AI Village·22 min
Sven Cattell
Deep learning approaches to security threats and vulnerabilities.
machine-learningai-securitydeep-learning+1
DEF CON 26/AI Village across years
AI Village DC26
Caesars Palace, Flamingo, Linq, Las Vegas · 9-12 August 2018 · 32 talks
AI Village presentations from DEF CON 26 covering machine learning security, AI safety, adversarial techniques, and ethical considerations in artificial intelligence.
1–24 of 30 talks / 32
AI Village·12 min
Zhao
Techniques and empirical results in adversarial training for hardening neural network models against evasion.
adversarial-machine-learningdeep-learningmodel-hardening+1
AI Village·14 min
Alex Long
Behind-the-scenes machine learning operations at a major antivirus company.
machine-learningai-securitymodel-applications+1
AI Village·27 min
Andy Applebaum
Using automated planning and AI to improve red team offensive operations.
machine-learningsecurity-applicationsmodel-training+2
AI Village·14 min
Kang Li
Deploying machine learning security systems in production.
machine-learningai-applicationssecurity-systems+1
AI Village·17 min
Xingxing Wei
Accelerating and stabilizing adversarial perturbation generation using momentum-based gradient optimization.
adversarial-machine-learninggradient-descentevasion+1
AI Village·13 min
Chris Gardner
Using natural language interaction with ML to discover vulnerabilities in software programs.
machine-learningvulnerability-discoverychatbots+2
AI Village·15 min
Ivan Torroledo
Threat detection using defensive machine learning techniques.
machine-learningthreat-detectionai-security+1
AI Village·33 min
Fedor Sakharov
Security research applications of machine learning analysis.
machine-learningsecurity-researchai-applications+1
AI Village·38 min
Brian Genz
Generating labeled datasets from adversary simulations using MITRE ATT&CK framework for ML training.
machine-learninglabeled-datamitre-att-and-ck+2
AI Village·25 min
Joseph Clements
Designing hardware trojan exploits embedded directly into neural network accelerator silicon and hardware.
hardware-trojansneural-networkshardware-security+1
AI Village·37 min
Li · Jiao
Leveraging open-source intelligence and public datasets for security research and AI model analysis.
osintopen-source-intelligenceadversarial-machine-learning+1
AI Village·27 min
TonTon Huang
Machine learning applications and techniques in cybersecurity.
machine-learningsecurityai-applications+1
AI Village·23 min
Andrew Morris
Identifying and correlating anomalies in internet-wide network scan data using machine learning.
anomaly-detectionmachine-learningnetwork-scanning+2
AI Village·27 min
Matt
Neural network approaches to cybersecurity challenges.
machine-learningneural-networksdeep-learning+1
AI Village·35 min
Rob Brandon
Evaluating machine learning models for security applications.
machine-learningsecurity-aimodel-evaluation+1
AI Village·18 min
Ariel Herbert Voss
Techniques for hardening machine learning models against adversarial attacks and evasion.
model-hardeningadversarial-trainingrobustness+2
AI Village·25 min
drhyrum
Threat analysis using defensive AI and machine learning.
machine-learningai-defensesecurity-systems+1
AI Village·33 min
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·39 min
Mark Mager
Malware detection using machine learning classifiers.
machine-learningclassificationdetection+1
AI Village·19 min
Guo · Cuevas
An overview of recent progress and developments in adversarial deep learning attacks and defenses.
adversarial-machine-learningdeep-learningevasion+1
AI Village·37 min
bodaceacat
Panel discussion on responsible and ethical approaches to offensive machine learning research.
machine-learning-adversarialoffensive-mlresponsible-disclosure+2
AI Village·20 min
Raphael Norwitz
Defensive machine learning strategies against adversarial attacks.
machine-learningai-defenseadversarial-defense+1
AI Village·22 min
Rohan Taori · Ameya Kamsetty
Generating targeted adversarial perturbation examples against black-box automated speech recognition systems.
adversarial-machine-learningaudio-processingspeech-recognition+1