Pith Number

pith:WS6MQUM7

pith:2026:WS6MQUM7IE45BN44KX2ODCOVK5

not attested not anchored not stored refs resolved

Backbone is All You Need: Assessing Vulnerabilities of Frozen Foundation Models in Synthetic Image Forensics

Andrea Montibeller, Chiara Musso, Giulia Boato, Joy Battocchio

Knowledge of only the Vision Transformer backbone in frozen deepfake detectors enables gray-box adversarial attacks that reach near white-box success rates.

arxiv:2605.13381 v1 · 2026-05-13 · cs.CV · cs.MM

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{WS6MQUM7IE45BN44KX2ODCOVK5}

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

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

backbone knowledge alone is sufficient to undermine detector reliability, highlighting the urgent need for more resilient defenses in adversarial multimedia forensics.

C2weakest assumption

That an attacker with only backbone knowledge can reliably access and manipulate the target detector's internal feature space to generate effective adversarial examples.

C3one line summary

Knowledge of the ViT backbone alone enables highly effective gray-box adversarial attacks on synthetic image detectors, often nearing white-box performance.

References

31 extracted · 31 resolved · 2 Pith anchors

[1] Adobe. 2023. Adobe Firefly: Generative AI for Content Creation. https://www. adobe.com/sensei/generative-ai/firefly.html. Accessed: 2026-02-09 2023

[2] Irene Amerini, Mauro Barni, Sebastiano Battiato, et al. 2025. Deepfake media forensics: Status and future challenges.Journal of Imaging11, 3 (2025), 73 2025

[3] Erik Arakelyan, Karen Hambardzumyan, Davit Papikyan, et al. 2025. With Great Backbones Comes Great Adversarial Transferability. arXiv:2501.12275 2025

[4] Sebastiano Battiato, Mirko Casu, Francesco Guarnera, et al. 2025. Adversarial Attacks on Deepfake Detectors: A Challenge in the Era of AI-Generated Me- dia (AADD-2025). InProceedings of the 33rd ACM I 2025

[5] Joy Battocchio, Stefano Dell’Anna, Andrea Montibeller, and Giulia Boato. 2025. Advance Fake Video Detection via Vision Transformers. InProceedings of the 2025 ACM Workshop on Information Hiding and Mu 2025

Receipt and verification

First computed	2026-05-18T02:44:47.830854Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

b4bcc8519f4139d0b79c55f4e189d5577259163aeecac2f2530644011f6b61e6

Aliases

arxiv: 2605.13381 · arxiv_version: 2605.13381v1 · doi: 10.48550/arxiv.2605.13381 · pith_short_12: WS6MQUM7IE45 · pith_short_16: WS6MQUM7IE45BN44 · pith_short_8: WS6MQUM7

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/WS6MQUM7IE45BN44KX2ODCOVK5 \
  | 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: b4bcc8519f4139d0b79c55f4e189d5577259163aeecac2f2530644011f6b61e6

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "92a579dd74c247ef2829e09f2fc1d9c867c39b671759bfec53785c62dd9851ea",
    "cross_cats_sorted": [
      "cs.MM"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2026-05-13T11:35:56Z",
    "title_canon_sha256": "10bb2b93d2dd8b8a0cba9008d24d534f9369cbbdf0e41ec211996932cd604552"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.13381",
    "kind": "arxiv",
    "version": 1
  }
}