The Vanishing Trick for Self-Driving Cars

AI Security AI Village28 minOpen on YouTube ↗

Adversarial physical and digital perturbations that make objects disappear from autonomous driving perception models.

Summary

AI adversarial attacks: The Vanishing Trick for Self-Driving Cars. At 3:00-4:00, attack methodology introduced. Mid-presentation demonstrates practical exploitation.

(AI summary — Claude Haiku)

Related talks

AI Village·17 min

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

Boosting Adversarial Attacks with Momentum

Xingxing Wei

Accelerating and stabilizing adversarial perturbation generation using momentum-based gradient optimization.

adversarial-machine-learninggradient-descentevasion+1

AI Village·19 min

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

Recent Progress in Adversarial Deep Learning

Guo · Cuevas

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

adversarial-machine-learningdeep-learningevasion+1

AI Village·12 min

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

Adversarial Training

Zhao

Techniques and empirical results in adversarial training for hardening neural network models against evasion.

adversarial-machine-learningdeep-learningmodel-hardening+1