"data poisoning" meaning in All languages combined

See data poisoning on Wiktionary

Noun [English]

Forms: data poisonings [plural]
Head templates: {{en-noun|~}} data poisoning (countable and uncountable, plural data poisonings)
  1. (machine learning, computer security) The deliberate use of a training dataset with data designed to increase errors in the output of a machine learning model. Tags: countable, uncountable Categories (topical): Artificial intelligence, Computer security Synonyms: poisoning attack
    Sense id: en-data_poisoning-en-noun-hNz9NCnE Categories (other): English entries with incorrect language header

Download JSON data for data poisoning meaning in All languages combined (2.9kB)

{
  "forms": [
    {
      "form": "data poisonings",
      "tags": [
        "plural"
      ]
    }
  ],
  "head_templates": [
    {
      "args": {
        "1": "~"
      },
      "expansion": "data poisoning (countable and uncountable, plural data poisonings)",
      "name": "en-noun"
    }
  ],
  "lang": "English",
  "lang_code": "en",
  "pos": "noun",
  "senses": [
    {
      "categories": [
        {
          "kind": "other",
          "name": "English entries with incorrect language header",
          "parents": [
            "Entries with incorrect language header",
            "Entry maintenance"
          ],
          "source": "w"
        },
        {
          "kind": "topical",
          "langcode": "en",
          "name": "Artificial intelligence",
          "orig": "en:Artificial intelligence",
          "parents": [
            "Computer science",
            "Cybernetics",
            "Computing",
            "Sciences",
            "Applied mathematics",
            "Systems theory",
            "Technology",
            "All topics",
            "Mathematics",
            "Systems",
            "Fundamental",
            "Formal sciences",
            "Interdisciplinary fields",
            "Society"
          ],
          "source": "w"
        },
        {
          "kind": "topical",
          "langcode": "en",
          "name": "Computer security",
          "orig": "en:Computer security",
          "parents": [
            "Computing",
            "Technology",
            "All topics",
            "Fundamental"
          ],
          "source": "w"
        }
      ],
      "examples": [
        {
          "ref": "2019, Simon N. Foley, editor, Data and Applications Security and Privacy XXXIII […], Springer, page 4",
          "text": "While data sanitization shows promise to defend against data poisoning, it is often impossible to validate every data source [14].",
          "type": "quotation"
        },
        {
          "ref": "2022, Alfred Z. Spector, Peter Norvig, Chris Wiggins, Jeannette M. Wing, Data Science in Context: Foundations, Challenges, Opportunities, Cambridge University Press, page 148",
          "text": "Similarly, the Tay chatbot suffered from data poisoning. To mitigate data poisoning, it is important not to let any one group contribute too much data to a model.",
          "type": "quotation"
        },
        {
          "ref": "2023, Katharine Jarmul, Practical Data Privacy, O'Reilly",
          "text": "Data poisoning is one type of adversarial attack—where a user or group of users submit false data to influence the model toward a particular or incorrect prediction.",
          "type": "quotation"
        },
        {
          "ref": "2023, Paul Scharre, Four Battlegrounds: Power in the Age of Artificial Intelligence, W. W. Norton & Company",
          "text": "Some forms of data poisoning are undetectable. Attackers can insert adversarial noise into the training data, altering the training data in a way that is hidden to human observers.",
          "type": "quotation"
        }
      ],
      "glosses": [
        "The deliberate use of a training dataset with data designed to increase errors in the output of a machine learning model."
      ],
      "id": "en-data_poisoning-en-noun-hNz9NCnE",
      "links": [
        [
          "machine learning",
          "machine learning"
        ],
        [
          "computer security",
          "computer security"
        ],
        [
          "dataset",
          "dataset"
        ],
        [
          "model",
          "model"
        ]
      ],
      "qualifier": "machine learning; computer security; machine learning; computer security",
      "raw_glosses": [
        "(machine learning, computer security) The deliberate use of a training dataset with data designed to increase errors in the output of a machine learning model."
      ],
      "synonyms": [
        {
          "word": "poisoning attack"
        }
      ],
      "tags": [
        "countable",
        "uncountable"
      ]
    }
  ],
  "word": "data poisoning"
}
{
  "forms": [
    {
      "form": "data poisonings",
      "tags": [
        "plural"
      ]
    }
  ],
  "head_templates": [
    {
      "args": {
        "1": "~"
      },
      "expansion": "data poisoning (countable and uncountable, plural data poisonings)",
      "name": "en-noun"
    }
  ],
  "lang": "English",
  "lang_code": "en",
  "pos": "noun",
  "senses": [
    {
      "categories": [
        "English countable nouns",
        "English entries with incorrect language header",
        "English lemmas",
        "English multiword terms",
        "English nouns",
        "English terms with quotations",
        "English uncountable nouns",
        "en:Artificial intelligence",
        "en:Computer security"
      ],
      "examples": [
        {
          "ref": "2019, Simon N. Foley, editor, Data and Applications Security and Privacy XXXIII […], Springer, page 4",
          "text": "While data sanitization shows promise to defend against data poisoning, it is often impossible to validate every data source [14].",
          "type": "quotation"
        },
        {
          "ref": "2022, Alfred Z. Spector, Peter Norvig, Chris Wiggins, Jeannette M. Wing, Data Science in Context: Foundations, Challenges, Opportunities, Cambridge University Press, page 148",
          "text": "Similarly, the Tay chatbot suffered from data poisoning. To mitigate data poisoning, it is important not to let any one group contribute too much data to a model.",
          "type": "quotation"
        },
        {
          "ref": "2023, Katharine Jarmul, Practical Data Privacy, O'Reilly",
          "text": "Data poisoning is one type of adversarial attack—where a user or group of users submit false data to influence the model toward a particular or incorrect prediction.",
          "type": "quotation"
        },
        {
          "ref": "2023, Paul Scharre, Four Battlegrounds: Power in the Age of Artificial Intelligence, W. W. Norton & Company",
          "text": "Some forms of data poisoning are undetectable. Attackers can insert adversarial noise into the training data, altering the training data in a way that is hidden to human observers.",
          "type": "quotation"
        }
      ],
      "glosses": [
        "The deliberate use of a training dataset with data designed to increase errors in the output of a machine learning model."
      ],
      "links": [
        [
          "machine learning",
          "machine learning"
        ],
        [
          "computer security",
          "computer security"
        ],
        [
          "dataset",
          "dataset"
        ],
        [
          "model",
          "model"
        ]
      ],
      "qualifier": "machine learning; computer security; machine learning; computer security",
      "raw_glosses": [
        "(machine learning, computer security) The deliberate use of a training dataset with data designed to increase errors in the output of a machine learning model."
      ],
      "synonyms": [
        {
          "word": "poisoning attack"
        }
      ],
      "tags": [
        "countable",
        "uncountable"
      ]
    }
  ],
  "word": "data poisoning"
}

This page is a part of the kaikki.org machine-readable All languages combined dictionary. This dictionary is based on structured data extracted on 2024-05-06 from the enwiktionary dump dated 2024-05-02 using wiktextract (f4fd8c9 and c9440ce). The data shown on this site has been post-processed and various details (e.g., extra categories) removed, some information disambiguated, and additional data merged from other sources. See the raw data download page for the unprocessed wiktextract data.

If you use this data in academic research, please cite Tatu Ylonen: Wiktextract: Wiktionary as Machine-Readable Structured Data, Proceedings of the 13th Conference on Language Resources and Evaluation (LREC), pp. 1317-1325, Marseille, 20-25 June 2022. Linking to the relevant page(s) under https://kaikki.org would also be greatly appreciated.