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
Improving Mapper's Robustness by Varying Resolution According to Lens-Space Density
Kaleb D. Ruscitti, Leland McInnes
Knowledge-Augmented Reasoning for EUAIA Compliance and Adversarial Robustness of LLMs
Tomas Bueno Momcilovic, Dian Balta, Beat Buesser, Giulio Zizzo, Mark Purcell
Make Interval Bound Propagation great again
Patryk Krukowski, Daniel Wilczak, Jacek Tabor, Anna Bielawska, Przemysław Spurek
FedCert: Federated Accuracy Certification
Minh Hieu Nguyen, Huu Tien Nguyen, Trung Thanh Nguyen, Manh Duong Nguyen, Trong Nghia Hoang, Truong Thao Nguyen, Phi Le Nguyen
Learning-Augmented Robust Algorithmic Recourse
Kshitij Kayastha, Vasilis Gkatzelis, Shahin Jabbari
Toward a Holistic Evaluation of Robustness in CLIP Models
Weijie Tu, Weijian Deng, Tom Gedeon
On the Robustness of Machine Learning Models in Predicting Thermodynamic Properties: a Case of Searching for New Quasicrystal Approximants
Fedor S. Avilov, Roman A. Eremin, Semen A. Budennyy, Innokentiy S. Humonen
Efficient PAC Learning of Halfspaces with Constant Malicious Noise Rate
Jie Shen, Xiaoyu Li
EndoDepth: A Benchmark for Assessing Robustness in Endoscopic Depth Prediction
Ivan Reyes-Amezcua, Ricardo Espinosa, Christian Daul, Gilberto Ochoa-Ruiz, Andres Mendez-Vazquez
SATA: Spatial Autocorrelation Token Analysis for Enhancing the Robustness of Vision Transformers
Nick Nikzad, Yi Liao, Yongsheng Gao, Jun Zhou