Corruption Robustness

Follow this topic Ask about this topic

It asks whether models and algorithms can still estimate, predict, or act reliably when inputs, labels, measurements, or feedback are missing, noisy, or deliberately altered. Common approaches include robust estimators and losses, corrupted-example filtering, robust aggregation, corruption-aware training, test-time adaptation, and algorithms with explicit corruption budgets. Evaluation uses controlled and real-world corruption benchmarks, measuring confidence and downstream reliability as well as accuracy across corruption types and severities. A central challenge is that defenses often depend on the corruption and data-coverage assumptions: adaptation can fail on unseen shifts, while stronger guarantees may require more computation or sacrifice clean-data performance.

Latest papers

50 papers3 papers in the last four weeks, against 2 the four weeks before. 0.0% of all new papers.

Sparse Recovery Bird's-Eye View Model Soup for Robust Camera-Based 3D Object Detection
Oct 26, 2026Jinwoo Chung, Sangho An, Hyunsung Park +1Corruption Robustness 3D Object Detection
Kookmin University, Seoul, Republic of Korea · Hyundai Motor Company · Corresponding author: Jangho Kim
Certified Corruption Budgets: Anytime-Valid Leaderboard Claims under Adaptive Rigging
Oct 6, 2026Hamed Khosravi, Xiaoming HuoCorruption Robustness Anytime-Valid Inference
H. Milton Stewart School of Industrial and Systems Engineering Georgia Institute of Technology, Atlanta, GA, USA
Vmem- $\varphi$ : Low-Compute Out-of-Distribution Detection in Spiking Neural Networks from Membrane-Potential Statistics
Sep 29, 2026Arul Rana, Agrim Tripathi, Shoaib Ahmed Dipu +3OOD Detection Spiking Neural Networks
Indian Institute of Technology Kharagpur · Indiana University Indianapolis · Bangladesh University of Engineering and Technology +1
Corruption-Robust Sparse Linear Contextual Bandits with Knapsack Constraints
Sep 29, 2026Yige Wang, Hanyang Li, Yiming Zong +2Contextual Bandits Linear Contextual Bandits
Department of Industrial Engineering and Decision Analytics, The Hong Kong University of Science and Technology · Department of Statistics and Data Science, The Wharton School, University of Pennsylvania
Toward Robust LiDAR Semantic Segmentation for Real-World Deployment: Evaluation under Coarse Labels, Adverse Conditions, and Domain Shifts
Sep 2, 2026Samir Abou Haidar, Alexandre Chariot, Mehdi Darouich +2Fine-Grained Semantic Segmentation Semantic Segmentation
Mines Paris, PSL University, Centre for Robotics (CAOR), 75006 Paris, France · Paris-Saclay University, CEA, List, F-91120, Palaiseau, France
Median-of-Means as an Extremal Convex Estimator and a Nonconvex Route to the Trimmed Oracle
Sep 1, 2026Angshul MajumdarNonconvex Optimization Robust Mean Estimation
Department of Electronics and Communications Engineering, IIIT Delhi, India
Continual Test-Time Adaptation via Entropy Sensitivity-Guidance in Strict Online Setting
Aug 30, 2026Chandler Timm C. Doloriel, Yunbei Zhang, Muhammad Salman Siddiqui +4Distribution Shift Robustness Test-Time Adaptation
Faculty of Science and Technology (REALTEK), Norwegian University of Life Sciences (NMBU) · Tulane University
ByteAction: Byte-space Action Recognition Foundation Model
Aug 24, 2026Fangcheng Li, Zhen Yu, Kejun Wu +2Corruption Robustness Visual Representation Learning
School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan, 430074, China
When Test-Time Adaptation Helps, Harms, or Becomes Inactive: A Condition-Level Study on CIFAR-10-C
Aug 23, 2026Sreeja Guha Majumdar, Aratrika SahaTest-Time Adaptation Corruption Robustness
Heritage Institute of Technology Kolkata, West Bengal, India
Accuracy and Robustness of Model Cascades Under Data Perturbations
Aug 18, 2026Pallavi Mitra, Jai Kushwaha, Felix BiessmannCost-Aware Inference Efficient Neural Network Inference
AUMOVIO AI Lab, Berlin, Germany · Berliner Hochschule für Technik, Berlin, Germany
Bitstream Action Recognition is Byte Modeling
Aug 16, 2026Fangcheng Li, Chaoran Huang, Tianyi Liu +5Video Action Recognition Corruption Robustness
School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan 430074, China · School of Electrical and Electronics Engineering, Nanyang Technological University, Singapore · VI Department, Institute for Infocomm Research, Agency for Science, Technology and Research (A*STAR), Singapore
Relational Response Fields: A General Theory of Black-Box LLM Response Consistency and Recovery
Aug 5, 2026Song ZichenLLM Reliability Corruption Robustness
Sungkyunkwan University
Robustness Emerges Early in Training Dynamics, but Is Not Preserved
Aug 5, 2026Jiangang Yang, Wenhui Shi, Lu Hu +2Distribution Shift Robustness Representation Learning
Institute of Microelectronics, Chinese Academy of Sciences, Beijing, China · University of Chinese Academy of Sciences, Beijing, China
RSC-GestureNet: Reliability-Aware Selective Causal Recognition of Chinese Traffic Police Gestures
Aug 3, 2026Cheng Li, Renjun Gao, Boyi FuSelective Prediction Autonomous Driving Perception
Academy of Interdisciplinary Studies, The Hong Kong University of Science and Technology, Hong Kong SAR, China · Faculty of Innovation Engineering, Macau University of Science and Technology, Macao SAR, China
Robust Asynchronous Q-Learning under Reward and State Corruption via Batching
Jul 23, 2026Sreejeet Maity, Aritra MitraAsynchronous RL Q-Learning
Department of Electrical and Computer Engineering, North Carolina State University.
Barnamala: Parameter-Efficient Handwritten Devanagari Recognition at Benchmark Saturation
Jul 15, 2026Ashish Thapa, Samrat KarkiCorruption Robustness Convolutional Neural Networks
Ampixa Labs · Pulchowk Campus
Active Learning on Adversarially Corrupted Graphs
Jul 6, 2026Marco Bressan, Nicolò Cesa-Bianchi, Tommaso d`Orsi +2Adversarial Attacks Active Learning
Università degli Studi di Milano, Italy · Bocconi University, Italy · Google Research
Exogenous Dropout: A Simple, Strong Baseline for Corruption-Robust Time Series Forecasting with Covariates
Jul 5, 2026Hao Hu, Xue-shan AiNeural Network Robustness Time Series Forecasting
State Key Laboratory of Water Resources Engineering and Management, Wuhan University, Wuhan 430072, China · Hubei Key Laboratory of Water System Science for Sponge City Construction (Wuhan University), Wuhan 430072, China
Burst Spiking Neural Networks
Jul 5, 2026Jiahong Zhang, Sijun Shen, Man Yao +5Distribution Shift Robustness Neural Network Robustness
Institute of Automation, Chinese Academy of Sciences, Beijing 100045, China · School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing 100049, China · State Key Laboratory of Media Convergence and Communication, Communication University of China, Beijing 100024, China +3
When Token Compression Breaks: Structural Pruning vs. Token Reduction for Robust ViT Segmentation under High Compression
Jul 2, 2026Tien-Phat Nguyen, Ngai-Man CheungDistribution Shift Robustness Vision Transformer
Temasek Laboratories, Singapore University of Technology and Design, Singapore
Fixed-Set Robustness in Programming by Example: Example Corruption and Semantic Partition Recovery
Jul 1, 2026Yuan Si, Jialu ZhangAdversarial Robustness Program Synthesis
University of Waterloo, Waterloo, Canada
RoPoLL: Robust Panel of LLM Judges
Jun 29, 2026Anish Acharya, Kris W Pan, Brian VerkhovskyLLM Evaluation LLM-as-a-Judge
Amazon Web Services
How Robust is OCR-Reasoning? Evaluating OCR-Reasoning Robustness of Vision-Language Models under Visual Perturbations
Jun 24, 2026Yuxing Cheng, Yuan Wu, Yi ChangVLM Evaluation VLM Robustness
School of Artificial Intelligence, Jilin University · Engineering Research Center of Knowledge-Driven Human-Machine Intelligence, MOE, China · International Center of Future Science, Jilin University
Sum-of-Squares Degree Barriers for the Reweighted-Hinge Method in Robust Halfspace Learning: A Christoffel-Function Characterization
Jun 15, 2026Xiaoyu LiCorruption Robustness Noise Robustness
University of New South Wales
Neural Bayesian Anomaly Mitigation: A Robust Loss that Doubles as an Unsupervised Contamination Classifier
Jun 15, 2026S. A. K. Leeney, W. J. Handley, H. T. J. Bevins +1Neural Network Robustness Noisy-Label Learning
Astrophysics Group, Cavendish Laboratory University of Cambridge · Institute of Astronomy University of Cambridge
Neural Variability Enhances Artificial Network Robustness
Jun 11, 2026Robin Preble, Praveen Venkatesh, Stefan Mihalas +1Distribution Shift Robustness Neural Network Robustness
Department of Computer Science, Western Washington University, Bellingham, WA 98225 · Allen Institute, Seattle, WA 98195
Neural networks become centroid classifiers when trained on heavily corrupted inputs
Jun 9, 2026Justin Tahmassebpur, Asadullah Bhuiyan, Hyejin Kim +1Neural Network Generalization Multilayer Perceptrons
Department of Applied and Engineering Physics, Cornell University, Ithaca, NY 14853, USA · Department of Physics, Cornell University, Ithaca, NY 14853, USA
Low-Frequency Shortcuts in Texture-Driven Visual Learning
Jun 2, 2026Utku Şirin, Cathy Hou, David Alvarez-Melis +1Distribution Shift Robustness Frequency-Domain Feature Learning
Harvard University
FlagGAM: Rule-Basis Generalized Additive Models for Explainable Tabular Prediction
May 29, 2026Zijie Zhao, Roy E. WelschInterpretable ML Corruption Robustness
EECS Department, Massachusetts Institute of Technology, Cambridge, MA, USA · Sloan School of Management, Massachusetts Institute of Technology, Cambridge, MA, USA
Convex Basins in Single-Index Model Loss Landscapes: Applications to Robust Recovery under Strong Adversarial Corruption
May 28, 2026Santanu Das, Sagnik Chatterjee, Jatin BatraSingle-Index Models Adversarial Robustness
School of Technology and Computer Science, Tata Institute of Fundamental Research, Mumbai, India.

Oct 26, 2026J/K move · Enter open · S save

Sparse Recovery Bird's-Eye View Model Soup for Robust Camera-Based 3D Object Detection

Jinwoo Chung, Sangho An, Hyunsung Park, Jangho Kim

Kookmin University, Seoul, Republic of Korea · Hyundai Motor Company · Corresponding author: Jangho Kim

Corruption Robustness 3D Object Detection Bird's-Eye-View Representation

Open paper AskPDF arXiv

Camera-based bird's-eye view (BEV) perception methods such as Fast-BEV have demonstrated promising results with fast inference speed and competitive accuracy. However, their robustness to real-world corruptions remains insufficiently explored, posing risks for autonomous driving deployment where environmental variations are inevitable. In this paper, we propose Sparse Recovery Bird's-Eye View Model Soup (SR-BEVS), a sparse recovery learning approach that simultaneously improves clean accuracy and corruption robustness without requiring additional data or architectural modifications. Our method identifies pruning candidates based on layer-wise weight magnitudes, applies random pruning to create diverse sparse models, and retrains each model with a randomly sampled learning rate. By averaging these diverse recovered models into a single dense model, we achieve enhanced robustness against various corruptions while introducing zero inference overhead. We further provide a mode connectivity analysis demonstrating that our pruning-based diversification preserves the connected low-loss basin necessary for stable weight averaging. Experiments on the nuScenes dataset demonstrate up to 33.8% improvement in corruption robustness and a 1.8% gain in clean accuracy over the Fast-BEV baseline, with consistent improvements across sensor noise, weather distortions, and illumination changes. Our simple yet effective approach may be applicable to other BEV models.