Data Poisoning Attacks

Ask about this topic

Momentum

12 papers in the last four weeks, up 50% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28
View on map

Latest papers 93

All topics
CardsList

  1. Distributed Denial of Science: How Indirect Data Poisoning of AI Systems Can Industrialize Scientific Fraud

    Jul 12, 2026Bálint Gyevnár, Atoosa Kasirzadeh, Nihar B. ShahAI-Assisted Scientific ResearchData Poisoning Attacks

    Institute for Complex Social Dynamics, Carnegie Mellon University · Departments of Philosophy & Software and Societal Systems, Carnegie Mellon University · Machine Learning and Computer Science Departments, Carnegie Mellon University

  2. Assessing the Operational Impact of Poisoning Attacks over Augmented 3D Point Cloud Public Datasets for Connected and Autonomous Vehicles

    Jul 7, 2026Marwan Lazrag, Badis Hammi, Lorena Gonzalez-Manzano +1Autonomous Driving DatasetsData Augmentation

    SAMOVAR, Télécom SudParis, Institut Polytechnique de Paris Palaiseau, France · Universidad Carlos III de Madrid Leganes, Spain

  3. Two Sides of the Same Coin: Learning the Backdoor to Remove the Backdoor

    Jul 7, 2026Qi Zhao, Christian WressneggerBackdoor AttacksBackdoor Detection

    KASTEL Security Research Labs · Karlsruhe Institute of Technology (KIT)

  4. Learning Only What Valid Adapters Can Express: Subspace-Constrained Adaptation Against Fine-Tuning Poisoning

    Jul 6, 2026Fabien PollyLLM Backdoor AttacksLow-Rank Adaptation

    Independent researcher

  5. Theory of Continual Learning Against Data Poisoning Attacks

    Jun 29, 2026Yiting Hu, Lingjie DuanContinual LearningAdversarial Robustness

    Singapore University of Technology and Design, Singapore · The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China.

  6. A Novel Latent-Class Attack and its Detection by Class Subspace Orthogonalization

    Jun 27, 2026Guangmingmei Yang, David J. Miller, George KesidisData Poisoning Attacks

    CSE & EE Depts, Penn State, University Park, PA, 16802 · Anomalee Inc., State College, PA, 16803

  7. Fairness Attacks on Recommender Systems

    Jun 27, 2026Yanan Wang, Yong GeAdversarial AttacksAlgorithmic Fairness

    Department of Information Systems and Operations Management, College of Business, The University of Texas at Arlington · Department of Management Information Systems, Eller College of Management, the University of Arizona

  8. Clustering Unsupervised Representations as Defense against Poisoning Attacks on Speech Commands Classification System

    Jun 27, 2026Thomas Thebaud, Sonal Joshi, Henry Li +4Backdoor AttacksAutomatic Speech Recognition

    Center for Language and Speech Processing, Johns Hopkins University, USA · Faculty of Information Technology, Brno University of Technology, Czechia

  9. ShareLock: A Stealthy Multi-Tool Threshold Poisoning Attack Against MCP

    Jun 25, 2026Liwei Liu, Tianzhu Han, Zijian Liu +2Adversarial AttacksMCP Security

    Shanghai Jiao Tong University · Shanghai, China

  10. Full spectrum Unlearnable Examples via Spectral Equalization

    Jun 25, 2026Jiale Cai, Gezheng Xu, Zhihao Li +6Adversarial ExamplesAdversarial Perturbations

    Department of Computer Science, Western University, London, ON, Canada · School of Statistics and Data Science, Southeast University, Nanjing, China · Department of Mechanical, Industrial and Aerospace Engineering, Concordia University +2

  11. TEMPO-Diffusion: Temporally Exposed Malicious Poisoning of Diffusion Models

    Jun 24, 2026William Aiken, Paula Branco, Guy-Vincent Jourdan +1Backdoor AttacksDiffusion-Based Image Generation

    School of Electrical Engineering and Computer Science, University of Ottawa, Ottawa, ON K1N 6N5, Canada

  12. Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning

    Jun 24, 2026Poojitha Thota, Shirin NilizadehLLM AuditingLLM Fine-Tuning

    The University of Texas at Arlington Arlington, Texas, USA

  13. Backdoor Attacks on Speech Emotion Recognition via TTS-Generated Poisoning

    Jun 19, 2026Yongbin Huang, Xihao Xie, Jia ZhangBackdoor AttacksSpeech Emotion Recognition

    Department of Computer Science Southern Methodist University Dallas, USA

  14. Stealthy World Model Manipulation via Data Poisoning

    Jun 17, 2026Yibin Hu, Xiaolin Sun, Zizhan ZhengWorld Model LearningAdversarial Attacks

    Department of Computer Science Tulane University New Orleans, LA, USA

  15. Loss Landscape Poisoning: Targeted Extraction of Unseen Training Data from LLMs

    Jun 15, 2026Md Abdullah Al Mamun, Ngoc Phu Doan, Pedram Zaree +2Privacy Leakage in Language ModelsLLM Security

    UC Riverside · Riverside, California, USA · Queen’s University Belfast +2

  16. Rapid Poison: Practical Poisoning Attacks Against the Rapid Response Framework

    Jun 15, 2026David Huang, Jaewon Chang, Avidan Shah +2LLM Backdoor AttacksPrompt Injection Attacks

    Princeton University · Anthropic · UC Berkeley +2

  17. One Polluted Page Is Enough: Evaluating Web Content Pollution in Generative Recommenders

    Jun 11, 2026Minghao Luo, Liang ChenLLM EvaluationRAG Security

    The Chinese University of Hong Kong

  18. When Poison Fails After Retrieval: Revisiting Corpus Poisoning under Chunking and Reranking Pipelines

    Jun 9, 2026Xi Nie, Hongwei Li, Shenghao Wu +3RAG Poisoning AttacksRAG Security

    School of Computer Science and Engineering, University of Electronic Science and Technology of China, China · School of Criminal Investigation, People’s Public Security University of China, China · School of Computer Science and Artificial Intelligence, Wuhan University of Technology, China

  19. Safe-RULE: Safe Reinforcement UnLEarning

    Jun 8, 2026Shixiong Jiang, Taozheng Zhu, Fanxin KongOffline RLSafe RL

    Department of Computer Science and Engineering, University of Notre Dame

  20. Securing Self-supervised Data Curation for Foundation Models Robustness

    Jun 8, 2026Sandeep Gupta, Roberto PasseroneTraining Data CurationAdversarial Example Detection

    Centre for Secure Information Technologies (CSIT), Queen’s University Belfast, UK. · Department of Information Engineering and Computer Science, University of Trento, Italy.

  21. Targeting World Models to Compromise Robot Learning Pipelines

    Jun 8, 2026Ethan Rathbun, Ahmed Agha, Saaduddin Mahmud +3Robot Policy LearningWorld Models for Robotics

    Northeastern University · University of Massachusetts Amherst

  22. Steering Vectors are an Adversarial Attack Surface

    Jun 4, 2026Abzal Aidakhmetov, Donato Crisostomi, Tommaso Mencattini +3Language Model SteeringAdversarial Attacks on LLMs

    1Sapienza University of Rome · 2EPFL

  23. Sequential Data Poisoning in LLM Post-Training

    Jun 3, 2026Jack Sanderson, Yihan Wang, Xiaoqian Lu +2LLM SecurityLLM Post-Training

    University of Chicago · Vector Institute · University of Waterloo +1

  24. Characterizing Detectability in 3DGS Poisoning: A Stage-wise Benchmark

    Jun 2, 2026Quoc-Anh Bui-Huynh, Thanh Duc Ngo, Xue Geng +43D Gaussian Splatting3D Reconstruction

    Temasek Laboratories, Singapore University of Technology and Design · Vietnam National University, Ho Chi Minh City · University of Information Technology, VNU-HCM +1

  25. CANARY: Zero-Label Detection of Fine-Tuning Contamination in Language Models

    Jun 1, 2026Swapnil ParekhLLM AuditingData Contamination in Language Models

    Intuit Inc.

  26. DiscourseFlip: An Oblique Discourse-Level Opinion Manipulation Attack against Black-box Retrieval-Augmented Generation

    May 31, 2026Yuyang Gong, Miaokun Chen, Jiawei Liu +5RAG Poisoning AttacksRAG Security

    Wuhan University · East China Normal University · Nanyang Technological University +1

  27. Token-Level Generalization in LoRA Adapter Backdoors: Attack Characterization and Behavioral Detection

    May 28, 2026Travis LelleLLM Backdoor AttacksBackdoor Detection

  28. Density-aware Sample-specific Attack

    May 27, 2026Qiyuan Wang, Yao Li, Raymond K. W. WongBackdoor AttacksAdversarial Robustness

    Texas A&M University · University of North Carolina at Chapel Hill

  29. Backdoor Attacks on Fault Detection and Localization in Cyber-Physical Systems

    May 26, 2026Abile Jean, Kuniyilh SCyber-Physical SystemsBackdoor Attacks

  30. Poison with Style: A Practical Poisoning Attack on Code Large Language Models

    May 26, 2026Khang Tran, Yazan Boshmaf, Issa Khalil +3LLM Backdoor AttacksData Poisoning Attacks

    Department of Data Science, New Jersey Institute of Technology, New Jersey, U.S.A. · Qatar Computing Research Institute, HBKU, Doha, Qatar · Mohamed Bin Zayed University of Artificial Intelligence, Abu Dhabi, United Arab Emirates