pith:XGYKGKEL
Undetectable Backdoors in Model Parameters: Hiding Sparse Secrets in High Dimensions
A sparse perturbation masked by Gaussian dither embeds backdoors whose detection reduces to the hard Sparse PCA problem.
arxiv:2605.04209 v2 · 2026-05-05 · cs.CR · cs.AI · cs.LG
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{XGYKGKELLB27GWS6QI64VWFZST}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
We prove that distinguishing the backdoor-injected model from this reference is at least as hard as Sparse PCA detection, which is computationally infeasible under standard hardness assumptions. The guarantee holds against any probabilistic polynomial-time distinguisher with white-box access to the parameters.
Under a mild margin condition on the pre-trained classifier, we show that the dithered reference is functionally equivalent to the original classifier.
Sparse Backdoor plants a provably undetectable backdoor in neural network weights via structured sparse perturbations and isotropic Gaussian dithering, with detection hardness reduced to Sparse PCA.
Formal links
Cited by
Receipt and verification
| First computed | 2026-07-07T02:17:26.415350Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
b9b0a3288b5875f35a5e823dcad8b994d37db6e64763d978c8deab016db7563a
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/XGYKGKELLB27GWS6QI64VWFZST \
| 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: b9b0a3288b5875f35a5e823dcad8b994d37db6e64763d978c8deab016db7563a
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "be79287cd0b4835d87a4ea0069326fbe1bcf2588d839ce266ab0d2c61886c46d",
"cross_cats_sorted": [
"cs.AI",
"cs.LG"
],
"license": "http://creativecommons.org/licenses/by/4.0/",
"primary_cat": "cs.CR",
"submitted_at": "2026-05-05T18:48:09Z",
"title_canon_sha256": "0fa9e7dc09eafd9c787eb6c712b03eb3824dfafa953e4cac6c0d93b4ed0489b0"
},
"schema_version": "1.0",
"source": {
"id": "2605.04209",
"kind": "arxiv",
"version": 2
}
}