Pith Number

pith:TA5KJQNT

pith:2026:TA5KJQNT3FHIQUNJIMRGMI64ZB

not attested not anchored not stored refs pending

Efficient Preference Poisoning Attack on Offline RLHF

Chenye Yang, Lifeng Lai, Weiyu Xu

Flipping one preference label in log-linear DPO creates a parameter-independent gradient shift that turns targeted poisoning into a binary sparse approximation problem.

arxiv:2605.02495 v2 · 2026-05-04 · cs.LG · cs.AI · stat.ML

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{TA5KJQNT3FHIQUNJIMRGMI64ZB}

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

Flipping one preference label induces a parameter-independent shift in the DPO gradient, converting the targeted poisoning problem into a structured binary sparse approximation problem that BAL-A and BMP-A solve with sufficient conditions and coherence-based guarantees.

C2weakest assumption

The central reduction assumes that the DPO objective is strictly log-linear in the parameters so that the gradient shift from a single label flip remains independent of the current parameter vector; if this independence fails for realistic non-linear models or regularizers, the conversion to sparse approximation no longer holds.

C3one line summary

Label-flip attacks on log-linear DPO reduce to binary sparse approximation problems that can be solved efficiently by lattice-based and binary matching pursuit methods with recovery guarantees.

Formal links

3 machine-checked theorem links

Receipt and verification

First computed	2026-05-26T02:04:11.841288Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

983aa4c1b3d94e8851a943226623dcc84bdf1b058985d897d42c7897ef4bb2de

Aliases

arxiv: 2605.02495 · arxiv_version: 2605.02495v2 · doi: 10.48550/arxiv.2605.02495 · pith_short_12: TA5KJQNT3FHI · pith_short_16: TA5KJQNT3FHIQUNJ · pith_short_8: TA5KJQNT

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/TA5KJQNT3FHIQUNJIMRGMI64ZB \
  | 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: 983aa4c1b3d94e8851a943226623dcc84bdf1b058985d897d42c7897ef4bb2de

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "168897d1319adf9cf5ca6ec100e90635defd2020f0090cbb82ced51119b27a71",
    "cross_cats_sorted": [
      "cs.AI",
      "stat.ML"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-05-04T11:45:38Z",
    "title_canon_sha256": "6ce72836f72c2d4bc21da7421672596e800250bd45781c68f4170bcb702393f2"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.02495",
    "kind": "arxiv",
    "version": 2
  }
}