Circumventing Video Identification Using Augmented Reality
Explore techniques for augmenting video streams with computer-generated ID cards, using OpenCV, OpenGL, and skin detection to create convincing fake identifications for video chats.
KI-Basierte Modifikation von Videostreams aus Überwachungskameras
Demonstration der KI-basierten Echtzeitmanipulation von Videostreams aus IP-Kameras, einschließlich Entfernung von Personen und Firmware-Modifikationen. Diskussion über Einschränkungen und Gegenmaßnahmen.
A New Open Source Multimedia Creativity Suite - AVIO
Explore AVIO: Python-based multimedia suite integrating visual media and audio. Overview, demos, and future possibilities of this open-source project for synchronized processing and mixing of various input streams.
Are Spoof-Proof Biometrics Really Possible?
Explore biometric security challenges, spoof attack detection, and best practices for implementing secure, privacy-respecting biometric systems with expert Dr. Stephanie Schuckers.
JARVIS Never Saw It Coming - Hacking Machine Learning in Speech, Text and Face Recognition
Explore hacking techniques for machine learning systems in speech, text, and facial recognition, including exploits, backdoors, and adversarial attacks. Live demo included.
Easterhegg 2019 - Generative Adversarial Networks für Anfänger
Einführung in Generative Adversarial Networks: Überblick, Geschichte und praktische Anwendungen für Entwickler. Erklärt Konzepte, Techniken und Herausforderungen anhand von Beispielen wie Pokémon-Generator und Gesichtsalterung.
Machine Duping - Pwning Deep Learning Systems
Explore vulnerabilities in deep learning systems and learn techniques to manipulate image recognition, speech recognition, and phishing detection through practical demonstrations and attack methodologies.
Some Thoughts on Deep Learning and Infosec - Jeremy Howard - USENIX Enigma - 2018
Exploring the potential of deep learning in infosec, challenging misconceptions and highlighting untapped opportunities for practical applications in cybersecurity.
Überwachung, Social Media und Repression am Beispiel von Belarus
Einblick in die systematische Nutzung moderner Überwachungstechnologien zur Unterdrückung politischer Bewegungen in Belarus unter dem autoritären Regime von Alexander Lukaschenko.
Datenschutz für Aktivist*innen
Leitfaden zur digitalen Selbstverteidigung für Aktivisten: Datenschutz, Verschlüsselung und praktische Tipps zum Schutz der Privatsphäre bei politischer Teilhabe und Demonstrationen.
How to Build an Effective Malware Protection Architecture for File Uploads in Modern Web Apps
Explore a novel approach to automated malware analysis for file uploads in web apps, focusing on scalability, performance, and effective detection of malicious content.
Tensor Networks and Neural Network States - From Chiral Topological Order to Image Classification
Explore neural networks in quantum physics and image recognition, bridging manybody physics with machine learning for innovative applications in various fields.
Unlocking the Power of ML for Your JavaScript Applications with TensorFlow.js
Explore TensorFlow.js for ML in JavaScript: learn to integrate, retrain models, and leverage ML beyond browsers. Includes demos of virtual makeup try-on and radiology diagnostics.
Challenges of Using V4L2 to Capture and Process Video Sensor Images
Explore challenges in capturing and processing video sensor images using V4L2, covering BAYER arrays, white balance, and color adjustment techniques.
Image Representations Learned With Unsupervised Pre-Training Contain Human-like Biases
Explore how unsupervised pre-training in image representations can lead to human-like biases, examining methods, results, and implications for AI fairness and ethics.
One Label, One Billion Faces - Usage and Consistency of Racial Categories in Computer Vision
Explores racial categorization in computer vision, examining usage, consistency, and implications for fairness in AI systems. Highlights challenges and potential biases in facial recognition technology.
AI and the Post Work World
Dr. Kai-Fu Lee explores AI's impact on work, proposing a 3Rs strategy (relearn, recalibrate, renaissance) to prepare for job displacement and harness AI's benefits for humanity.
Deep Learning in OpenCV
Explore OpenCV's deep learning module, its architecture, and acceleration techniques for optimal performance in computer vision applications.
Complex Cameras on Linux
Explore Linux camera support, from traditional V4L2 to media-controller devices. Learn about image processing, APIs, and efforts to standardize complex camera applications.
Computer Vision - IEEE VR 2022
Cutting-edge computer vision research for VR, including gaze tracking, perceptual optimization, marker-based localization, and visual-inertial odometry. Explores innovative techniques to enhance VR experiences.
Accessorize to a Crime - Real and Stealthy Attacks on State-Of-The-Art Face Recognition
Explores stealthy attacks on face recognition systems using adversarial machine learning techniques, demonstrating vulnerabilities in state-of-the-art facial recognition technology through impersonation experiments.