Data Poisoning Attacks

Ask about this topic

Overview

Data poisoning studies how malicious or corrupted examples can alter a model during training, from degrading overall accuracy to implanting a backdoor that activates only under a chosen trigger. Attacks include label flipping, clean-label and trigger-based poisoning, malicious client updates in federated learning, and poisoned documents or preferences used by language models and retrieval systems. Defenses use data provenance and filtering, robust aggregation, representation and influence analysis, certified training, and post-training unlearning. A central challenge is that small, carefully targeted poisons can preserve normal benchmark performance, while defenses often depend on the model, data pipeline, and attack type.

Latest papers

CardsList

126 papers11 papers in the last four weeks, down 42% on the four weeks before. 0.1% of all new papers.

  1. Fox in the Henhouse: Supply-Chain Backdoor Attacks Against Reinforcement Learning

    May 26, 2025Shijie Liu, Andrew C. Cullen, Paul Montague +2Adversarial AttacksBackdoor Attacks

    School of Computing and Information Systems, University of Melbourne, Parkville, Australia · DST Group, Adelaide

  2. How to Backdoor Image Knowledge Distillation

    Apr 30, 2025Qian Ma, Chen Wu, Prasenjit Mitra +1Adversarial AttacksData Poisoning Attacks

    The Pennsylvania State University, State College, USA · Carnegie Mellon University Africa, Kigali, Rwanda

  3. Trust Under Siege: Label Spoofing Attacks against Machine Learning for Android Malware Detection

    Mar 14, 2025Tianwei Lan, Luca Demetrio, Farid Nait-Abdesselam +2Android Malware DetectionMalware Classification

    1Université Paris Cité, France · University of Genova, Italy · 3INRIA, France +1

  4. Approaching the Harm of Gradient Attacks While Only Flipping Labels

    Feb 28, 2025Abdessamad El-Kabid, El-Mahdi El-MhamdiFederated Learning AggregationAdversarial Attacks

    École Polytechnique

  5. FedNIA: Noise-Induced Activation Analysis for Mitigating Data Poisoning in Federated Learning

    Feb 23, 2025Ehsan Hallaji, Roozbeh Razavi-Far, Mehrdad SaifData Poisoning AttacksFederated Learning

    Department of Electrical and Computer Engineering, University of Windsor, Windsor ON, Canada · Faculty of Computer Science, University of New Brunswick, Fredericton NB, Canada

  6. SynGhost: Invisible and Universal Task-agnostic Backdoor Attack via Syntactic Transfer

    Feb 29, 2024Pengzhou Cheng, Wei Du, Zongru Wu +4Language Model PretrainingLLM Backdoor Attacks

    School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University · Department of Computer Science and Engineering Southern University of Science and Technology