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 - Page 3
Robust Conformal Prediction with a Single Binary Certificate
Soroush H. Zargarbashi, Aleksandar BojchevskiCISPA Helmholtz Center for Information Security●University of CologneRobustness of Generalized Median Computation for Consensus Learning in Arbitrary Spaces
Andreas Nienkötter, Sandro Vega-Pons, Xiaoyi JiangSichuan University-Hongkong Polytechnic University●Lake Worth●University of M¨ unsterAdaptive-LIO: Enhancing Robustness and Precision through Environmental Adaptation in LiDAR Inertial Odometry
Chengwei Zhao, Kun Hu, Jie Xu, Lijun Zhao, Baiwen Han, Kaidi Wu, Maoshan Tian, Shenghai YuanHarbin Institute of Technology●Hangzhou Qisheng Intelligent Techology Co. Ltd.●China University of Mining and Technology●Nanyang...+2
Benchmarking Reasoning Robustness in Large Language Models
Tong Yu, Yongcheng Jing, Xikun Zhang, Wentao Jiang, Wenjie Wu, Yingjie Wang, Wenbin Hu, Bo Du, Dacheng TaoKnow Thy Judge: On the Robustness Meta-Evaluation of LLM Safety Judges
Francisco Eiras, Eliott Zemour, Eric Lin, Vaikkunth MugunthanDynamo AI
Towards Trustworthy Federated Learning
Alina Basharat, Yijun Bian, Ping Xu, Zhi TianUniversity of Texas Rio Grande Valley●University of Copenhagen●George Mason UniversityWhen Claims Evolve: Evaluating and Enhancing the Robustness of Embedding Models Against Misinformation Edits
Jabez Magomere, Emanuele La Malfa, Manuel Tonneau, Ashkan Kazemi, Scott HaleUniversity of Oxford●Alan Turing Institute●World Bank●Meedan
A Guide to Failure in Machine Learning: Reliability and Robustness from Foundations to Practice
Eric Heim, Oren Wright, David ShriverCarnegie Mellon UniversityUnstable Grounds for Beautiful Trees? Testing the Robustness of Concept Translations in the Compilation of Multilingual Wordlists
David Snee, Luca Ciucci, Arne Rubehn, Kellen Parker van Dam, Johann-Mattis ListUniversity of Passau
In-Model Merging for Enhancing the Robustness of Medical Imaging Classification Models
Hu Wang, Ibrahim Almakky, Congbo Ma, Numan Saeed, Mohammad YaqubMohamed bin Zayed University of Artificial Intelligence●New York University Abu DhabiTraining Robust Graph Neural Networks by Modeling Noise Dependencies
Yeonjun In, Kanghoon Yoon, Sukwon Yun, Kibum Kim, Sungchul Kim, Chanyoung ParkKAIST●UNC Chapel Hill●Adobe Research
The Mighty ToRR: A Benchmark for Table Reasoning and Robustness
Shir Ashury-Tahan, Yifan Mai, Rajmohan C, Ariel Gera, Yotam Perlitz, Asaf Yehudai, Elron Bandel, Leshem Choshen, Eyal Shnarch, Percy Liang+1IBM Research●Bar-Ilan University●Stanford University●MITInvariance Pair-Guided Learning: Enhancing Robustness in Neural Networks
Martin Surner, Abdelmajid Khelil, Ludwig BothmannLandshut University of Applied Sciences●LMU Munich●Munich Center for Machine Learning (MCML)
Robust Federated Learning with Global Sensitivity Estimation for Financial Risk Management
Lei Zhao, Lin Cai, Wu-Sheng LuUniversity of VictoriaImproved Diffusion-based Generative Model with Better Adversarial Robustness
Zekun Wang, Mingyang Yi, Shuchen Xue, Zhenguo Li, Ming Liu, Bing Qin, Zhi-Ming MaHarbin Institute of Technology●Renmin University of China●Academy of Mathematics and Systems Science●University of Chinese Academy of...+2