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
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
ERAS: Evaluating the Robustness of Chinese NLP Models to Morphological Garden Path Errors
Qinchan Li, Sophie Hao
New Paradigm of Adversarial Training: Breaking Inherent Trade-Off between Accuracy and Robustness via Dummy Classes
Yanyun Wang, Li Liu, Zi Liang, Qingqing Ye, Haibo Hu
TPFL: A Trustworthy Personalized Federated Learning Framework via Subjective Logic
Jinqian Chen, Jihua Zhu
One Language, Many Gaps: Evaluating Dialect Fairness and Robustness of Large Language Models in Reasoning Tasks
Fangru Lin, Shaoguang Mao, Emanuele La Malfa, Valentin Hofmann, Adrian de Wynter, Jing Yao, Si-Qing Chen, Michael Wooldridge, Furu Wei
Adversarially Robust Out-of-Distribution Detection Using Lyapunov-Stabilized Embeddings
Hossein Mirzaei, Mackenzie W. Mathis
Feature Averaging: An Implicit Bias of Gradient Descent Leading to Non-Robustness in Neural Networks
Binghui Li, Zhixuan Pan, Kaifeng Lyu, Jian Li
Generative Deep Learning and Signal Processing for Data Augmentation of Cardiac Auscultation Signals: Improving Model Robustness Using Synthetic Audio
Leigh Abbott, Milan Marocchi, Matthew Fynn, Yue Rong, Sven Nordholm