AI Village·21 min
Nahid Farhady
Examines privacy-preserving machine learning techniques, homomorphic encryption, and differential privacy safeguards.
privacy-preserving-mlmachine-learningdifferential-privacy+1
DEF CON Safe Mode/AI Village across years
AI Village Safe Mode
Virtual (Discord and Twitch) · 6-9 August 2020 · 12 talks
AI Village explores the intersection of artificial intelligence and information security. Talks cover adversarial machine learning, evasion techniques against ML-based malware detectors, deep reinforcement learning vulnerabilities, and privacy-preserving model architectures.
1–12 of 12 talks
AI Village·1 hr 30 min
Workshop
Hands-on workshop demonstrating adversarial evasion techniques targeting ML-based Antimalware Scan Interface providers.
amsiadversarial-mlevasion+2
AI Village·30 min
Erick Galinkin
A primer breaking down core vocabulary, concepts, and foundational theory in machine learning security.
machine-learningvocabularyadversarial-ml+1
AI Village·49 min
Lee · Saxe
Presents a cutting-edge deep neural network architecture designed to detect subtle social engineering patterns in emails.
social-engineeringphishingnlp+2
AI Village·54 min
Journal Club Live
Examines Fawkes, an image cloaking tool that adds pixel-level perturbations to photos to deceive facial recognition models.
facial-recognitionfawkesadversarial-perturbation+1
AI Village·49 min
GTKlondike
Analyzes how threat actors can leverage machine learning and artificial intelligence to automate and enhance cyberattacks.
adversarial-aioffensive-securityai-assisted-attacks+1
AI Village·29 min
comathematician
Demonstrates Goko, an algorithm and tool for detecting fine-grained, localized concept drift in production ML models.
concept-driftdrift-detectionmachine-learning+1
AI Village·22 min
Hyrum Anderson · Zoltan Balaz
Reviews results and top evasion strategies from the AI Village machine learning security and evasion competition.
machine-learningadversarial-mlcontest+1
AI Village·28 min
Imeyerov
Details Project Domino, an open-source citizen data science effort leveraging NLP to track COVID-19 misinformation.
misinformationdata-sciencenlp+1
AI Village·58 min
Journal Club Live
Discusses practical methodologies for discovering exploitable bugs, implementation flaws, and attack surfaces in ML systems.
adversarial-mlvulnerability-researchmachine-learning+1
AI Village·58 min
Vahid Behdazan
Explores vulnerabilities and adversarial manipulation techniques in deep reinforcement learning agents and environments.
reinforcement-learningdeep-learningadversarial-attacks+1
AI Village·24 min
Nahid Farhady
Introduces the Spectrum framework for deploying and operationalizing machine learning models in threat monitoring pipelines.
machine-learningthreat-monitoringdetection+1