Splitting the Difference on Adversarial Training - A Method for Robust Neural Networks
Discover a novel approach to adversarial training that enhances neural network robustness while maintaining optimal accuracy by splitting data classes into clean and adversarial categories.
Scalable Multi-Party Computation Protocols for Machine Learning in the Honest-Majority Setting
Discover groundbreaking advances in privacy-preserving machine learning through scalable multi-party computation protocols, featuring efficient methods for secure operations and unprecedented performance with up to 63 parties.
Defending Against Data Reconstruction Attacks in Federated Learning: An Information Theory Approach
Explore advanced defense strategies against data reconstruction attacks in federated learning through information theory, focusing on privacy preservation and efficient training methods.
K-Waay: Fast and Deniable Post-Quantum X3DH without Ring Signatures
Explore a groundbreaking post-quantum secure protocol for messaging apps that improves upon Signal's X3DH, offering enhanced security and efficiency without ring signatures through split-KEM technology.
MD-ML: Super Fast Privacy-Preserving Machine Learning for Malicious Security with Dishonest Majority
Explore groundbreaking advances in privacy-preserving machine learning with MD-ML framework, offering enhanced security and efficiency for multi-party computation in neural network inference and training.
DNN-GP: Diagnosing and Mitigating Model's Faults Using Latent Concepts
Explore an innovative fault diagnosis tool for Deep Neural Networks that interprets latent concepts to detect and mitigate various model vulnerabilities, from adversarial attacks to concept drift.
Lotto: Secure Participant Selection against Adversarial Servers in Federated Learning
Explore secure participant selection in Federated Learning through Lotto, a system designed to protect against adversarial servers while maintaining efficient performance and privacy guarantees.
Quantum Locally Testable Codes and Codes with Transversal Gates
Delve into advanced quantum error correction concepts, focusing on qLDPC codes, local testability, and transversal gates through higher-dimensional construction methods and cup product structures.
Microsoft OmniParser - AI Screen Reading and UI Interaction
Discover how OmniParser enables AI agents to interpret and interact with user interfaces through advanced screen reading and LLM integration capabilities.
Rehashing and Collision Handling in Data Structures
Master efficient data storage and retrieval techniques through hashing, including hash functions and collision handling methods like chaining and open addressing for optimized data structure performance.
All Pairs Shortest Path Using Dynamic Programming: Floyd-Warshall Algorithm
Master the Floyd-Warshall algorithm for finding shortest paths between all vertex pairs in weighted graphs using dynamic programming techniques and systematic path optimization methods.
Machine Learning Applications in Cosmology - Past, Present, and Future
Explore the evolution and impact of machine learning in cosmological research, from historical applications to cutting-edge developments and future possibilities in astronomical studies.
Real-Time Path Tracing in Unreal Engine 5
Discover groundbreaking real-time path tracing techniques using ReSTIR technology in UE5, achieving offline-quality lighting and visuals that match the Path Tracer's capabilities in real-time rendering.
The Future of Human-Computer Interaction - Opening Keynote UIST 2024
Discover groundbreaking insights into user interface technology and software development through Prof. Raj Reddy's keynote address at the 37th ACM Symposium on User Interface Software and Technology.
Setting Up STM32MP1 as AWS Greengrass V2 Core Device
Master the configuration of STM32MP135 DK for AWS Greengrass V2, including automated IoT setup, IAM roles, PKCS#11 key management, and secure service deployment for IoT solutions.
The Unfinished Epic of Discrete Tomography
Delve into the mathematical foundations of discrete tomography through an engaging exploration of its ongoing challenges and theoretical developments in modern computational geometry.
Finding Complex Patterns in Trajectory Data via Geometric Set Cover
Explore geometric set cover techniques for analyzing complex trajectory patterns, focusing on mathematical approaches to pattern recognition and data analysis in spatial movement.
Constant-Cost Communication in Randomized Computing
Explore the fascinating role of randomness in communication complexity, focusing on efficient protocols for solving equality problems and their broader implications in computing theory.
Building Adaptive Multi-Agent AI Systems: From Theory to Implementation
Explore adaptive multi-agent AI systems through reinforcement learning, examining how agents navigate dynamic physical and social environments while developing cooperative strategies and decision-making capabilities.
Towards Persistent Computing - Next Generation of Computational Science
Explore the future of computational science and persistent computing with insights from aerospace engineering expert Venkat Raman's innovative research and perspectives.
How Generative AI Powers the Next Generation of Mercari Marketplace
Discover how Mercari leverages GenAI to enhance its C2C marketplace, from streamlining item listings to improving search relevance and product recommendations through advanced ML engineering techniques.