Robust Design Discovery and Exploration in Bayesian Optimization
Explore data-driven methods for robust design discovery and optimization, focusing on Bayesian techniques that efficiently handle uncertainties and adversarial scenarios in various scientific domains.
Robust Multivariate Time-Series Forecasting: Adversarial Attacks and Defense Mechanisms
Explore adversarial attacks on multivariate forecasting models and learn effective defense strategies, including randomized smoothing and adversarial training, to enhance robustness in time-series predictions.
In Search of Invariance in Brains and Machines
Explore mathematical frameworks for robust AI perception, focusing on Lie theory to model hierarchical structures and transformations in real-world object recognition.
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.
AI Under the Hood: Unmasking Hidden Threats
Explore a comprehensive analysis of AI threat modeling frameworks, examining safety protocols and risk assessment methods for AI/ML applications while learning to identify and address potential vulnerabilities.
Safeguarding Machine Learning Systems - A Comprehensive Security Plan
Discover a holistic security framework for ML systems, covering data protection, model fortification, platform security, compliance measures, and human-centric safeguards for robust AI deployment.
Formalizing and Benchmarking Prompt Injection Attacks and Defenses
Explore a systematic framework for understanding and evaluating prompt injection attacks on LLM applications, including analysis of 5 attack types and 10 defense mechanisms across multiple models.
PhishDecloaker: Detecting CAPTCHA-cloaked Phishing Websites via Hybrid Vision-based Interactive Models
Discover how PhishDecloaker uses AI and computer vision to detect CAPTCHA-protected phishing websites, improving detection rates from 0% to 74.25% and enhancing cybersecurity defenses.