Adversarial Corruption

Ask about this topic

Momentum

9 papers in the last four weeks, up 200% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28
View on map

Latest papers 58

All topics
CardsList

  1. Graph Residual Conjugate Diffusion: SNR-Equalized Heat Flow for Graph Signals

    Sep 30, 2026Jinwei Li, Daniel TenbrinckResidual Conditional Diffusion ModelGraph Edge Sparsification

    Department of Data Science Friedrich-Alexander-Universität Erlangen-Nürnberg Erlangen, Germany

  2. Does This Action Still Explain the Task? Reverse Scoring for Diffusion Language Model Agents

    Sep 29, 2026Jiacheng Qiu, Christopher E. Mower, Jan Peters +2Large Language Model AgentsAgentic

    Huawei Noah’s Ark Lab · Technical University of Darmstadt · UCL Centre for AI

  3. Spontaneous Context Restoration: How Language Models Recover from Corrupted Inputs

    Sep 28, 2026Pranjal Garg, Jacob BeckCorrupted InputsLanguage Model Computes

    Independent Researcher

  4. Learning to Re-Draft: A Variational Stackelberg Game for Discrete Diffusion

    Sep 28, 2026Dmitrii Moor, Federico Tomasi, Paul N. Bennett +2Masked Diffusion Language ModelsDiffusion Dynamics

    Spotify, London, UK · Spotify, Boston, USA · Spotify, New York, USA

  5. Certified Multi-Source Integrity for Structured Agent Actions

    Sep 28, 2026Anmol Pandey, Aditya Jain, Liang Chen +2IntegrityOn-Chain Attestations

    University of Warwick · University of Hertfordshire

  6. ODPure: Backdoor Purification for Object Detection via Ensemble Corruption Consensus

    Sep 23, 2026Li Zeng, Mingcheng Duan, Longfei Fan +5Object DetectionAdversarial Corruption

    School of Computer and Communication Engineering, Changsha University of Science & Technology, Changsha 410114, China · School of Computer Science, Xiangtan University, Xiangtan 411105, China · School of Software, Yunnan University, Kunming 650500, China +3

  7. Median Temporal Ensembling: Training-Free Robust Aggregation for Action-Chunked Visuomotor Policies

    Sep 22, 2026Yuhang JiangVisuomotor PolicyAdversarial Corruption

    University of Trento, Italy

  8. DCRA: Diffusion-Conditioned Representation Alignment for Robust Time-Series Learning

    Sep 14, 2026Wenrui Xu, Anas Enanaa, Keshab K. ParhiSeizure DetectionRepresentation Learning

    University of Minnesota, Twin Cities

  9. In RAG We Trust? Measuring Robustness of Retrieval-Augmented Generation Under Document Poisoning

    Sep 10, 2026Iliano FasolinoAgentic Retrieval-Augmented Generation SystemsLarge Language Model Reliability

    Department of Computer Science University of Milan Milan, Italy

  10. Sensing Which Modality Matters: Evidence-Gated Regularization for Robust VLA Policies

    Sep 2, 2026Yue Yang, Diego Romeres, Chiori Hori +3Sensory FeedbackModalities

    Department of Computer Science, University of North Carolina at Chapel Hill · 2Mitsubishi Electric Research Laboratories (MERL)

  11. Failure or Drift? Evaluating Monocular SLAM under Synthetic and Real-World Corruptions

    Aug 31, 2026Abhay Skaria Thomas, Shashank Agnihotri, Margret KeuperOrb-Slam2Simultaneous Localization And Mapping

    Machine Learning Group, University of Mannheim, Germany · Max-Planck-Institute for Informatics, Saarland Informatics Campus, Germany

  12. Beyond Decision Boundaries: Relational Geometry Attacks on Contrastive Embedding Manifolds

    Aug 10, 2026Fei Zhao, Peiyuan Zhang, Xi Li +2Black-Box Adversarial AttacksContrastive Learning

    The University of Alabama at Birmingham, Birmingham, USA · Texas A&M University, College Station, USA

  13. BRUCE: Benchmarking Robustness Under Corruption Escalation for Scientific Vision-Language Reasoning

    Aug 7, 2026Saim Rehman, Muhammad ShafiqueMultimodal Reasoning BenchmarksMultimodal Reasoning

    eBRAIN Lab New York University Abu Dhabi (NYUAD) Abu Dhabi, United Arab Emirates

  14. Suppress and Diversify: Refining Robust Pathways for Corruption Robustness

    Aug 7, 2026Jiangang Yang, Wenhui Shi, Xiaoran Xu +4Robustness VerificationAdversarial Corruption

    Institute of Microelectronics, Chinese Academy of Sciences, Beijing, China · University of Chinese Science, Beijing, China

  15. Unmasking Removal-Budget Confounding: A Matched Operating-Point Evaluation Framework for Adaptive Data Cleaning

    Aug 6, 2026Wei-Hsiang Chen, Pin-Hsuan Yu, Chen-Hsuan Fang +1Adversarial CorruptionClear

    Department of Electrical Engineering, National Taiwan Ocean Univ., Keelung City, Taiwan · AI Research Center, National Taiwan Ocean Univ., Keelung City, Taiwan.

  16. Combating Knowledge Corruption in Agent Systems: A Byzantine-Tolerant Secure Collaborative RAG Framework

    Aug 5, 2026Zhaoqi Wang, Daqing He, Zijian Zhang +13Agentic Retrieval-Augmented Generation SystemsAdversarial Corruption

    Beijing Institute of Technology, Beijing, China

  17. ReLATE: Reliability-Guided Evidence Fusion for Robust UAV--Satellite cross-view Geo-Localization

    Jul 28, 2026Haochen Jiang, Jialei Pan, Yuzhe Sun +4Drone-View Geo-LocalizationSatellite Data

    School of Electronics and Information Engineering, Harbin Institute of Technology, Harbin 150001, China · National Key Laboratory of Radar Detection and Sensing, Nanjing Research Institute of Electronics Technology, Nanjing 210039, China · School of Electrical and Electronic Engineering, University of Manchester, Manchester M13 9PL, United Kingdom

  18. UNIFUSION: Adapting Autoregressive Language Models into Discrete Diffusion under a Unified Reverse-Rate Objective

    Jul 27, 2026Xiaoyi Jiang, Jingyuan Li, Yixuan Jiang +4Autoregressive Language ModelsAutoregressive Model

    Tsinghua University · MathonAI · Beijing Institute of Mathematical Sciences and Applications +1

  19. TriShieldRAG: A Three-Ring Defense-in-Depth Framework Against Knowledge Corruption in Retrieval-Augmented Generation

    Jul 26, 2026Susil Kumar Mohanty, Rohit Patel, Kosuru Yuvaraj +2Agentic Retrieval-Augmented Generation SystemsPoisoning

    Department of Computer Science and Engineering, Indian Institute of Technology Jodhpur, Jodhpur, India

  20. Robust Asynchronous Q-Learning under Reward and State Corruption via Batching

    Jul 23, 2026Sreejeet Maity, Aritra MitraQ-LearningAdversarial Corruption

    Department of Electrical and Computer Engineering, North Carolina State University.

  21. MotifRole-Diff: Risk-Optimal Role-Aware Corruption for Masked Molecular Graph Diffusion

    Jul 20, 2026Tasfia Nuzhat Ornee, Elias Hossain, Ivan Garibay +1Physics-Guided DiffusionMasked Diffusion Language Models

    University of Central Florida

  22. Barnamala: Parameter-Efficient Handwritten Devanagari Recognition at Benchmark Saturation

    Jul 15, 2026Ashish Thapa, Samrat KarkiHandwritten Text RecognitionConvolutional Neural Networks

    Ampixa Labs · Pulchowk Campus

  23. ChartGenEval: Corruption-Tested Multi-Dimensional Feedback for Rhythm-Game Chart Generation

    Jul 14, 2026Jhen-Ke LinMelodyStress Testing

    National Yang Ming Chiao Tung University

  24. Gauge dependence and structured-output corruption in sign-branched repetition penalties: measurements across models, inference stacks, and alternative repetition controls

    Jul 9, 2026Peter HollowsLogit LensRepetition

  25. The Blind Curator: How a Biased Judge Silently Disables Skill Retirement in Self-Evolving Agents

    Jul 8, 2026Xing Zhang, Yanwei Cui, Guanghui Wang +4Self-Evolving AgentsJudges

    1AWS Generative AI Innovation Center · 2HSBC Holdings Plc., HSBC Technology Center, China

  26. Assessing VLM Reliability for Medical Image Quality Evaluation Under Corruption and Bias

    Jul 2, 2026Sofiane Ouaari, Kevin Vorwalder, Nico PfeiferVision-Language Foundation ModelsAdversarial Corruption

    Methods in Medical Informatics, Department of Computer Science, University of Tuebingen, Germany. · Institute for Bioinformatics and Medical Informatics (IBMI), University of Tuebingen, Germany.

  27. Fixed-Set Robustness in Programming by Example: Example Corruption and Semantic Partition Recovery

    Jul 1, 2026Yuan Si, Jialu ZhangAutomated Program RepairCorrupted Inputs

    University of Waterloo, Waterloo, Canada

  28. RoPoLL: Robust Panel of LLM Judges

    Jun 29, 2026Anish Acharya, Kris W Pan, Brian VerkhovskyLlm-As-A-JudgeLarge Language Model Judges

    Amazon Web Services

  29. Online Distributional Prediction via Latent Cluster Geometry Under Drift and Corruption

    Jun 17, 2026Navyansh Mahla, Prateek Chanda, Ganesh RamakrishnanLearning-Augmented AlgorithmsPosterior Predictive Distribution

    Indian Institute of Technology, Bombay

  30. Comparison Patrols on Drifting Orders: Certified Rank Maintenance, Evolving Planar Maxima, and Selection under Drifting Fitness

    Jun 12, 2026Faruk Alpay, Levent SariogluUpper BoundsOrder

    Department of Computer Engineering, Bahçeşehir University, Istanbul, Turkey

  31. Analyzing Training-Free Corruption Detection for Object Detection Datasets

    Jun 9, 2026Christian Sieberichs, Simon Geerkens, Thomas Waschulzik +2Object DetectionBounding Box

    University of Applied Sciences Düsseldorf · Siemens Mobility GmbH · Goethe University Frankfurt

  32. A Systems-Level Analysis of Sensitivity, Robustness, and Stability in Retrieval-Augmented Generation

    May 29, 2026Bharath Simha Reddy MuthyamAgentic Retrieval-Augmented Generation SystemsAdversarial Corruption

    Independent Researcher

  33. MarginGate: Sparse Margin-Triggered Verification for Batch-Invariant LLM Inference

    May 28, 2026Kexin Chu, Yang Zhou, Wei ZhangLLM Inference OptimizationDecoding

    University of Connecticut · UC Davis

  34. COD10K-C: Benchmarking Robustness of Camouflaged Object Detection Under Natural Image Corruptions

    May 23, 2026Arafat Hossain SayemCamouflaged Object DetectionObject Detection

  35. Characterizing the Fault Response of the Intel Neural Compute Stick 2 Under Single-Pulse Electromagnetic Fault Injection

    May 21, 2026Štefan Kučerák, Jakub Breier, Xiaolu HouReal-World Cloud Fault Injection DatasetNeural Network Inference

    Faculty of Informatics and Information Technologies, Slovak University of Technology, Slovakia · TTControl GmbH, Vienna, Austria · State Key Laboratory of Blockchain and Data Security, Zhejiang University

  36. RADAR: Defending RAG Dynamically against Retrieval Corruption

    May 21, 2026Ziyuan Chen, Yueming Lyu, Yi Liu +4RadarRetrieval-Augmented Generation Pipelines

    School of Intelligence Science and Technology, Nanjing University, Suzhou, China · City University of Hong Kong, Hong Kong, China · Institute of Automation, Chinese Academy of Sciences, Beijing, China

  37. PFlow-T: A Persistence-Driven Forward Process for Topology-Controlled Generation

    May 17, 2026Snigdha Chandan KhilarDiffusion ModelsPersistent Homology

    Independent Researcher

  38. SB-BEVFusion: Enhancing the Robustness against Sensor Malfunction and Corruptions

    May 12, 2026Markus Essl, Marta Moscati, Mubashir Noman +4Multi-Sensor Fusion3D Object Detection

    Johannes Kepler University Linz, Austria · MBZUAI, UAE · Macquarie University, Sydney, Australia +1

  39. Regret Minimization in Bilateral Trade With Perturbed Markets

    May 11, 2026Anna Lunghi, Matteo Castiglioni, Alberto MarchesiMatching MarketsAdversarial Corruption

    Politecnico di Milano

  40. DRIVE-C: A Controlled Corruption Dataset for Autonomous Driving

    May 10, 2026Shiva AherNaturalistic Driving DataAutonomous Driving

    Georgia Institute of Technology, Georgia, United States

  41. \mathsf{VISTA}: Decentralized Machine Learning in Adversary Dominated Environments

    May 8, 2026Hanzaleh Akbari Nodehi, Parsa Moradi, Soheil Mohajer +1Bounded AdversaryAdversarial Robustness

    University of Minnesota

  42. PRA-RAG: Provably Robust Aggregation in Retrieval-Augmented Generation against Retrieval Corruption

    May 8, 2026Xue Tan, Yi Zheng, Chang Huo +7Agentic Retrieval-Augmented Generation SystemsHievi-Rag

    School of Computer Science, Fudan University, Shanghai, China · Institute of Big Data, Fudan University, Shanghai, China · Department of Computer Science, Worcester Polytechnic Institute, MA, USA

  43. Toward Optimal Regret in Robust Pricing: Decoupling Corruption and Time

    May 8, 2026Kalana Kalupahana, Francesco Emanuele Stradi, Matteo Castiglioni +1Dynamic PricingRegret

    Politecnico di Milano

  44. Contrastive Identification and Generation in the Limit

    May 7, 2026Xiaoyu Li, Andi Han, Jiaojiao Jiang +1Contrastive LearningAdversarial Corruption

    University of New South Wales · University of Sydney

  45. The Cost of Context: Mitigating Textual Bias in Multimodal Retrieval-Augmented Generation

    May 7, 2026Hoin Jung, Xiaoqian WangMultimodal Retrieval Augmented GenerationMultimodal Large Language Models

    Elmore Family School of Electrical and Computer Engineering Purdue University West Lafayette, IN 47907

  46. Robust Linear Dueling Bandits with Post-serving Context under Unknown Delays and Adversarial Corruptions

    May 3, 2026Youngmin OhContextual Bandit FrameworkBandits

    InfiniTree, Republic of Korea

  47. Discriminator-Guided Adaptive Diffusion for Source-Free Test-Time Adaptation under Image Corruptions

    Apr 26, 2026Francesco Olivato, Cigdem Beyan, Vittorio MurinoDomain AdaptationCorrupted Inputs

    Department of Computer Science, University of Verona, Verona, Italy · AI for Good (AIGO), Istituto Italiano di Tecnologia, Genova, Italy

  48. Correction and Corruption: A Two-Rate View of Error Flow in LLM Protocols

    Apr 20, 2026Fernando ReitichCorrectnessEvaluation Protocols

    Imens, LLC · Weston, Florida, USA

  49. The Consensus Trap: Rescuing Multi-Agent LLMs from Adversarial Majorities via Token-Level Collaboration

    Apr 18, 2026Jiayuan Liu, Shiyi Du, Weihua Du +2Multi-Agent Large Language Model SystemsCollaboration

    Carnegie Mellon University · Foundations of Cooperative AI Lab (FOCAL) · Adelaide University

  50. Learning to Recorrupt: Noise Distribution Agnostic Self-Supervised Image Denoising

    Mar 26, 2026Brayan Monroy, Jorge Bacca, Julián TachellaNoise-AwareIterative Denoising Methods

    Universidad Industrial de Santander, Colombia · CNRS, ENS de Lyon, France

  51. A Jointly Efficient and Optimal Algorithm for Heteroskedastic Generalized Linear Bandits with Adversarial Corruptions

    Feb 11, 2026Sanghwa Kim, Junghyun Lee, Se-Young YunAdversarial CorruptionMirror Descent

    Kim Jaechul Graduate School of AI, KAIST

  52. Improved Bounds for Private and Robust Alignment

    Dec 29, 2025Wenqian Weng, Yi He, Xingyu ZhouAdversarial CorruptionUpper Bounds

    Department of Electrical and Computer Engineering, Wayne State University, Detroit, USA.

  53. DHAuDS: A Dynamic and Heterogeneous Audio Benchmark for Test-Time Adaptation

    Nov 23, 2025Weichuang Shao, Iman Yi Liao, Tomas Henrique Bode Maul +1Test-Time AdaptationEvaluation Protocols

    School of Computer and Mathematical Sciences, University of Nottingham Malaysia, Semenyih, Malaysia

  54. Robustness to Sparse Adversarial Corruption in Arbitrary Linear Measurements: Beyond Exact Recovery

    Oct 28, 2025Vishal Halder, Alexandre Reiffers-Masson, Abdeldjalil Aïssa-El-Bey +1Tensor CompletionSparsity

    IMT Atlantique, Lab-STICC, CNRS UMR 6285, Brest, France · Department of Computer Science and Automation, Indian Institute of Science, Bengaluru, India

  55. Measuring the Robustness of Audio Deepfake Detection under Real-World Corruption

    Mar 21, 2025Xiang Li, Pin-Yu Chen, Wenqi WeiEnvironmental Sound Deepfake DetectionAudio Deepfake Detection

    Fordam University New York City, New York, USA · IBM Research Yorktown Heights, New York, USA · Fordham University New York City, New York, USA

  56. Adaptive and oblivious statistical adversaries are equivalent

    Oct 17, 2024Guy Blanc, Gregory ValiantBounded AdversaryOptimal Sample Complexity

    Stanford

  57. Corruption Robust Offline Reinforcement Learning with Human Feedback

    Feb 9, 2024Debmalya Mandal, Andi Nika, Parameswaran Kamalaruban +2Reinforcement Learning From Human FeedbackModel-Based Reinforcement Learning

    Dept. of Computer Science University of Warwick, UK · Max-Planck Institute for Software Systems, Germany · Independent Researcher London, UK

  58. VITA: A Multi-Source Vicinal Transfer Augmentation Method for Out-of-Distribution Generalization

    Apr 25, 2022Minghui Chen, Cheng Wen, Feng Zheng +2Data AugmentationOut-Of-Distribution

    Department of Computer Science and Engineering, Southern University of Science and Technology · The University of Sydney · JD Explore Academy, JD.com Inc +1