Non Robust

Non-robustness in machine learning and robotics focuses on understanding and mitigating the vulnerability of systems to unexpected inputs or perturbations. Current research investigates this issue across various models, including deep neural networks and robotic control systems, exploring factors like noise sensitivity, adversarial examples, and the impact of model parameters and training regimes. This research is crucial for improving the reliability and safety of AI systems in critical applications, such as autonomous vehicles and medical diagnosis, where robustness is paramount. Addressing non-robustness is essential for building trustworthy and dependable AI systems.

Papers

October 14, 2024

Feature Averaging: An Implicit Bias of Gradient Descent Leading to Non-Robustness in Neural Networks
Binghui Li, Zhixuan Pan, Kaifeng Lyu, Jian Li
Neural Network Native Robustness Gradient Descent Stochastic Gradient Descent Implicit Bias Non Robust

January 31, 2024

Force Push: Robust Single-Point Pushing with Force Feedback
Adam Heins, Angela P. Schoellig
Neural Network Force Feedback Force Torque Sensor UNO Push Omnidirectional Robot Non Robust

August 18, 2023

Noise Sensitivity and Stability of Deep Neural Networks for Binary Classification
Johan Jonasson, Jeffrey E. Steif, Olof Zetterqvist
Deep Neural Network Core Stability Binary Classification Non Robust Noise Tolerance

July 5, 2023

Transgressing the boundaries: towards a rigorous understanding of deep learning and its (non-)robustness
Carsten Hartmann, Lorenz Richter
Deep Learning Machine Learning Document Boundary Statistical Learning Bayesian Deep Learning Rigorous Framework Non Robust Robustness Issue

June 9, 2023

Bring Your Own (Non-Robust) Algorithm to Solve Robust MDPs by Estimating The Worst Kernel
Kaixin Wang, Uri Gadot, Navdeep Kumar, Kfir Levy, Shie Mannor
Native Robustness Practical Algorithm Sequential Decision Robust Policy DeepMind Control Suite Non Robust Novel Kernel

May 18, 2023

Robust Single-Point Pushing with Force Feedback
Adam Heins, Angela P. Schoellig
Neural Network Force Feedback Force Torque Sensor Stable Pushing Non Robust

March 15, 2023

Agnostic Multi-Robust Learning Using ERM
Saba Ahmadi, Avrim Blum, Omar Montasser, Kevin Stangl
Robust Learning Robust Loss Non Robust

June 30, 2022

Detecting and Recovering Adversarial Examples from Extracting Non-robust and Highly Predictive Adversarial Perturbations
Mingyu Dong, Jiahao Chen, Diqun Yan, Jingxing Gao, Li Dong, Rangding Wang
Adversarial Example Data Detection Adversarial Perturbation Imperceptible Adversarial Perturbation Non Robust Adversarial Example Detection

March 22, 2022

On the (Non-)Robustness of Two-Layer Neural Networks in Different Learning Regimes
Elvis Dohmatob, Alberto Bietti
Neural Network Native Robustness Adversarial Example Adversarial Robustness Two Layer Neural Network Regime Switching Non Robust Lazy Training

March 1, 2022

FP-Loc: Lightweight and Drift-free Floor Plan-assisted LiDAR Localization
Ling Gao, Laurent Kneip
Lightweight High LiDAR Based Localization Drift Free Ground Plane Structural Constraint Non Robust

Non Robust

Papers

Feature Averaging: An Implicit Bias of Gradient Descent Leading to Non-Robustness in Neural Networks

Force Push: Robust Single-Point Pushing with Force Feedback

Noise Sensitivity and Stability of Deep Neural Networks for Binary Classification

Transgressing the boundaries: towards a rigorous understanding of deep learning and its (non-)robustness

Bring Your Own (Non-Robust) Algorithm to Solve Robust MDPs by Estimating The Worst Kernel

Robust Single-Point Pushing with Force Feedback

Agnostic Multi-Robust Learning Using ERM

Detecting and Recovering Adversarial Examples from Extracting Non-robust and Highly Predictive Adversarial Perturbations

On the (Non-)Robustness of Two-Layer Neural Networks in Different Learning Regimes

FP-Loc: Lightweight and Drift-free Floor Plan-assisted LiDAR Localization