Robust Adversarial

Robust adversarial research focuses on developing machine learning models resistant to adversarial attacks—malicious inputs designed to cause misclassification. Current efforts concentrate on improving adversarial training techniques, exploring diverse model architectures like Bayesian neural networks and employing methods such as tensor factorization and information gain optimization to enhance robustness. This field is crucial for ensuring the reliability and safety of AI systems in high-stakes applications like autonomous driving and medical diagnosis, where vulnerabilities to adversarial attacks can have severe consequences. The ultimate goal is to create models that are both accurate and resilient to manipulation.

Papers

May 14, 2024

The Pitfalls and Promise of Conformal Inference Under Adversarial Attacks
Ziquan Liu, Yufei Cui, Yan Yan, Yi Xu, Xiangyang Ji, Xue Liu, Antoni B. Chan
Adversarial Attack Adversarial Training Adversarial Robustness Common Pitfall Promise Conformal Inference Robust Adversarial

September 3, 2023

Robust Adversarial Defense by Tensor Factorization
Manish Bhattarai, Mehmet Cagri Kaymak, Ryan Barron, Ben Nebgen, Kim Rasmussen, Boian Alexandrov
Adversarial Attack Adversarial DEfense Tensor Factorization Low Rank Decomposition Robust Defense Robust Adversarial

December 5, 2022

Bayesian Learning with Information Gain Provably Bounds Risk for a Robust Adversarial Defense
Bao Gia Doan, Ehsan Abbasnejad, Javen Qinfeng Shi, Damith C. Ranasinghe
Adversarial Attack Adversarial Training Bayesian Neural Network High Quality Risk Description Bayesian Learning Information Gain Adversarial Risk Robust Adversarial

October 6, 2022

Dynamic Stochastic Ensemble with Adversarial Robust Lottery Ticket Subnetworks
Qi Peng, Wenlin Liu, Ruoxi Qin, Libin Hou, Bin Yan, Linyuan Wang
Adversarial Attack Ensemble Defense Dynamic Ensemble Robust Adversarial

May 5, 2022

Can collaborative learning be private, robust and scalable?
Dmitrii Usynin, Helena Klause, Johannes C. Paetzold, Daniel Rueckert, Georgios Kaissis
Differential Privacy Adversarial Training Adversarial Sample Collaborative Learning Adversarial Data Robust Adversarial

April 26, 2022

RAMBO-RL: Robust Adversarial Model-Based Offline Reinforcement Learning
Marc Rigter, Bruno Lacerda, Nick Hawes
Reinforcement Learning Offline Reinforcement Learning Robust Version Model Based Offline Reinforcement Learning Adversarial Environment Conservative Policy Robust Adversarial

December 2, 2021

Training Efficiency and Robustness in Deep Learning
Fartash Faghri
Deep Learning Native Robustness Deep Learning Model Adversarial Robustness Robust Adversarial