AVID-2022-V001

Vulnerability from avid – Published: 2022-12-23 – Updated: 2022-12-23 LLM Evaluation
Summary
Sentence Completion Tasks performed by bert-base-uncased demonstrate significant gender bias, perpetuating negative social and professional stereotypes against females.
Risk domain
Ethics
SEP view
E0101: Group fairness
Lifecycle
L05: Evaluation
Organisations
HuggingFace (deployer)
Affected artifacts
Artifact Type
bert-base-uncased Model
References
URL Label
https://huggingface.co/bert-base-uncased bert-base-uncased on Hugging Face
To clipboard 

{
  "affects": {
    "artifacts": [
      {
        "name": "bert-base-uncased",
        "type": "Model"
      }
    ],
    "deployer": [
      "HuggingFace"
    ],
    "developer": []
  },
  "credit": [
    {
      "lang": "eng",
      "value": "Harry Saini, AVID"
    },
    {
      "lang": "eng",
      "value": "Sasha Luccioni, Hugging Face"
    }
  ],
  "data_type": "AVID",
  "data_version": "0.1",
  "description": {
    "lang": "eng",
    "value": "Sentence Completion Tasks performed by bert-base-uncased demonstrate significant gender bias, perpetuating negative social and professional stereotypes against females."
  },
  "impact": {
    "avid": {
      "lifecycle_view": [
        "L05: Evaluation"
      ],
      "risk_domain": [
        "Ethics"
      ],
      "sep_view": [
        "E0101: Group fairness"
      ],
      "taxonomy_version": "0.1"
    }
  },
  "last_modified_date": "2022-12-23",
  "metadata": {
    "vuln_id": "AVID-2022-V001"
  },
  "problemtype": {
    "classof": "LLM Evaluation",
    "description": {
      "lang": "eng",
      "value": "Gender Bias in Sentence Completion Tasks performed by bert-base-uncased"
    }
  },
  "published_date": "2022-12-23",
  "references": [
    {
      "label": "bert-base-uncased on Hugging Face",
      "url": "https://huggingface.co/bert-base-uncased"
    }
  ],
  "reports": [
    {
      "name": "Gender Bias in Sentence Completion Tasks performed by bert-base-uncased using the HONEST metric",
      "report_id": "AVID-2022-R0001",
      "type": "Detection"
    },
    {
      "name": "Profession bias reinforcing gender stereotypes found in bert-base-uncased, as measured on the Winobias dataset",
      "report_id": "AVID-2022-R0003",
      "type": "Detection"
    }
  ]
}


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.