- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 1
Read review
Paper summary
This paper presents a query-free attack that combines gallery retrieval, embedding averaging, and inversion to generate a face with a chosen demographic label while preserving acceptance as a reference identity. A rank-consensus variant aims to improve transfer across recognizers.
Critical strengths
- A meaningful zero-query setting. Once the reference image and public resources are available, the attack requires no queries to the deployed verifier. Transfer to two commercial APIs shows a relevant offline attack surface.
- Broad empirical coverage. The paper covers several operating points, inverse models, galleries, surrogate subsets, and commercial services. Testing against another image of the same identity is especially useful because it reveals an important limitation.
Critical weaknesses
- The theory and implementation do not fully match the stated method. Coverage is defined as , but PCA optimizes the expected squared norm, so the claimed PCA optimality does not follow. The analysis also omits the decoder and target-model re-encoding used by the actual attack.
- The evaluation does not yet show target-agnostic, identity-level impersonation. The main test verifies against the same image used to build the attack. With another image of the same identity, Ours-C drops from 96.1–98.1% to 54.1–57.1% at FMR , and from 88.2–92.2% to 37.4–38.9% at . Some “held-out” targets also inform the analyses or share training data with surrogates.
Questions for authors
- Which quantity was plotted in Figures 1 and 6: , , or the square root of the latter? Please revise the PCA argument accordingly.
- Can the authors remove all exact, near-duplicate, and same-identity gallery items related to LFW, CFP-FP, and AgeDB, then rerun the attack using a separate enrollment image for verification?
Thank you for examining the formulation and evaluation. We correct the PCA-optimality inference identified in your review. Our controlled evaluations support reference-conditioned composition and surrogate consensus for the stated joint objective. To explain how the evidence supports these claims, we clarify the intended roles of construction analysis under available models, target verification against the supplied reference, and supplementary cross-photo evaluation.
W1/Q1. Coverage and the corrected inference. Submitted Figures 1(a) and 6 plot E[∥B⊤E(x)∥2], the mean projection norm. This is mean cosine similarity to the nearest subsphere point.
PCA's squared-norm optimality does not establish optimality for this unsquared measure. We removed the resulting claims of maximal coverage and no room for improvement. Section 3.2 now confines the conclusion to the observed coverage–validity trade-off within the evaluated PCA family. The k/d reference is the RMS projection norm for uniform unit vectors and an upper bound on their mean norm.
Direct gallery selection and averaging do not rely on this optimality inference.
W1. Decoder and target re-encoding. Submitted validity V=Pr[a(D(z))=c] includes decoding, and joint ASR evaluates chosen-class assignment and target acceptance of generated images. Section 4.2 separately studies cross-model gallery selection.
We connect these stages on 1,500 reference–class cases, reporting mean cosine to the corresponding reference:
Consensus increases target similarity despite lower source-composition similarity and comparable generated-image source similarity. Section 5.2 also shows that coefficient fitting increases target identity acceptance but decreases chosen-class assignment and joint success. Appendix B.2 tests decoded validity under projected inputs and alternative models.
W2. Additional cross-photo generalization. Our primary objective is to generate a chosen-attribute image accepted against the supplied reference (Section 2), which the main evaluation directly tests. Acceptance against another photograph of the same identity is an additional generalization property.
The submission included a supplementary cross-photo evaluation to characterize this additional capability. Following your suggestion, we expanded it from 773 cases to all 57,658 eligible reference–class cases with benchmark-labeled same-identity partners from LFW, CFP-FP, and AgeDB.
On this population, Ours-C's construction-reference ASRs at 10−4 are 89.5% and 93.9%, respectively. The decrease quantifies the extent of additional cross-photo generalization. Ours-C remains highest under both verifiers and operating points, providing additional evidence of acceptance across photographs (Appendix D.1).
Q2. Sensitivity to reference–gallery overlap. We screened galleries using ArcFace scores at the threshold calibrated to FMR 10−6. Potential same-identity matches are flagged for 501 of 115,390 reference–class cases (0.43%). This is a score-based sensitivity control rather than exhaustive identity-disjoint cleaning and regeneration.
For Ours and Ours-C, excluding cases whose selections contain any flagged gallery image changes ASR by less than 1.0 percentage point at FMRs 10−4 and 10−5 (Appendix A.2). Applying the screen to separate-photo verification leaves 54,694 common cases for all three methods. Across both verifiers and FMRs, the maximum absolute ASR change is 0.28 percentage points. Ours-C remains highest, followed by Ours and NAFG (Appendix D.1).
W2. Target roles and broader evaluation. TransFace-L and ViT-KPRPE are excluded from selection and construction but appear in evaluation analyses. Table 3 discloses their shared training datasets with TopoFR and AdaFace; their target role does not imply independent training or development.
The submitted evaluation also covers AWS and Tencent Cloud, whose architectures and training data are undisclosed. Ours-C exceeds NAFG in every chosen class at both service thresholds (Table 1).
We additionally evaluate Glint360K-trained TopoFR-R100 and TransFace-L across all 115,390 cases (Appendix D.7). Glint360K includes MS1MV2, so this broadens checkpoint coverage without establishing training-disjoint transfer. At FMRs 10−4 / 10−5, Ours-C achieves 91.2% / 64.5% and 60.1% / 34.4%, respectively, exceeding both Ours and NAFG across all evaluated classes at both operating points.