Pith Number

pith:UXPFIIL4

pith:2026:UXPFIIL4VD74LD25BAB5BXWPBH

not attested not anchored not stored refs resolved

Adversarial Fragility and Language Vulnerability in Clinical AI: A Systematic Audit of Diagnostic Collapse Under Imperceptible Perturbations and Cross-Lingual Drift in Low-Resource Healthcare Settings

Ahmad Rufai Yusuf, Anthonio Oladimeji Gabriel

Clinical AI for chest X-rays loses accuracy from 89 percent to 62 percent under tiny invisible image changes and drops further on Nigerian dialects.

arxiv:2605.16993 v1 · 2026-05-16 · cs.CY · cs.AI · cs.LG

Open paper page JSON Open Graph Bundle Merged state What is a Pith Number?

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{UXPFIIL4VD74LD25BAB5BXWPBH}

Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more

Record completeness

1 Bitcoin timestamp

2 Internet Archive

3 Author claim open · sign in to claim

4 Citations open

5 Replications open

✓ Portable graph bundle live · download bundle · merged state

The bundle contains the canonical record plus signed events. A mirror can host it anywhere and recompute the same current state with the deterministic merge algorithm.

Claims

C1strongest claim

Diagnostic accuracy collapses from 89.3% to 62.0% under a Fast Gradient Method (FGM) perturbation of epsilon=0.021, a magnitude imperceptible to the human eye, and language models drop from 85.0% to 55.0% on Nigerian Pidgin and Yoruba-inflected English cases.

C2weakest assumption

The 20 clinical cases and the specific perturbation magnitude of epsilon=0.021 are representative of real deployment conditions in Nigerian Primary Health Centres without further validation against actual noisy images or spoken dialects.

C3one line summary

The study shows clinical AI accuracy collapsing from 89% to 62% on X-rays under imperceptible adversarial perturbations and from 85% to 55% on clinical cases in Nigerian Pidgin and Yoruba-inflected English.

References

35 extracted · 35 resolved · 2 Pith anchors

[1] Wahl B. et al. Artificial intelligence (AI) and global health: how can AI contribute to health in resource-poor settings? BMJ Global Health, 3(4), e000798 (2018). https://doi.org/10.1136/bmjgh-2018-00 2018 · doi:10.1136/bmjgh-2018-000798

[2] Okafor C. et al. The utilization of artificial intelligence (AI) and machine learning (ML) for health in Nigeria: a rapid review. Journal of Medical Artificial Intelligence (2024). https://jmai.amegro 2024

[3] Amgad M. et al. Robust and Interpretable Chest X-ray Classification via Diffusion Purification and Concept-Based Adversarial Detection. Journal of Object Technology in Biomedical Research, 2025. https 2025 · doi:10.1016/j.media.2025.103375

[4] Tahir A.M. et al. COVID-19 infection localization and severity grading from chest X-ray images. Computers in Biology and Medicine, 139, 105002 (2021). https://doi.org/10.1016/j.compbiomed.2021.105002 2021 · doi:10.1016/j.compbiomed.2021.105002

[5] Adeyemi O. et al. WeCAViT: A Weighted CNN-ViT model for Pneumonia Detection in Chest X-rays. IEEE Access, 2025. https://www.researchgate.net/publication/389527548 2025

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-20T00:03:34.956759Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

a5de54217ca8ffc58f5d0803d0decf09c288e6477b472941a89e73efbf3fbb12

Aliases

arxiv: 2605.16993 · arxiv_version: 2605.16993v1 · doi: 10.48550/arxiv.2605.16993 · pith_short_12: UXPFIIL4VD74 · pith_short_16: UXPFIIL4VD74LD25 · pith_short_8: UXPFIIL4

Agent API

Resolver JSON Graph JSON Events JSON Schema Signing key

Verify this Pith Number yourself

curl -sH 'Accept: application/ld+json' https://pith.science/pith/UXPFIIL4VD74LD25BAB5BXWPBH \
  | jq -c '.canonical_record' \
  | python3 -c "import sys,json,hashlib; b=json.dumps(json.loads(sys.stdin.read()), sort_keys=True, separators=(',',':'), ensure_ascii=False).encode(); print(hashlib.sha256(b).hexdigest())"
# expect: a5de54217ca8ffc58f5d0803d0decf09c288e6477b472941a89e73efbf3fbb12

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "2e58869f8bb03d69b1fcfa985c8621f11d58b040eff2a5ecf67cc5862d1eff13",
    "cross_cats_sorted": [
      "cs.AI",
      "cs.LG"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CY",
    "submitted_at": "2026-05-16T13:33:47Z",
    "title_canon_sha256": "5650944dc18229b8943a03836a846176b3926052edd187b2ec34a1729f370a17"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.16993",
    "kind": "arxiv",
    "version": 1
  }
}