AVID-2022-V003

Vulnerability from avid – Published: 2022-12-23 – Updated: 2022-12-23 LLM Evaluation
Summary
xyz xyz
Risk domain
Ethics
SEP view
E0101: Group fairness
Lifecycle
L05: Evaluation
Organisations
HuggingFace (deployer), EleutherAI (developer)
Affected artifacts
Artifact Type
EleutherAI/gpt-neo-125M Model
References
URL Label
https://huggingface.co/EleutherAI/gpt-neo-125M gpt-neo-125M on Hugging Face

{
  "affects": {
    "artifacts": [
      {
        "name": "EleutherAI/gpt-neo-125M",
        "type": "Model"
      }
    ],
    "deployer": [
      "HuggingFace"
    ],
    "developer": [
      "EleutherAI"
    ]
  },
  "credit": [
    {
      "lang": "eng",
      "value": "Subho Majumdar, AVID"
    }
  ],
  "data_type": "AVID",
  "data_version": "0.1",
  "description": {
    "lang": "eng",
    "value": "xyz xyz"
  },
  "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-V003"
  },
  "problemtype": {
    "classof": "LLM Evaluation",
    "description": {
      "lang": "eng",
      "value": "Multiple fairness harms found in generated text from EleutherAI/gpt-neo-125M"
    }
  },
  "published_date": "2022-12-23",
  "references": [
    {
      "label": "gpt-neo-125M on Hugging Face",
      "url": "https://huggingface.co/EleutherAI/gpt-neo-125M"
    }
  ],
  "reports": [
    {
      "name": "Demographic bias found in EleutherAI/gpt-neo-125M for multiple sensitive categories, as measured on prompts supplied in the BOLD dataset",
      "report_id": "AVID-2022-R0005",
      "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…