Data Poisoning

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

No benchmark for this task in the archive.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

No dataset record in the archive lists this task.

Subtasks archive 2025-07-28

No subtask under this task in the archive's task tree.

Most implemented papers archive 2025-07-28

30 shown of 170 papers with code (492 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networks
  3 Apr 2018 5 repositories listed
  The proposed attacks use "clean-labels"; they don't require the attacker to have any control over the labeling of training data.
• IMMA: Immunizing text-to-image Models against Malicious Adaptation
  30 Nov 2023 3 repositories listed Syntology ran 1 of 17 samples · 16 unverified
  We propose to ``immunize'' the model by learning model parameters that are difficult for the adaptation methods when fine-tuning malicious content; in short IMMA.
• Analysis and Detectability of Offline Data Poisoning Attacks on Linear Dynamical Systems
  16 Nov 2022 3 repositories listed
  In recent years, there has been a growing interest in the effects of data poisoning attacks on data-driven control methods.
• Adversarial Examples Make Strong Poisons
  21 Jun 2021 3 repositories listed Syntology ran 2 of 2 samples · 0 unverified
  The adversarial machine learning literature is largely partitioned into evasion attacks on testing data and poisoning attacks on training data.
• How To Backdoor Federated Learning
  2 Jul 2018 3 repositories listed Syntology ran 1 of 1 samples · 0 unverified
  An attacker selected in a single round of federated learning can cause the global model to immediately reach 100% accuracy on the backdoor task.
• 2D-OOB: Attributing Data Contribution Through Joint Valuation Framework
  7 Aug 2024 2 repositories listed
  Data valuation has emerged as a powerful framework for quantifying each datum's contribution to the training of a machine learning model.
• Data Poisoning in LLMs: Jailbreak-Tuning and Scaling Laws
  6 Aug 2024 2 repositories listed Syntology ran 1 of 5 samples · 4 unverified · 5 pointer-only (licence)
  LLMs produce harmful and undesirable behavior when trained on poisoned datasets that contain a small fraction of corrupted or harmful data.
• Mitigating Backdoor Attack by Injecting Proactive Defensive Backdoor
  25 May 2024 2 repositories listed Syntology ran 4 of 5 samples · 1 unverified · 5 pointer-only (licence)
  Specifically, PDB leverages the home-field advantage of defenders by proactively injecting a defensive backdoor into the model during training.
• Defending Against Patch-based Backdoor Attacks on Self-Supervised Learning
  4 Apr 2023 2 repositories listed
  It was shown that an adversary can poison a small part of the unlabeled data so that when a victim trains an SSL model on it, the final model will have a backdoor that the adversary can exploit.
• Run-Off Election: Improved Provable Defense against Data Poisoning Attacks
  5 Feb 2023 2 repositories listed Syntology ran 1 of 1 samples · 0 unverified · 1 pointer-only (licence)
  Based on this approach, we propose DPA+ROE and FA+ROE defense methods based on Deep Partition Aggregation (DPA) and Finite Aggregation (FA) approaches from prior work.
• CorruptEncoder: Data Poisoning based Backdoor Attacks to Contrastive Learning
  15 Nov 2022 2 repositories listed
  In this work, we take the first step to analyze the limitations of existing backdoor attacks and propose new DPBAs called CorruptEncoder to CL.
• Not All Poisons are Created Equal: Robust Training against Data Poisoning
  18 Oct 2022 2 repositories listed Syntology ran 4 of 12 samples · 8 unverified
  Data poisoning causes misclassification of test time target examples by injecting maliciously crafted samples in the training data.
• Adversarial Robustness of Representation Learning for Knowledge Graphs
  30 Sep 2022 2 repositories listed
  This thesis argues that state-of-the-art KGE models are vulnerable to data poisoning attacks, that is, their predictive performance can be degraded by systematically crafted perturbations to the training knowledge graph.
• Autoregressive Perturbations for Data Poisoning
  8 Jun 2022 2 repositories listed Syntology ran 3 of 5 samples · 2 unverified · 2 pointer-only (licence)
  Unfortunately, existing methods require knowledge of both the target architecture and the complete dataset so that a surrogate network can be trained, the parameters of which are used to generate the attack.
• Bilevel Optimization with a Lower-level Contraction: Optimal Sample Complexity without Warm-start
  7 Feb 2022 2 repositories listed Syntology ran 8 of 8 samples · 0 unverified
  We analyse a general class of bilevel problems, in which the upper-level problem consists in the minimization of a smooth objective function and the lower-level problem is to find the fixed point of a smooth contraction…
• Data Poisoning Attacks on Regression Learning and Corresponding Defenses
  15 Sep 2020 2 repositories listed
  Adversarial data poisoning is an effective attack against machine learning and threatens model integrity by introducing poisoned data into the training dataset.
• Witches' Brew: Industrial Scale Data Poisoning via Gradient Matching
  4 Sep 2020 2 repositories listed Syntology ran 4 of 5 samples · 1 unverified · 5 pointer-only (licence)
  We consider a particularly malicious poisoning attack that is both "from scratch" and "clean label", meaning we analyze an attack that successfully works against new, randomly initialized models, and is nearly…
• Data Poisoning Attacks Against Federated Learning Systems
  16 Jul 2020 2 repositories listed Syntology ran 0 of 3 samples · 3 unverified
  Federated learning (FL) is an emerging paradigm for distributed training of large-scale deep neural networks in which participants' data remains on their own devices with only model updates being shared with a central…
• Just How Toxic is Data Poisoning? A Unified Benchmark for Backdoor and Data Poisoning Attacks
  22 Jun 2020 2 repositories listed Syntology ran 0 of 10 samples · 10 unverified
  Data poisoning and backdoor attacks manipulate training data in order to cause models to fail during inference.
• MetaPoison: Practical General-purpose Clean-label Data Poisoning
  1 Apr 2020 2 repositories listed Syntology ran 2 of 3 samples · 1 unverified · 3 pointer-only (licence)
  Existing attacks for data poisoning neural networks have relied on hand-crafted heuristics, because solving the poisoning problem directly via bilevel optimization is generally thought of as intractable for deep models.
• Radioactive data: tracing through training
  3 Feb 2020 2 repositories listed
  The mark is robust to strong variations such as different architectures or optimization methods.
• Penalty Method for Inversion-Free Deep Bilevel Optimization
  8 Nov 2019 2 repositories listed
  We present results on data denoising, few-shot learning, and training-data poisoning problems in a large-scale setting.
• TrojDRL: Trojan Attacks on Deep Reinforcement Learning Agents
  1 Mar 2019 2 repositories listed
  Recent work has identified that classification models implemented as neural networks are vulnerable to data-poisoning and Trojan attacks at training time.
• Stronger Data Poisoning Attacks Break Data Sanitization Defenses
  2 Nov 2018 2 repositories listed
  In this paper, we develop three attacks that can bypass a broad range of common data sanitization defenses, including anomaly detectors based on nearest neighbors, training loss, and singular-value decomposition.
• Certified Defenses for Data Poisoning Attacks
  9 Jun 2017 2 repositories listed
  Machine learning systems trained on user-provided data are susceptible to data poisoning attacks, whereby malicious users inject false training data with the aim of corrupting the learned model.
• Addressing The Devastating Effects Of Single-Task Data Poisoning In Exemplar-Free Continual Learning
  5 Jul 2025 1 repository listed
  We show that STP attacks are able to strongly disrupt the whole continual training process: decreasing both the stability (its performance on past tasks) and plasticity (capacity to adapt to new tasks) of the algorithm.
• VLMs Can Aggregate Scattered Training Patches
  4 Jun 2025 1 repository listed
  Building on this, we simulate the adversarial data poisoning scenario mentioned above by using patches from dangerous images and replacing IDs with text descriptions like ``safe'' or ``unsafe'', demonstrating how…
• Does Low Rank Adaptation Lead to Lower Robustness against Training-Time Attacks?
  19 May 2025 1 repository listed Syntology ran 0 of 1 samples · 1 unverified · 1 pointer-only (licence)
  In this paper, we theoretically investigate the security implications of LoRA's low-rank structure during fine-tuning, in the context of its robustness against data poisoning and backdoor attacks.
• Adversarial Robustness of Deep Learning Models for Inland Water Body Segmentation from SAR Images
  3 May 2025 1 repository listed
  In this work, we simulate manual errors in the form of adversarial attacks on the U-Net model and study the robustness of the model to human errors in annotation.
• Data Poisoning in Deep Learning: A Survey
  27 Mar 2025 1 repository listed
  However, during the training process, deep learning models face the significant threat of data poisoning, where attackers introduce maliciously manipulated training data to degrade model accuracy or lead to anomalous…

Syntology lines on 14 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. Read from the graph 2026-09-24.