Native Robustness
Native robustness in machine learning focuses on developing models inherently resistant to various forms of input perturbations, including adversarial attacks and noisy data, without relying solely on post-hoc defenses. Current research emphasizes techniques like ensemble methods, reprogramming existing models, and modifying training procedures (e.g., using different learning rates for specific model layers or incorporating regularization methods) to improve robustness across diverse model architectures, including convolutional neural networks, vision transformers, and large language models. This field is crucial for deploying reliable AI systems in safety-critical applications, such as healthcare and autonomous driving, where model resilience to unexpected inputs is paramount.
Papers
Robust Bayesian Learning for Reliable Wireless AI: Framework and Applications
Matteo Zecchin, Sangwoo Park, Osvaldo Simeone, Marios Kountouris, David Gesbert
Robustness of Epinets against Distributional Shifts
Xiuyuan Lu, Ian Osband, Seyed Mohammad Asghari, Sven Gowal, Vikranth Dwaracherla, Zheng Wen, Benjamin Van Roy
Analyzing Explainer Robustness via Probabilistic Lipschitzness of Prediction Functions
Zulqarnain Khan, Davin Hill, Aria Masoomi, Joshua Bone, Jennifer Dy
Robustness to corruption in pre-trained Bayesian neural networks
Xi Wang, Laurence Aitchison
Robustness of Explanation Methods for NLP Models
Shriya Atmakuri, Tejas Chheda, Dinesh Kandula, Nishant Yadav, Taesung Lee, Hessel Tuinhof
Adversarial Robustness of Deep Neural Networks: A Survey from a Formal Verification Perspective
Mark Huasong Meng, Guangdong Bai, Sin Gee Teo, Zhe Hou, Yan Xiao, Yun Lin, Jin Song Dong
Measuring Representational Robustness of Neural Networks Through Shared Invariances
Vedant Nanda, Till Speicher, Camila Kolling, John P. Dickerson, Krishna P. Gummadi, Adrian Weller
Invariant Causal Mechanisms through Distribution Matching
Mathieu Chevalley, Charlotte Bunne, Andreas Krause, Stefan Bauer
Bi-stochastically normalized graph Laplacian: convergence to manifold Laplacian and robustness to outlier noise
Xiuyuan Cheng, Boris Landa
Understanding the effect of sparsity on neural networks robustness
Lukas Timpl, Rahim Entezari, Hanie Sedghi, Behnam Neyshabur, Olga Saukh
Guided Diffusion Model for Adversarial Purification from Random Noise
Quanlin Wu, Hang Ye, Yuntian Gu
Robust Universal Adversarial Perturbations
Changming Xu, Gagandeep Singh