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
ImageNet-RIB Benchmark: Large Pre-Training Datasets Don't Guarantee Robustness after Fine-Tuning
Jaedong Hwang, Brian Cheung, Zhang-Wei Hong, Akhilan Boopathy, Pulkit Agrawal, Ila Fiete
Robustness and Generalization in Quantum Reinforcement Learning via Lipschitz Regularization
Nico Meyer, Julian Berberich, Christopher Mutschler, Daniel D. Scherer
Evaluating the Robustness of LiDAR Point Cloud Tracking Against Adversarial Attack
Shengjing Tian, Yinan Han, Xiantong Zhao, Bin Liu, Xiuping Liu
Towards Trustworthy Machine Learning in Production: An Overview of the Robustness in MLOps Approach
Firas Bayram, Bestoun S. Ahmed
Beyond Interpretability: The Gains of Feature Monosemanticity on Model Robustness
Qi Zhang, Yifei Wang, Jingyi Cui, Xiang Pan, Qi Lei, Stefanie Jegelka, Yisen Wang
Integrating uncertainty quantification into randomized smoothing based robustness guarantees
Sina Däubener, Kira Maag, David Krueger, Asja Fischer
Towards Robust Out-of-Distribution Generalization: Data Augmentation and Neural Architecture Search Approaches
Haoyue Bai
RobustKV: Defending Large Language Models against Jailbreak Attacks via KV Eviction
Tanqiu Jiang, Zian Wang, Jiacheng Liang, Changjiang Li, Yuhui Wang, Ting Wang
Considerations for Distribution Shift Robustness of Diagnostic Models in Healthcare
Arno Blaas, Adam Goliński, Andrew Miller, Luca Zappella, Jörn-Henrik Jacobsen, Christina Heinze-Deml