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
A Multi-module Robust Method for Transient Stability Assessment against False Label Injection Cyberattacks
Hanxuan Wang, Na Lu, Yinhong Liu, Zhuqing Wang, Zixuan Wang
Boosting Robustness in Preference-Based Reinforcement Learning with Dynamic Sparsity
Calarina Muslimani, Bram Grooten, Deepak Ranganatha Sastry Mamillapalli, Mykola Pechenizkiy, Decebal Constantin Mocanu, Matthew E. Taylor
MeanSparse: Post-Training Robustness Enhancement Through Mean-Centered Feature Sparsification
Sajjad Amini, Mohammadreza Teymoorianfard, Shiqing Ma, Amir Houmansadr
Certified Robustness to Data Poisoning in Gradient-Based Training
Philip Sosnin, Mark N. Müller, Maximilian Baader, Calvin Tsay, Matthew Wicker
Contextual fusion enhances robustness to image blurring
Shruti Joshi, Aiswarya Akumalla, Seth Haney, Maxim Bazhenov
Compositional Curvature Bounds for Deep Neural Networks
Taha Entesari, Sina Sharifi, Mahyar Fazlyab
Robust Reward Design for Markov Decision Processes
Shuo Wu, Haoxiang Ma, Jie Fu, Shuo Han
Clarifying Myths About the Relationship Between Shape Bias, Accuracy, and Robustness
Zahra Golpayegani, Patrick St-Amant, Nizar Bouguila
The Price of Implicit Bias in Adversarially Robust Generalization
Nikolaos Tsilivis, Natalie Frank, Nathan Srebro, Julia Kempe
URGENT Challenge: Universality, Robustness, and Generalizability For Speech Enhancement
Wangyou Zhang, Robin Scheibler, Kohei Saijo, Samuele Cornell, Chenda Li, Zhaoheng Ni, Anurag Kumar, Jan Pirklbauer, Marvin Sach, Shinji Watanabe, Tim Fingscheidt, Yanmin Qian
Helpful or Harmful Data? Fine-tuning-free Shapley Attribution for Explaining Language Model Predictions
Jingtan Wang, Xiaoqiang Lin, Rui Qiao, Chuan-Sheng Foo, Bryan Kian Hsiang Low
To Distill or Not to Distill? On the Robustness of Robust Knowledge Distillation
Abdul Waheed, Karima Kadaoui, Muhammad Abdul-Mageed
Improving Alignment and Robustness with Circuit Breakers
Andy Zou, Long Phan, Justin Wang, Derek Duenas, Maxwell Lin, Maksym Andriushchenko, Rowan Wang, Zico Kolter, Matt Fredrikson, Dan Hendrycks
Evaluating Durability: Benchmark Insights into Multimodal Watermarking
Jielin Qiu, William Han, Xuandong Zhao, Shangbang Long, Christos Faloutsos, Lei Li
Fine-Grained Causal Dynamics Learning with Quantization for Improving Robustness in Reinforcement Learning
Inwoo Hwang, Yunhyeok Kwak, Suhyung Choi, Byoung-Tak Zhang, Sanghack Lee
Unveiling Selection Biases: Exploring Order and Token Sensitivity in Large Language Models
Sheng-Lun Wei, Cheng-Kuang Wu, Hen-Hsen Huang, Hsin-Hsi Chen
Exploring Robustness in Doctor-Patient Conversation Summarization: An Analysis of Out-of-Domain SOAP Notes
Yu-Wen Chen, Julia Hirschberg