- Rating
- 1
- Confidence
- 3
- Informativeness
- 1
- Presentation
- 1
- Soundness
- 1
Read review
Paper summary
This paper proposes an evaluation framework for LLM-based deanonymization attacks. The authors argue that raw attack performance is misleading without appropriate reference levels. On this basis, the framework defines a floor and a conditional ceiling, as well as a pre-run statistical screening procedure, to assess whether a benchmark can detect improvements over trivial baselines. Experiments on synthetic benchmarks and existing attack systems reveal inflation in existing results with limited statistical distinguishability.
Critical strengths
S1. The paper focuses on a relevant and real concern that existing deanonymization performance may be inflated due to scoring conventions and dataset characteristics.
S2. The labeled-eveidence ceiling and screening procedure offer a potentially useful way to identify benchmark limitations.
Critical weaknesses
W1. Clarity and organization are a major problem of this paper. The paper is extremely difficult to follow. Core concepts, including "persona", "null attacker", "claim volume", "labeled-evidence ceiling" and many more, are undefined at all. The abstract and introduction are dominated by numbers and these specialized, but undefined terminologies, rather than a clear statement of the research question and contributions.
W2. The figures are clearly AI-generated and poorly organized. Figures 6 to 10 pack multiple metrics, baselines, intervals, and annotations into dense plots with overlapping or very small labels. It would be much clearer to present them as conventional tables. A substantial restructuring and simplified figures are needed.
W3. Many experiment setups are missing. The Q1/Q2 distinction also appears hard to follow. What constitutes a successful attack in each setting? What information does the attacker have in each dataset and baseline? How are ground-truth identities and attributes constructed?
W4. The principal agent audit relies on a small dataset of only 20 synthetic personas, with a single run per condition. Larger-scale benchmarks, repeated independent runs, and evaluation of different attack policies are needed to support the claims made in this paper.
W5. Novelty and the definition of the floor need stronger justification. Based on the definition in the paper, the floor is essentially the maximum over a manually selected, non-exhaustive family of trivial baselines at a pre-specified claim volume. The ceiling is a count of ground-truth links satisfying an evidence-matching rule. Technically, both are closely connected to established practice in existing benchmark evaluation, entity resolution, and power analysis. It is unclear which components are genuinely novel, and what conclusions are unique contributions from this paper, instead of simpler baseline comparisons.
Questions for authors
See weaknesses.
4 comments
Response to Reviewer iEnF (2/2)
W4. The audit uses 20 synthetic personas and a single run per condition.
Both are stated as limits in Section 8, and the first is one of the paper's findings: the pre-run screen shows that 20 personas of that corpus cannot separate a rule-following attacker from random (Sec. 7). The audit is listed as "a worked example" among the contributions, and Section 8 says that "the external evidence here is therefore the SynthPAI re-analysis and the published systems rather than the audit". The evidence beyond 20 personas is:
| Evidence | Scale | Ref |
|---|---|---|
| SynthPAI re-analysis | 18 models, 144 model-by-attribute cells, 700 human-verified labels | Sec. 5 |
| Population floor | 45,222 census records; 1,000 sampler personas | Sec. 5; App. C |
| Audit across corpora | 4 corpora, 80 personas pooled | Fig. 7 |
| Screen | 20 corpora (up to 1,000 personas), 540 cells | Table 8; App. H |
| Other attack policies | 6 published systems, 4 baselines, 5 single-tool ablations | Figs. 6, 8, 9; App. I |
On single runs: each cell is one temperature-0 transcript, so we have no estimate of run-to-run variance, and Section 8 says so. The declared test takes its variance across personas, which is the unit the conclusions are about.
W5. The floor is a maximum over a hand-picked, non-exhaustive family; the ceiling is a count. What is new?
On non-exhaustive: yes, and Section 3 says so (l. 150–151: the family is "exhibited rather than exhausted", so "every lift is an upper bound"). The direction is safe. Adding a null can only raise F and lower a lift. A verdict of "does not clear the floor" therefore survives any larger family, and that is the audit's verdict on the seeded task.
On novelty, Section 2 names the origin of each part. What is borrowed and what is added:
| Component | Prior practice | What we add | Conclusion that needs it |
|---|---|---|---|
| Floor | Excess over one naive guess (Anonymeter); pool chance in closed-set linkage | A null family limited to a declared claim volume, for tasks with no candidate pool | Recall below random at v, above random at matched volume |
| Harness credit | Filtered metrics in link prediction | Complement scoring for a seed-union harness | Identification 1.000 and linkage F1 0.562 conceded |
| Test | A test chosen per result | One declared test for every lift and contrast, with a declared correction family | 65 of 144 SynthPAI cells clear; none on age or income |
| Ceiling | Pair completeness in entity resolution | The same count on labelled evidence under the attacker's own declared rule, with no model call | Only 10 of 121 pairs directly corroborated on SeqBench-20 |
| Screen | Power analysis with an assumed effect size | The key and the rule fix the largest lift, so no effect size is assumed; three verdicts | SeqBench-20 unresolvable; four corpora need 42–60 personas |
We claim three things: agentic deanonymisation results are being reported without these checks, the task needs these specific adaptations for a floor to be defined at all, and applying them changes what the published numbers say.
Dear Reviewer iEnF,
We greatly appreciate the time and effort you’ve invested in reviewing our work. As we are now two days away from the discussion deadline, we wanted to reach out regarding our rebuttal, which we submitted earlier.
If possible, we would be grateful for any feedback you might be able to provide, as this would give us the opportunity to engage in a productive discussion before the deadline. We’re eager to address any remaining questions or concerns you may have about our paper.
We understand that you likely have a busy schedule, and we truly appreciate your valuable insights and expertise in this process.
Thank you for your time and consideration.
Thanks for the additional explanations. However, my concerns regarding the presentation and clarity remain. I encourage the authors to fully revise the paper. I'll keep my current rating.
Response to Reviewer iEnF (1/2)
Thank you for the detailed review. Line numbers refer to the submitted PDF.
Most of these terms are defined, but too briefly and not always at first use. Their meanings, with where the submission defines each:
We put numbers in the abstract and introduction because this is a measurement paper and we wanted each claim to carry the value that supports it. We accept that this buried the research question, and the revised introduction states it first: how much of a reported deanonymisation score would a procedure that reads nothing also obtain, and can the benchmark tell the two apart?
Figures 6–10 are tables with an interval drawn beside each row. They are generated by scripts from the stored run reports, and we chose the format so that every score sits on the same line as its null and its interval, which is the paper's argument. We agree that they are too dense. In the revision every result figure has a conventional table with the same numbers, and the figure points to it. For Figures 5, 6, 8 and 10 these are the appendix tables of the submission (Tables 1, 8 and 10–16). For Figures 7, 9 and 11 the revision adds three new appendix tables, generated from the same files as the figures and checked equal to what each figure draws. The audit's scores are now also a table in the main text (Section 6).
Ground truth: the identities are fabricated, so the handle-to-person map and each persona's attributes are exact by construction (Fig. 3; App. E). Leak labels come from a per-post detector on the audited corpora (Sec. 4). Every metric is defined with its denominator in Table 4 (App. B), the corpora in App. E, and the comparison attackers and what each reads in App. I. The revision has this table in Section 4.