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
Deep Active Learning for Scientific Computing in the Wild
Simiao Ren, Yang Deng, Willie J. Padilla, Leslie Collins, Jordan Malof
The Impacts of Unanswerable Questions on the Robustness of Machine Reading Comprehension Models
Son Quoc Tran, Phong Nguyen-Thuan Do, Uyen Le, Matt Kretchmar
Interpreting Robustness Proofs of Deep Neural Networks
Debangshu Banerjee, Avaljot Singh, Gagandeep Singh
Are Defenses for Graph Neural Networks Robust?
Felix Mujkanovic, Simon Geisler, Stephan Günnemann, Aleksandar Bojchevski
Learning Against Distributional Uncertainty: On the Trade-off Between Robustness and Specificity
Shixiong Wang, Haowei Wang, Jean Honorio
Robust Linear Regression: Gradient-descent, Early-stopping, and Beyond
Meyer Scetbon, Elvis Dohmatob
Optimal Transport Perturbations for Safe Reinforcement Learning with Robustness Guarantees
James Queeney, Erhan Can Ozcan, Ioannis Ch. Paschalidis, Christos G. Cassandras
Benchmarking Robustness to Adversarial Image Obfuscations
Florian Stimberg, Ayan Chakrabarti, Chun-Ta Lu, Hussein Hazimeh, Otilia Stretcu, Wei Qiao, Yintao Liu, Merve Kaya, Cyrus Rashtchian, Ariel Fuxman, Mehmet Tek, Sven Gowal
On Robustness of Prompt-based Semantic Parsing with Large Pre-trained Language Model: An Empirical Study on Codex
Terry Yue Zhuo, Zhuang Li, Yujin Huang, Fatemeh Shiri, Weiqing Wang, Gholamreza Haffari, Yuan-Fang Li
Red teaming ChatGPT via Jailbreaking: Bias, Robustness, Reliability and Toxicity
Terry Yue Zhuo, Yujin Huang, Chunyang Chen, Zhenchang Xing