{
  "annotation_id": "7d89694d-dc51-494d-8176-3b40af63ecd8",
  "date_created": "2026-02-17T05:53:20.185000Z",
  "date_modified": "2026-02-17T05:53:20.185000Z",
  "file_hash": "60dff4d1ef12d92b296a7afcc68cfe457b4083ac388397319bd6e85f1151ff4d",
  "private": false,
  "record": {
    "abstract": "We study the pointwise maximal leakage (PML) envelope of the Gaussian mechanism, which characterizes the smallest information leakage bound that holds with high probability under arbitrary post-processing. For the Gaussian mechanism with a Gaussian secret, we derive a closed-form expression for the deterministic PML envelope for sufficiently small failure probabilities. We then extend this result to general unbounded secrets by identifying a sufficient condition under which the envelope coincides with the Gaussian case. In particular, we show that strongly log-concave priors satisfy this condition via an application of the Brascamp-Lieb inequality.",
    "arxiv_id": "2601.08986",
    "authors": [
      "Sara Saeidian"
    ],
    "categories": [
      "cs.IT",
      "math.IT"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "title": "On the Information Leakage Envelope of the Gaussian Mechanism",
    "url": "https://arxiv.org/abs/2601.08986",
    "version": "v1"
  },
  "schema_id": "dorsal/arxiv",
  "source": {
    "execution_id": "aea7d1f3-c311-4e5a-a60c-9c93a4b5d177",
    "id": "arXiv Dataset",
    "type": "Model",
    "variant": "snapshot-2026-01-17",
    "version": "0.1.0"
  },
  "user_id": 1000002
}