Pith Number

pith:REFJ7D2X

pith:2023:REFJ7D2XWI4UUYCPRUQEBUEWMK

not attested not anchored not stored refs resolved

SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation

Chongyu Fan, Dennis Wei, Eric Wong, Jiancheng Liu, Sijia Liu, Yihua Zhang

Gradient-based weight saliency enables effective unlearning of data, classes, or concepts in both image classifiers and generators while approaching exact retraining performance.

arxiv:2310.12508 v5 · 2023-10-19 · cs.LG · cs.AI

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{REFJ7D2XWI4UUYCPRUQEBUEWMK}

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

To the best of our knowledge, SalUn is the first principled MU approach that can effectively erase the influence of forgetting data, classes, or concepts in both image classification and generation tasks.

C2weakest assumption

That gradient-derived weight saliency reliably isolates the parameters responsible for the forgetting data without introducing large unintended side effects on retained knowledge, an assumption tested only through the reported empirical gaps to exact unlearning.

C3one line summary

SalUn uses gradient-based weight saliency to achieve effective machine unlearning of data, classes, or concepts in image classification and generation, narrowing the gap to exact retraining.

References

206 extracted · 206 resolved · 17 Pith anchors

[1] Sanity checks for saliency maps 2018

[2] Gradient surgery for one-shot unlearning on generative model, 2023 2023

[4] Nudenet: Neural nets for nudity classification, detection and selective censoring, 2019 2019

[6] Membership inference attacks from first principles 2022

[7] Grad- CAM ++: Generalized gradient-based visual explanations for deep convolutional networks 2018

Formal links

2 machine-checked theorem links

Cited by

25 papers in Pith

Exploring Nonlinear Pathway in Parameter Space for Machine Unlearning

PIU: Proximity-guided Identity Unlearning in ID-Conditioned Diffusion Models

Forget-It-All: Multi-Concept Machine Unlearning via Concept-Aware Neuron Masking

Class Unlearning via Depth-Aware Removal of Forget-Specific Directions

BARRIER: Bounded Activation Regions for Robust Information Erasure

Receipt and verification

First computed	2026-05-17T23:38:47.057421Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

890a9f8f57b2394a604f8d2040d09662b0bc5beee36f5e6a491737aaa5d68b61

Aliases

arxiv: 2310.12508 · arxiv_version: 2310.12508v5 · doi: 10.48550/arxiv.2310.12508 · pith_short_12: REFJ7D2XWI4U · pith_short_16: REFJ7D2XWI4UUYCP · pith_short_8: REFJ7D2X

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/REFJ7D2XWI4UUYCPRUQEBUEWMK \
  | 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: 890a9f8f57b2394a604f8d2040d09662b0bc5beee36f5e6a491737aaa5d68b61

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "5eac234552947cfb2efda6547732a6a9a90987672ef62839303d3bd53fd71da5",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2023-10-19T06:17:17Z",
    "title_canon_sha256": "f4ea98bc5a3945b38919063f119d895f0cf638dcfaf78b38bf0f870a67099082"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2310.12508",
    "kind": "arxiv",
    "version": 5
  }
}