- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 1
Read review
Paper summary
This paper presents MARC, a multi-bit watermarking scheme for autoregressive audio generation. It tackles token substitution and temporal desynchronization caused by the audio detokenization, compression, and retokenization pipeline. To address this, MARC groups tokens into clusters by combining embedding similarity with cross-codec confusion patterns so that mutually confusable tokens share the same cluster.
Critical strengths
-
Beyond watermark detection, the paper addresses how to recover multi-bit payloads after audio re-encoding. It separates token substitution from temporal misalignment, making the research problem much better defined than simply boosting detection rates on clean audio.
-
The evaluation covers speech, dialogue, and music generation across 21 audio perturbations and watermark overwriting attacks. This helps delineate the method's effective operating regime.
Critical weaknesses
-
Section 4.3 states that the verifier takes a candidate message as input to guide the alignment search, and the match-rate parameter during decoding is also computed using . The reported results reflect recovery performance aided by a candidate message and auxiliary checksum information, rather than blind message extraction solely from the audio without prior knowledge of the payload. This paper needs to clarify how much these auxiliary inputs actually contribute to the reported accuracy.
-
"The paper states that during verification, the verifier can use the provided attack type and processing parameters to construct waveform variants. It is necessary to distinguish between recovery when the audio processing history is known and blind recovery when the transformation history is completely unknown. The current presentation does not clearly specify which codecs are used during cluster construction versus which test codecs are held out as unseen, leaving the method's generalization to unknown codecs unclear.
Questions for authors
-
How much information can still be recovered without providing the ground-truth candidate message? Could you remove the guidance of from both alignment and scoring, and report the bit accuracy and full-message recovery rate before and after checksum correction? Also, since the default payload is only 12 bits, how much information can a trivial enumeration baseline recover using only the public checksum and secret suffix without reading the audio at all?
-
How is the FPR calibrated for the full detection pipeline? After searching over multiple windows, offsets, and waveform variants, is the final decision threshold recalibrated to account for multiple testing? Could you compare the TPR across all methods on the same negative sample set at a fixed FPR, rather than only comparing ?
-
How does the method perform when the attack type and parameters are unknown? Could you provide unified decoding results without using attack labels, and clearly separate the codecs seen during cluster construction from unseen test codecs? What is the computational time overhead required for this search?
7 comments
Response to Reviewer BQvF (Part 2/4)
W2: Construction codecs and unseen test codecs.
Section 4.1 distinguishes ordinary retokenization from codec-processed confusion and combines them in the codec union. The test suite includes reconstruction methods not used to construct the cluster map. The verified model construction split is:
Response Table R1. Construction exposure.
| Transformation | Used in the cluster construction |
|---|---|
| Ordinary model retokenization | ✓ |
| MP3 | ✓ |
| Opus | ✓ |
| EnCodec | ✓ |
| DAC | ✓ |
| External SpeechTokenizer | × |
| FACodec | × |
| SoCodec | × |
| SemantiCodec | × |
| VoiceCraft–EnCodec pipeline | × |
Ordinary model retokenization differs from the external SpeechTokenizer attack. VoiceCraft–EnCodec is held out as a reconstruction pipeline while sharing the EnCodec component with a construction codec. This makes the exposure definition precise at the codec/pipeline level.
Main Table 3 reports 98% bit accuracy under FACodec and 97% under SemantiCodec on SpiritLM/FinanceQA. Appendix A.2, Tables 9–11 further evaluate codec parameters and waveform perturbations. These results support transfer beyond the construction transformations. The construction split concerns offline representation learning. The same receiver policy is used at test time without being told which transformation was applied.
Response to Reviewer BQvF (Part 3/4)
Q2: Complete-pipeline FPR and comparable detection metrics.
We have made the metric choice and its operating-point interpretation explicit in Section 5.1.
Why report ? In the evaluated 1%-target-FPR condition, the cluster detection TPR is already 100% for all four methods. Thresholded TPR therefore has little remaining ability to distinguish their detection evidence. Following HiPT [1], provides an additional description of how strongly the observed token/cluster statistics support watermarking.
Why also report multi-bit TPR? Following VINE [2], the multi-bit score is the fraction of extracted bits matching the target message. It evaluates recovered-message agreement, beyond detecting a statistical watermark signal. The zero-bit baselines output no -bit payload estimate, so this particular message-matching TPR cannot be computed from their native outputs. Their ordinary presence-detection performance is compared at the statistical-detection level, as shown below.
Response Table R2. Distinct evaluation quantities.
| Metric | Computation | Purpose |
|---|---|---|
| Cluster TPR | Fraction of watermarked samples passing the statistical detector's threshold | Presence detection |
| Negative log of the median cluster p-value | Distinguish evidence when thresholded TPR saturates | |
| Multi-bit TPR | Fraction whose extracted-bit matching score passes its target-FPR threshold | Message verification |
| Average fraction of correctly recovered bits | Payload recovery quality |
Response Table R3. Saturated statistical detection in the evaluated setting.
| Method | Target FPR | Cluster TPR |
|---|---|---|
| AR speech WM | 1% | 100% |
| Aligned-IS | 1% | 100% |
| HiPT | 1% | 100% |
| MARC | 1% | 100% |
All methods in Table R3 use the same unwatermarked evaluation set, with method-specific thresholds calibrated at the common 1% target FPR.
For the VINE-style score , matching TPR and FPR are the fractions of watermarked and unwatermarked inputs satisfying the same rule . The extracted message is fixed before its reference is used to compute this score. Thus, multi-bit TPR counts accepted samples, whereas averages bit agreement.
Complete-search calibration. Section 4.3 uses the same feature construction for received inputs and frozen null references, and Eq. (6) defines the final OR decision. The independent measurement is:
Response Table R4. Empirical FPR after the complete search.
| Method | Unwatermarked inputs | False positives | Empirical FPR |
|---|---|---|---|
| MARC | 500 | 3 | 0.60% |
The final count includes every enabled branch, waveform variant, window, and offset. Table R4 reports the empirical FPR of the complete multi-bit verification protocol on unwatermarked inputs. The same fixed verification rule is applied to watermarked inputs to measure the corresponding multi-bit TPR. The 1% target and 0.60% empirical test rate are consistent: the target specifies the operating level, while the independent test count reports the frozen protocol's observed behavior. Table R3 separately concerns cluster/statistical detection.
Revision: Section 5.1 now states why cluster TPR saturation motivates , cites VINE for message-matching verification, and explains why the zero-bit baselines have no corresponding payload-matching output.
References
[1] Georgios Milis, Yubin Qin, Yihan Wu, and Heng Huang. Hidden in Plain Tokens: Simply Robust, Gradient-Free Watermark for Synthetic Audio. ICML 2026.
[2] Shilin Lu, Zihan Zhou, Jiayou Lu, Yuanzhi Zhu, and Adams Wai-Kin Kong. Robust Watermarking Using Generative Priors Against Image Editing: From Benchmarking to Advances. ICLR 2025.
Response to Reviewer BQvF (Part 1/4)
Dear Reviewer BQvF,
Thank you for emphasizing the connection between codec robustness, payload recovery, and the verification protocol. We explain the receiver step by step and provide common-pipeline detection, construction-exposure, and computational evidence.
Recovery uses the received waveform and registered keys, without a supplied ground-truth message. Section 4.3 now makes this procedure explicit. The receiver applies the same fixed steps to every input:
The estimated rate ηa(m) is computed from the candidate's audio support, not agreement with the embedded reference. The pri-key constrains combinations and supplies consistency evidence. The pub-key supplies a fixed ranking bonus and final validation. The reference bitstring is compared only after the output is fixed. No attack label or actual processing parameter is an input to this procedure.
Auxiliary-information contribution. Thank you for asking us to distinguish the contribution of auxiliary validation. D3 in revised Table 4 isolates the pub-key ranking contribution: removing its bonus reduces bit accuracy from 98.17% to 80.75%, while TPR remains 94% and the cluster statistic remains 37.08. Section 4.3 distinguishes candidate selection from final validation. Audio evidence and key consistency determine the selected candidate. The final check determines whether that candidate is emitted. This comparison quantifies the benefit to payload selection separately from detection performance. Section 5.5 explains the corresponding recovery mechanism.
Role of the metadata-only baseline. Given both registered values, enumeration of the short 12-bit space can identify the registered target. The verification task also requires audio evidence supporting that target: identifying a message from metadata is not a positive watermark decision for the received waveform. The complete multi-bit verification protocol combines audio-evidence screening and key-assisted recovery, with an observed 0.60% complete-search FPR on unwatermarked inputs. We therefore describe the protocol as registered-key-assisted extraction and verification. Confidentiality, when required, is a deployment-layer property of the selected encryption/access-control mechanism and key management. Section 3 specifies the watermark threat model separately from cryptographic secrecy.
Revision: Section 4.3 now explicitly defines the candidate-specific rate, audio score, two key roles, and final validation in Eq. (7). Table 4 and Section 5.5 add the public-check ranking ablation.