Summary
When asked to recommend papers on explainability, privacy, adversarial ML, etc. ChatGPT recommends papers that (a) may not always exist, (b) mixes up correct and incorrect information, e.g. correct title but wrong authors, or (c) have incomplete information on authors.
Risk domain
Ethics
SEP view
E0402: Generative Misinformation
Lifecycle
L05: Evaluation, L06: Deployment
Affected artifacts
1 artifact
| Artifact | Type |
|---|---|
| ChatGPT | System |
References
1 reference
| URL | Label |
|---|---|
| ../img/R00031.png | Screenshot of example answer |
{
"affects": {
"artifacts": [
{
"name": "ChatGPT",
"type": "System"
}
],
"deployer": [
"OpenAI"
],
"developer": [
"OpenAI"
]
},
"credit": [
{
"lang": "eng",
"value": "Jaydeep Borkar, N/A"
}
],
"data_type": "AVID",
"data_version": "0.2",
"description": {
"lang": "eng",
"value": "When asked to recommend papers on explainability, privacy, adversarial ML, etc. ChatGPT recommends papers that (a) may not always exist, (b) mixes up correct and incorrect information, e.g. correct title but wrong authors, or (c) have incomplete information on authors."
},
"impact": {
"avid": {
"lifecycle_view": [
"L05: Evaluation",
"L06: Deployment"
],
"risk_domain": [
"Ethics"
],
"sep_view": [
"E0402: Generative Misinformation"
],
"taxonomy_version": "0.2"
}
},
"last_modified_date": "2023-03-31",
"metadata": {
"vuln_id": "AVID-2023-V027"
},
"problemtype": {
"classof": "LLM Evaluation",
"description": {
"lang": "eng",
"value": "ChatGPT generates false or incomplete references to scientific literature"
},
"type": "Issue"
},
"published_date": "2023-03-31",
"references": [
{
"label": "Screenshot of example answer",
"type": "screenshot",
"url": "../img/R00031.png"
}
],
"reports": [
{
"name": "ChatGPT links wrong authors to papers",
"report_id": "AVID-2023-R0003",
"type": "Issue"
}
]
}
Loading…
Loading…
Experimental. This forecast is provided for visualization only and may change without notice. Do not use it for operational decisions.
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…
The MITRE ATT&CK techniques below are AI-generated suggestions, inferred from the description of the
vulnerability by the CIRCL/vulnerability-attack-technique-classification-roberta-base
model, served locally by ML-Gateway.
They have not been verified by an analyst and are provided for guidance only.
The approach is described in our paper Mapping CVEs to MITRE ATT&CK Techniques: A Curated Gold-Set Classifier and the Limits of LLM-Assisted Label Expansion.
Browse all ATT&CK techniques and the vulnerabilities related to each.
The approach is described in our paper Mapping CVEs to MITRE ATT&CK Techniques: A Curated Gold-Set Classifier and the Limits of LLM-Assisted Label Expansion.
Browse all ATT&CK techniques and the vulnerabilities related to each.
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…