Randomized Smoothing
PulseAugur coverage of Randomized Smoothing — every cluster mentioning Randomized Smoothing across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
AuditVotes framework boosts GNN robustness and accuracy
Researchers have introduced AuditVotes, a novel framework designed to enhance the robustness of Graph Neural Networks (GNNs) against adaptive attacks. This framework integrates graph rewiring augmentation and conditiona…
-
New framework enhances certified robust regression with gradient information · 2 sources tracked
Researchers have developed a new framework for certified robust regression, addressing limitations in existing methods. This novel approach offers a prediction-centered certificate that ensures the stability of smoothed…
-
New TrajRS framework offers certified robustness for autonomous driving trajectory prediction
Researchers have developed TrajRS, a new framework based on Randomized Smoothing to provide certified robustness for pedestrian trajectory prediction models. This is crucial for the safety of autonomous driving systems,…
-
New meta-learning framework slashes compute costs for certified neural network robustness
Researchers have developed a new meta-learning framework for certified robustness in neural networks, aiming to reduce the extreme computational costs associated with Randomized Smoothing (RS). This approach uses a ligh…
-
Audio classification robustness needs clear representation reporting
Researchers have identified a critical ambiguity in applying randomized smoothing for audio classification robustness certification. The standard method assumes noise is added in a single vector space, but audio process…
-
New RRISE method drastically cuts cost for certified AI robustness
Researchers have developed RRISE, a novel framework for robust radius inference that significantly speeds up the process of certifying $\ell_2$ classification robustness. By training a learned surrogate model, RRISE rep…
-
New defense offers certified robustness for time-series anomaly detection
Researchers have developed the first defense mechanism that provides certified robustness for time-series anomaly detection under the Dynamic Time Warping (DTW) metric. This new approach adapts the randomized smoothing …
-
Laplace-Bridged Smoothing offers faster, certified AI robustness on edge devices
Researchers have developed Laplace-Bridged Smoothing (LBS), a new method to improve the efficiency and effectiveness of certified robustness for machine learning models. LBS analytically reformulates Randomized Smoothin…