Measuring the Speed of the Red Queen's Race - Adaption and Evasion in Malware
Explore the dynamic evolution of malware and security measures using machine learning to quantify adaptation rates in the ongoing cybersecurity arms race.
DeepLocker - Concealing Targeted Attacks with AI Locksmithing
DeepLocker: AI-powered targeted attacks using deep neural networks for evasive malware. Explores mechanisms, implications, and defenses against AI-weaponized cybercrime.
Lowering the Bar - Deep Learning for Side Channel Analysis
Explore deep learning's potential to automate power side channel analysis, enhancing cryptanalytic techniques and signal processing for improved security assessments.
Perception Deception - Physical Adversarial Attack Challenges
Explore physical adversarial attacks on object detection systems, focusing on YOLOv3. Learn tactics to overcome challenges in real-world scenarios and understand implications for AI security.
AI Gone Rogue - Exterminating Deep Fakes Before They Cause Menace
Explore the dangers of deepfakes and learn about an innovative deep learning solution for identifying complex deepfake videos, with a live demonstration of the proposed technology.
The Applications of Deep Learning on Traffic Identification
Explore deep learning for network traffic identification, covering neural networks, automatic feature learning, and anomaly detection. Improve protocol identification beyond traditional methods.
Deep Learning on Disassembly
Explore deep learning techniques applied to disassembly for malware identification, covering the process from raw binaries to model training and evaluation against active malware feeds.
I'm Not a Human - Breaking the Google reCAPTCHA
Explore techniques to bypass Google's reCAPTCHA using risk analysis manipulation, deep learning for image recognition, and automated solving methods. Discusses implications for CAPTCHA security.
Deep Learning and NLP with Spark
Explore deep learning and NLP using Spark, focusing on LSTM neural networks for complex language tasks. Includes real-time demos with Spark Notebook and Streaming.
Audio Classification with Machine Learning
Learn practical techniques for audio classification using machine learning, including spectrograms, CNNs, and transfer learning. Explore applications in speech, music, medical diagnostics, and more using Keras and TensorFlow.
Efficient Defenses Against Adversarial Examples for Deep Neural Networks
Explore efficient defense strategies against adversarial examples in deep neural networks, enhancing the robustness and security of AI systems in critical applications.
The Rise of Artificial Intelligence through Deep Learning
Explore the AI revolution through deep learning with Yoshua Bengio. Discover progress, challenges, and societal impacts of human-level AI, emphasizing the importance of public understanding for collective decision-making.
Stealthy Porn - Understanding Real World Adversarial Images for Illicit Online Promotion
Explore real-world adversarial techniques used to evade image-based detection in online porn promotion, analyzing evasion methods and their effectiveness against popular content detectors.
Comprehensive Privacy Analysis of Deep Learning
Análisis exhaustivo de la privacidad en el aprendizaje profundo, destacando ataques de inferencia de caja blanca y vulnerabilidades en modelos centralizados y federados.
A Deep Learning Approach to Fast, Format-Agnostic Detection of Malicious Web Content
Innovative deep learning method for detecting malicious web content, operating on token streams from static HTML files. Achieves high accuracy and speed without complex parsing or emulation.
Deepfakes Unveiled - The Dark Side of AI and The Future of Truth
Explore the world of deepfakes and synthetic media with AI expert Dr. Mirza Omer Beg. Uncover the technologies behind these creations and their impact on truth, reality, and trust in our digital age.
BGL - GPU-Efficient GNN Training by Optimizing Graph Data I/O and Preprocessing
Optimizing GPU-based GNN training for large graphs through improved data preprocessing, caching, and partitioning techniques, enhancing efficiency and performance in graph-based machine learning tasks.
SLNet - A Spectrogram Learning Neural Network for Deep Wireless Sensing
Innovative deep learning approach for wireless sensing, combining spectrogram generation and learning to enhance accuracy in various applications like gesture recognition and fall detection.
DOTE - Rethinking Predictive WAN Traffic Engineering
Innovative approach to WAN traffic engineering using historical data and deep learning, outperforming existing methods in quality and runtime while nearly matching an omniscient oracle.
An AI Approach to Malware Similarity Analysis - Mapping the Malware Genome With a Deep Neural Network
Explore AI-driven malware similarity analysis using deep neural networks for improved accuracy and adaptability in threat detection and classification.
SHEPHERD - Serving DNNs in the Wild
SHEPHERD: A scalable model serving system that optimizes goodput, resource utilization, and scalability for unpredictable workloads, using a two-level design and novel online algorithm for efficient DNN inference.