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

{
  "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.


Loading…

Loading…

Loading…

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.

Loading…

Loading…

Loading…

Related by attack behaviour

Vulnerabilities whose description is nearest to this one in the vector space of the CIRCL/vulnerability-attack-technique-biencoder model. This is a similarity search over the bi-encoder space (plain cosine), not a classification, and it has no measured accuracy.


Loading…