Search Results for author:
Found 10 papers, 4 papers with code
Larimar: Large Language Models with Episodic Memory Control
Efficient and accurate updating of knowledge stored in Large Language Models (LLMs) is one of the most pressing research challenges today.
PatchCURE: Improving Certifiable Robustness, Model Utility, and Computation Efficiency of Adversarial Patch Defenses
State-of-the-art defenses against adversarial patch attacks can now achieve strong certifiable robustness with a marginal drop in model utility.
MultiRobustBench: Benchmarking Robustness Against Multiple Attacks
Using our framework, we present the first leaderboard, MultiRobustBench, for benchmarking multiattack evaluation which captures performance across attack types and attack strengths.
Characterizing the Optimal 0-1 Loss for Multi-class Classification with a Test-time Attacker
Finding classifiers robust to adversarial examples is critical for their safe deployment.
Formulating Robustness Against Unforeseen Attacks
Based on our generalization bound, we propose variation regularization (VR) which reduces variation of the feature extractor across the source threat model during training.
Parameterizing Activation Functions for Adversarial Robustness
To address this, we analyze the direct impact of activation shape on robustness through PAFs and observe that activation shapes with positive outputs on negative inputs and with high finite curvature can increase robustness.
Robust Learning Meets Generative Models: Can Proxy Distributions Improve Adversarial Robustness?
We circumvent this challenge by using additional data from proxy distributions learned by advanced generative models.
Neural Networks with Recurrent Generative Feedback
This mechanism can be interpreted as a form of self-consistency between the maximum a posteriori (MAP) estimation of an internal generative model and the external environment.
Brain-inspired Robust Vision using Convolutional Neural Networks with Feedback
Primates have a remarkable ability to correctly classify images even in the presence of significant noise and degradation.
Out-of-Distribution Detection Using Neural Rendering Generative Models
Our results show that when trained on CIFAR-10, lower likelihood (of latent variables) is assigned to SVHN images.
