SIGNAL//DESK
AI securitysrc: Roost FA glossary v2

Data poisoning

Injecting bad examples into a model's training data so it learns the wrong thing. In your FA practice, this looks like using unverified 'open-source' datasets to fine-tune your internal models, effectively importing a Trojan horse.

Data poisoning occurs when malicious or unverified data is introduced into a training or fine-tuning pipeline to manipulate model outputs. In practice, this often happens when developers integrate untrusted open-source datasets, inadvertently embedding backdoors or performance biases that compromise the model's integrity.

Data poisoning is an adversarial machine learning attack involving the intentional injection of corrupted or adversarial samples into the training or fine-tuning distribution. By manipulating the model's objective function through poisoned gradients or feature-space perturbations, an attacker can induce targeted misclassifications, create persistent backdoors, or degrade overall model utility, often facilitated by the ingestion of unverified third-party datasets.

evolution

  1. 2004 · history
    Poisoning Attacks on SVMs

    Biggio et al. formally demonstrated that support vector machines could be compromised by injecting malicious training samples.

  2. 2012 · history
    Label Flipping Attacks

    Researchers introduced label flipping as a specific poisoning technique to degrade the performance of machine learning classifiers.

  3. 2017 · history
    Backdoor Attacks in Deep Learning

    Gu et al. published 'BadNets,' showing how neural networks can be trained to trigger specific malicious behaviors via hidden patterns.

  4. 2020 · history
    Poisoning Large-Scale Datasets

    Studies demonstrated that poisoning attacks could be effective against large-scale models like those trained on ImageNet by manipulating a small fraction of the data.

  5. 2023 · history
    Supply Chain Poisoning via Open Source

    Security researchers highlighted the risk of 'data poisoning' in LLM supply chains through the use of unverified, scraped, or compromised public datasets.


← all terms