AVID-2022-V010

Vulnerability from avid – Published: 2022-12-23 – Updated: 2022-12-23 AIID Incident
Summary
The publicly launched conversational AI demo BlenderBot 3 developed by Meta was reported by its users and acknowledged by its developers to have “occasionally” made offensive and inconsistent remarks such as invoking Jewish stereotypes.
Risk domain
Ethics
SEP view
E0101: Group fairness, E0301: Toxicity, E0402: Generative Misinformation
Lifecycle
L06: Deployment
Organisations
Facebook (deployer), Facebook (developer)
References
URL Label
https://incidentdatabase.ai/cite/278 Incident 278: Meta’s BlenderBot 3 Chatbot Demo Made Offensive Antisemitic Comments
To clipboard 

{
  "affects": {
    "artifacts": [
      {
        "name": "",
        "type": "System"
      }
    ],
    "deployer": [
      "Facebook"
    ],
    "developer": [
      "Facebook"
    ]
  },
  "credit": [
    {
      "lang": "eng",
      "value": "Khoa Lam, AIID"
    }
  ],
  "data_type": "AVID",
  "data_version": "0.1",
  "description": {
    "lang": "eng",
    "value": "The publicly launched conversational AI demo BlenderBot 3 developed by Meta was reported by its users and acknowledged by its developers to have \u201coccasionally\u201d made offensive and inconsistent remarks such as invoking Jewish stereotypes."
  },
  "impact": {
    "avid": {
      "lifecycle_view": [
        "L06: Deployment"
      ],
      "risk_domain": [
        "Ethics"
      ],
      "sep_view": [
        "E0101: Group fairness",
        "E0301: Toxicity",
        "E0402: Generative Misinformation"
      ],
      "taxonomy_version": "0.1"
    }
  },
  "last_modified_date": "2022-12-23",
  "metadata": {
    "vuln_id": "AVID-2022-V010"
  },
  "problemtype": {
    "classof": "AIID Incident",
    "description": {
      "lang": "eng",
      "value": "Meta\u2019s BlenderBot 3 Chatbot Demo Made Offensive Antisemitic Comments"
    }
  },
  "published_date": "2022-12-23",
  "references": [
    {
      "label": "Incident 278: Meta\u2019s BlenderBot 3 Chatbot Demo Made Offensive Antisemitic Comments",
      "url": "https://incidentdatabase.ai/cite/278"
    }
  ],
  "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.