Latest

• iDECODe: In-distribution Equivariance for Conformal Out-of-distribution Detection
• Shaping Noise for Robust Attributions in Neural Stochastic Differential Equations
• Trigger Hunting with a Topological Prior for Trojan Detection
• Detecting out-of-context objects using graph contextual reasoning network.
• Principal Manifold Flows
• Trinity: Trust, Resilience and Interpretability of Machine Learning Models
• Automated Synthesis of Quantum Circuits using Symbolic Abstractions and Decision Procedures
• MISA: Online Defense of Trojaned Models using Misattributions
• On Smoother Attributions using Neural Stochastic Differential Equations
• TrojDRL: Evaluation of Backdoor Attacks on Deep Reinforcement Learning
• Learning Certified Control Using Contraction Metric
• Estimating the Density of States of Boolean Satisfiability Problems on Classical and Quantum Computing Platforms
• Model-Centered Assurance for Autonomous Systems
• On the Need for Topology-Aware Generative Models for Manifold-Based Defenses
• Attribution-Based Confidence Metric For Deep Neural Network
• A risk-sensitive finite-time reachability approach for safety of stochastic dynamic systems
• Detecting OODs as datapoints with high uncertainty
• Sherlock : A Tool for Verification of Deep Neural Networks
• TeLEx: learning signal temporal logic from positive examples using tightness metric
• Data-efficient Learning of Robust Control Policies
• Duality-Based Nested Controller Synthesis from STL Specifications for Stochastic Linear Systems
• Learning Task Specifications from Demonstrations
• Explaining AI Decisions Using Efficient Methods for Learning Sparse Boolean Formulae
• Learning and Verification of Feedback Control Systems using Feedforward Neural Networks
• Output range analysis for deep neural networks
• Safe autonomy under perception uncertainty using chance-constrained temporal logic