Writing study: LDP-Slicing: Local Differential Privacy for Images via Randomized Bit-Plane Slicing

CVPR overviewCorpus atlasBy contribution typeVisual galleryRules & templateWriting patternsPaper studies

← CVPR 2026 oral writing corpus

Yuanming Cao, Chengqi Li, Wenbo He · Official CVPR 2026 oral record

Observed writing choices, not acceptance rules. This study examines the inspected manuscript version. It does not establish why the paper was accepted or that its presentation choices should be copied unchanged.

Figure, table and section ledger

Editorial contribution type: Theory & formal analysis (primary).

Layout extraction, not a required paper template. Counts are distinct caption labels; a multi-panel figure counts once. Section spans are estimated from heading positions, including floats and whitespace. Method and limitations.

Canonical PDF

10 physical pages

Before references / appendix

≈ 8.05 page-equivalents

Main figures / tables

8 / 5

Attached appendix figures / tables

0 / 0

Attached appendix span

Separate file recorded below; not in this PDF total

Before references / appendix: ≈ 80.5%References / intervening material: ≈ 19.5%Estimated layout envelopes, not text/artwork area. Unresolved appendix boundaries remain within the undivided post-body material.

Extraction notes: No attached appendix boundary detected. Zero means no recognized caption, not independently verified absence.

Section-by-section lengths and source pages

The title/abstract/front matter precede the first numbered heading. A span ends at the next detected top-level heading, not at the last sentence; end-page whitespace is included. References and statements are listed separately. These are not measurements of text-only or artwork area.

Top-level heading	Starts on PDF page	Estimated span	Share of entire PDF
1. Introduction	1	≈ 1.37 pp.	13.7%
2. Related work	2	≈ 0.49 pp.	4.9%
3. Preliminaries	3	≈ 0.64 pp.	6.4%
4. Methodology	3	≈ 2.4 pp.	24%
5. Experiments	6	≈ 2.6 pp.	26%
6. Conclusion	8	≈ 0.19 pp.	1.9%
References	9	≈ 1.95 pp.	19.5%

All detected figure and table locations

Main text

• Figure 1 · p. 2
• Figure 2 · p. 4
• Figure 3 · p. 4
• Table 1 · p. 6
• Figure 4 · p. 6
• Figure 5 · p. 6
• Figure 6 · p. 7
• Table 2 · p. 7
• Table 3 · p. 7
• Figure 7 · p. 8
• Figure 8 · p. 8
• Table 4 · p. 8
• Table 5 · p. 8

Attached appendix

No recognized caption labels.

Separate source files—excluded from canonical-PDF totals

A separate author version may repeat main text and references. Whole-file lengths and counts are not extra appendix material and are never added to the canonical PDF totals. Read the study's source scope for which sections received substantive reading versus layout inspection.

Additional source 1

Separate PDF (or ZIP containing it): whole-file layout of 4 physical pages; 2 detected figures and 2 tables. These may include overlapping main-text material.

Located appendix only: starts on physical p.1; ≈ 3.93 page-equivalents, 2 figure labels and 2 table labels. This interval is distinct from the whole file.

Detected heading	PDF page	Estimated span
Supplementary Material	1	≈ 0.12 pp.
A. Formal attack definition	1	≈ 0.16 pp.
B. Derivation of utility-aware budget optimiza-	1	≈ 0.53 pp.
C. Complete proofs	1	≈ 1.66 pp.
D. Experiments	3	≈ 1 pp.
E. Ethical considerations.	4	≈ 0.45 pp.

• Figure 9 · p. 2
• Table 6 · p. 4
• Table 7 · p. 4
• Figure 10 · p. 4

Argument and organization

1. Problem and contribution

   Attributes poor image privacy–utility behavior to representation mismatch and then introduces bit planes as the intervention.

2. Argument sequence

   Places threat model and privacy definitions before obfuscation, randomization, budget optimization and formal analysis.

3. Evidence and verification

   Table 1 labels the guarantee type of each baseline, while subsequent attack images and utility curves answer separate empirical questions.

Problem, claim and contribution

Attributes poor image privacy–utility behavior to representation mismatch and then introduces bit planes as the intervention.

Abstract and Section 4, pp. 1 and 4 · Main paper · Additional source 2

Argument and section order

Places threat model and privacy definitions before obfuscation, randomization, budget optimization and formal analysis.

Sections 3–4, pp. 3–5 · Main paper · Additional source 2

Figures, captions and visual explanation

Figures 2–3 expose what different bit planes and color channels retain; the explanation uses actual decomposed images instead of a purely symbolic flow.

Figures 2–3, p. 4 · Main paper · Additional source 2

Tables, comparisons and evidence

Table 1 labels the guarantee type of each baseline, while subsequent attack images and utility curves answer separate empirical questions.

Table 1 and Figures 4–7, pp. 6–8 · Main paper · Additional source 2

Appendix and reproducibility

Complete proofs and formal attack definitions are separated from additional empirical evaluations and ethical discussion.

Supplement Appendices A–E, pp. 1–4 · Main paper · Additional source 2

Clarity and writing conventions

The main privacy analysis explicitly separates composition from post-processing, keeping the proof mechanism named.

Section 4.4, p. 5 · Main paper · Additional source 2

What to reuse—and what not to infer

Transferable lesson: State the unit protected by a theorem next to the guarantee, then distinguish that guarantee from visual obscurity and downstream utility.

Boundary: Pixel-level, block-level and whole-image guarantees are not interchangeable; empirical reconstruction failure does not strengthen the formal guarantee.

Apply this lesson using the argument and evidence worksheet.

Inspection record and sources

Checked

2026-09-26

Reading status

Writing-focused manuscript scan + selected visuals inspected

Main text

Writing-oriented scan throughout Sections 1–6, PDF pp. 1–8; references pp. 9–10: abstract/framing, section sequence, figure/table captions, evaluation organization and conclusions; not an exhaustive technical verification.

Appendix / supplement

Writing-oriented supplement scan: Supplement Appendices A–E, pp. 1–4: formal attack definition, budget derivation, complete proofs, training/ablation details and ethics. Video/code assets were not executed or assessed.

Visually inspected PDF pages

4, 6

This is a writing-focused scan of the manuscript and the stated supplementary scope: framing, organization, visual explanation, evidence presentation and wording. It is not a line-by-line proof audit, reproduction of results or exhaustive scientific review.

• Official CVF open-access CVPR 2026 accepted-paper PDF · 10 pages
• Official CVF supplementary PDF · 4 pages