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
Certified Robust Control under Adversarial Perturbations
Jinghan Yang, Hunmin Kim, Wenbin Wan, Naira Hovakimyan, Yevgeniy Vorobeychik
How Many and Which Training Points Would Need to be Removed to Flip this Prediction?
Jinghan Yang, Sarthak Jain, Byron C. Wallace
Interpolation for Robust Learning: Data Augmentation on Wasserstein Geodesics
Jiacheng Zhu, Jielin Qiu, Aritra Guha, Zhuolin Yang, Xuanlong Nguyen, Bo Li, Ding Zhao
Rating Sentiment Analysis Systems for Bias through a Causal Lens
Kausik Lakkaraju, Biplav Srivastava, Marco Valtorta
From Robustness to Privacy and Back
Hilal Asi, Jonathan Ullman, Lydia Zakynthinou
Revisiting Personalized Federated Learning: Robustness Against Backdoor Attacks
Zeyu Qin, Liuyi Yao, Daoyuan Chen, Yaliang Li, Bolin Ding, Minhao Cheng
Beyond the Universal Law of Robustness: Sharper Laws for Random Features and Neural Tangent Kernels
Simone Bombari, Shayan Kiyani, Marco Mondelli
Effective Robustness against Natural Distribution Shifts for Models with Different Training Data
Zhouxing Shi, Nicholas Carlini, Ananth Balashankar, Ludwig Schmidt, Cho-Jui Hsieh, Alex Beutel, Yao Qin
On the Robustness of Randomized Ensembles to Adversarial Perturbations
Hassan Dbouk, Naresh R. Shanbhag