AVID-2022-V013

Vulnerability from avid – Published: 2022-12-23 – Updated: 2022-12-23 AIID Incident
Summary
Microsoft's Tay, an artificially intelligent chatbot, was released on March 23, 2016 and removed within 24 hours due to multiple racist, sexist, and anit-semetic tweets generated by the bot.
Risk domain
SecurityEthics
SEP view
S0601: Ingest Poisoning, E0101: Group fairness, E0301: Toxicity
Lifecycle
L06: Deployment
Organisations
Microsoft (deployer), Microsoft (developer)
References
To clipboard 

{
  "affects": {
    "artifacts": [
      {
        "name": "",
        "type": "System"
      }
    ],
    "deployer": [
      "Microsoft"
    ],
    "developer": [
      "Microsoft"
    ]
  },
  "credit": [
    {
      "lang": "eng",
      "value": "Sean McGregor, AIID"
    }
  ],
  "data_type": "AVID",
  "data_version": "0.1",
  "description": {
    "lang": "eng",
    "value": "Microsoft\u0027s Tay, an artificially intelligent chatbot, was released on March 23, 2016 and removed within 24 hours due to multiple racist, sexist, and anit-semetic tweets generated by the bot."
  },
  "impact": {
    "avid": {
      "lifecycle_view": [
        "L06: Deployment"
      ],
      "risk_domain": [
        "Security",
        "Ethics"
      ],
      "sep_view": [
        "S0601: Ingest Poisoning",
        "E0101: Group fairness",
        "E0301: Toxicity"
      ],
      "taxonomy_version": "0.1"
    }
  },
  "last_modified_date": "2022-12-23",
  "metadata": {
    "vuln_id": "AVID-2022-V013"
  },
  "problemtype": {
    "classof": "AIID Incident",
    "description": {
      "lang": "eng",
      "value": "TayBot"
    }
  },
  "published_date": "2022-12-23",
  "references": [
    {
      "label": "Incident 6: TayBot",
      "url": "https://incidentdatabase.ai/cite/6"
    },
    {
      "label": "Tay Poisoning",
      "url": "https://atlas.mitre.org/studies/AML.CS0009"
    }
  ],
  "reports": []
}


Log in or create an account to share your comment.




Tags
Taxonomy of the tags.





Forecast uses a logistic model when the trend is rising, or an exponential decay model when the trend is falling. Fitted via linearized least squares.

Sightings

Author Source Type Date Other

Nomenclature

  • Seen: The vulnerability was mentioned, discussed, or observed by the user.
  • Confirmed: The vulnerability has been validated from an analyst's perspective.
  • Published Proof of Concept: A public proof of concept is available for this vulnerability.
  • Exploited: The vulnerability was observed as exploited by the user who reported the sighting.
  • Patched: The vulnerability was observed as successfully patched by the user who reported the sighting.
  • Not exploited: The vulnerability was not observed as exploited by the user who reported the sighting.
  • Not confirmed: The user expressed doubt about the validity of the vulnerability.
  • Not patched: The vulnerability was not observed as successfully patched by the user who reported the sighting.


Detection rules are retrieved from Rulezet.