las Vegas

Practical Adversarial Attacks

Moustafa Alzantot · Yash Sharma

Practical black-box and gradient-free adversarial attack methodologies against machine learning systems.

adversarial-machine-learningblack-box-attacksevasion+1

AI Village·23 min

DEF CON
AI Security
Date: Aug 2018
Location: Las Vegas

Weapons for Dog Fight: Adapting Malware

Zhuang Zhang

Adapting and mutating malware samples using adversarial techniques to bypass machine-learning antivirus detectors.

malware-analysisadversarial-machine-learningevasion+1

Main Stage·44 min

DEF CON
AI Security
Date: Aug 2016
Location: Las Vegas

Machine Duping 101: Pwning Deep Learning Systems

Clarence Chio

Clarence Chio explores adversarial perturbation techniques to evade deep neural network classifiers used in biometric authentication and malware detection.

adversarial-machine-learningdeep-learningmodel-evasion+2