- Rating
- 2(+1)
- Confidence
- 2(−1)
- Informativeness
- 3(+2)
- Presentation
- 2(+1)
- Soundness
- 2(+1)
Read review
Paper summary
The paper studies attacks on reference speech used by nonautoregressive speech synthesis systems It constructs auxiliary representations with an audio codec and a language model and optimizes reference audio to increase representation differences The resulting perturbation is evaluated across speech synthesis models and defense configurations The paper uses attention differentials and trajectory sensitivity to motivate the mechanism and speaker similarity to measure its effects.
Critical strengths
- Target query-free attacks on reference speech are a relevant robustness problem, and transfer across synthesis architectures is worth investigating.
- The appendix includes approximately energy-matched sign randomization and temporal shifts, providing more informative evidence than a random noise comparison alone.
- Attack settings, the reference prompt, evaluation model, and some paired uncertainty estimates are documented.
Critical weaknesses
- The stated optimization is stationary at initialization. Section 3.1 sets x=x_ref, while Equation 15 uses L(x)=||z(x)-z(x_ref)||². Consequently its gradient is zero, and every sign-gradient update in Equation 18 leaves the input unchanged. The straight-through estimator does not remove the zero representation residual. No attack random start or other symmetry-breaking mechanism is specified in A.4.2. This is a decisive inconsistency between the stated algorithm and the reported nonzero perturbations, although it does not establish what unpublished code actually does.
- The acoustic-to-language projection is not reproducible. The cited LLaMA is a text language model; an affine map from codec features does not establish semantic alignment. Training, initialization, data, and checkpoints for W_proj are missing. An untrained projection might still support a feature attack, but would not substantiate the semantic interpretation. LLaMA
- Appendix uses one reference utterance and one perturbation across targets. Multiple generated sentences and datasets do not establish robustness across reference speakers or prompts. Sentence-level confidence intervals do not account for prompt-selection variability.
- Speaker similarity does not measure semantic collapse, intelligibility, or catastrophic noise. The imperceptibility claim also needs perceptual evidence beyond the reported SNR and norm budget. Clean and adversarial prompts have different stated sampling/encoding paths that require matched controls.
- The local linearization does not prove amplification: the propagator may contract, and no relevant lower bound or perturbation alignment is established. Auxiliary-model feature displacement does not demonstrate causal attention disruption in the target synthesizer.
- The adversarial-training defense lacks sufficient training/checkpoint details, and most defenses lack clean-plus-defense controls. Existing local random-smoothing controls should be credited, but do not establish all defense comparisons.
Questions for authors
Q1. How does the implementation produce its first nonzero update when Section 3.1 initializes at the clean reference and Equation 15 then has zero gradient? Please provide initialization code and initial loss/gradient norms, identifying any random start or additional objective.
Q2. How are W_proj and b_proj initialized or trained, using which data, objective, and checkpoint? What evidence establishes acoustic-to-language semantic alignment?
Q3. Do all main experiments reuse the single reference utterance and perturbation in Appendix 4.2? What are the outcomes and failure cases across independently selected reference speakers and clips?
Q4. Can you provide a clean control with identical resampling/PCM processing and intelligibility/listening evidence separating identity degradation, semantic collapse, and audible noise?
Q5. What parameters, data, training budget, and held-out protocol define “100% adversarial training,” and how does each defense perform on clean inputs?
3 comments
Reply to Reviewer [2/3]
3. Independent speakers and reference recordings (Q3)
The main five-model benchmark deliberately reuses one constructed adversarial reference across target architectures and synthesis texts, testing transfer without model-specific adaptation. The new reference-diversity experiment separately evaluates six independently selected recordings from three speakers, with two recordings per speaker, fixed selection rules, and durations of 3–6 seconds. Each recording receives its own seed-42 attack, reused across F5-TTS, E2-TTS, and ten texts per target (the revised Appendix A.7, Table A7).
All 120 paired comparisons decrease SIM. Across references, the mean changes are on F5-TTS and on E2-TTS, with between-reference standard deviations of and . The weakest reference-level decreases remain and , respectively. Table A7 reports every reference, making variation and the weakest observed cases directly inspectable.
Uncertainty is evaluated at the speaker level: 10000 cluster-bootstrap replicates retain both recordings and all generated texts for each sampled speaker. The exploratory 95% intervals are and . Leaving out each speaker in turn also preserves negative mean changes on both targets. These results directly establish persistence across the tested independent recordings, with speaker-cluster uncertainty distinguished from text-conditional intervals.
4. Matched processing and distinct output effects (Q4)
Identical external resampling and PCM serialization preserve the attack effect. The revised Appendix A.8 compares native clean audio (16-kHz FLOAT), processed clean audio (24-kHz PCM16), and attacked audio (24-kHz PCM16). Processing the clean reference changes mean SIM by only on F5-TTS and on E2-TTS. In contrast, attacked-minus-processed-clean changes are and , corresponding to 64.81% and 65.75% relative decreases. Every matched text pair decreases SIM, and both paired 95% intervals exclude zero (Tables A8–A11).
The same outputs receive three complementary measurements (Table A12):
| Target | SIM: clean → attack | WER: clean → attack | CER: clean → attack | UTMOS22: clean → attack |
|---|---|---|---|---|
| F5-TTS | 0.7099 → 0.2498 | 8.27% → 9.00% | 3.40% → 3.08% | 2.8493 → 1.4666 |
| E2-TTS | 0.7803 → 0.2672 | 9.25% → 19.46% | 3.46% → 8.68% | 2.0885 → 2.0628 |
WER/CER pool edit counts under fixed Whisper-base decoding and text normalization, with 411 reference words and 1821 characters per model–condition cell. F5-TTS shows pronounced predicted-quality degradation, while E2-TTS shows substantial transcription degradation. Both show strong identity degradation. These measurements distinguish the affected output dimensions.
Input strength is characterized separately across seven matched reference pairs: SNR ranges from 18.10 to 21.57 dB, with mean 19.1350 dB. The largest serialized difference is 328 PCM quantization steps, or , following floating-point optimization at . No input pair reaches full-scale endpoints. The revised paper therefore describes input strength in measured amplitude and energy terms, and reports UTMOS22 as predicted output quality.
5. Direct target measurements ground the mechanism
The revised Appendix A.9 measures the target synthesizer after the attack is fixed. F5-TTS clean/attack pairs share reference length, gain, initial noise, and solver grid, and instrumentation reproduces the corresponding PCM outputs. Across three texts, the maximum increases in attention mass from generation-region queries to reference-frame keys are 71.63, 75.95, and 75.26 percentage points, sampled over layers, solver evaluations, and guidance branches. This is the relevant frame-key quantity in F5-TTS's single-stream architecture.
The trajectories begin from identical synthesis states, , and separate at every recorded point, reaching final RMS distances 3.0080, 3.4837, and 2.9179. All 192 Euler updates across the six runs are reconstructed from recorded states, velocities, and time grids. Section 3.3 expresses the local response as a conditioning-driven sensitivity integral whose magnitude depends on the trajectory Jacobians and perturbation direction. The empirical result is progressive separation under the evaluated attacks. The differential analysis identifies its propagation pathway.
The independent CTC diagnostic further records decreased intended-order advantages on all three texts: , , and nats per symbol, with intended order still preferred. This provides an additional explicitly defined output-level alignment measurement. All target instrumentation is post-construction, preserving the target-query-free attack setting.
Reply to Reviewer [3/3]
6. Full defense controls and specified AT checkpoints (Q5)
The revised Appendix A.11 evaluates all five models under all eight defenses in four conditions: clean (C), defended clean (CD), attack (A), and defended attack (AD). Tables A18–A27 report speaker fidelity, transcription, and predicted quality, while , , and separately quantify clean-side change, attack-side recovery, and residual attack effect.
39 of the 40 residual SIM point estimates are negative. The exception, E2-TTS with TV, accompanies a defended-clean SIM decrease from to . The design therefore makes each defense's clean-fidelity cost visible. Recovery in one output dimension can coexist with persistent identity loss: MaskGCT AT improves attack-side WER from to and UTMOS22 from to , while retaining residual SIM with paired 95% interval .
For AT, “100%” specifies offline adversarial-reference coverage of all 180 training pairs. The 244-pair LibriSpeech dev-clean manifest separates 180 training pairs/24 speakers, 32 checkpoint-validation pairs/eight other speakers, and 32 hyperparameter-development pairs/eight further speakers. Equation (58) combines adversarial and clean student-feature consistency against a frozen clean teacher, with . The training plan specifies AdamW, learning rate , zero weight decay, gradient clipping 1.0, microbatch size one, accumulation over four microbatches, and a 100-update budget. Checkpoints are selected using mean clean/adversarial SIM on the separate 32-pair validation set.
The evaluated checkpoints are MaskGCT u050, ZipVoice step100, LEMAS-TTS u025, and F5-TTS/E2-TTS u075. All five retain negative defended attack–clean SIM differences with individually paired 95% intervals excluding zero (Table A28). This establishes persistent speaker-fidelity degradation at the explicitly documented checkpoints and training budgets.
Reply to Reviewer [1/3]
Thank you for identifying the implementation, reference diversity, output measurement, and defense controls that are central to evaluating this threat model. The revision provides direct evidence for each: nonzero initialization diagnostics, a precisely specified pretrained surrogate, independent reference recordings, matched audio processing, instrumented target dynamics, and clean/attacked evaluations with and without every defense. These results establish a reproducible target-query-free attack whose substantial speaker-fidelity degradation persists across the evaluated references and defensive settings.
1. Random initialization activates the objective (Q1)
The implemented attack uses a bounded random start. The revised Section 3.1, Appendix A.4.2, and Appendix A.6 now specify
\widetilde{x}^{(0)}=\operatorname{clip}_{[-1,1]}(x_{\mathrm{ref}}+u).$$ Equivalent minimal pseudocode for this operation is: ```python u = torch.empty_like(x_ref).uniform_(-eps, eps) x = (x_ref + u).clamp(-1.0, 1.0).detach().requires_grad_(True) ``` The random start provides the initial representation residual. The STE propagates its gradient through quantization. These two components have distinct roles. The seed-42 diagnostic confirms an initial loss of **369,834.5625**, an input-gradient $\ell_2$ norm of **18,562,286**, and nonzero gradients at **all 106,920 waveform coordinates**. The first maximum update is **0.002000004**, matching the specified step size $\eta=0.002$ up to floating-point rounding. An independent seed-42 process reproduces all **201 recorded states** and the final floating-point and PCM waveforms in the tested environment. With attack seeds 42, 43, and 44, **all 120 clean–attack text pairs** decrease SIM. Across-seed mean changes are $-0.4800\pm0.0189$ on F5-TTS and $-0.5571\pm0.0458$ on E2-TTS (Appendix A.7, Table A6). Seed 42 yields the smallest mean decrease of the three on both targets. # 2. Checkpoint-defined audio representations (Q2) **The surrogate uses the speech-pretrained `ICTNLP/SLED-TTS-Libriheavy` checkpoint.** `Llama1` identifies its LLaMA-style Transformer architecture: 12 layers, hidden dimension 1024, and 16 attention heads. The revised Appendix A.6 specifies exactly which components enter JASDA: the pretrained projection, normalization, and Transformer backbone. The checkpoint's TTS-specific generation modules are not used in attack construction. The interface is a checkpoint-loaded $128\rightarrow1024$ affine projection followed by affine LayerNorm with $\mathrm{eps}=10^{-6}$. Its weight, bias, and normalization tensors are loaded without reinitialization and remain frozen, together with the backbone. At attack time, these pretrained parameters provide the audio-specific mapping without additional projection fitting. JASDA optimizes only the reference waveform, using the summed squared displacement of final contextual audio representations. Independent checkpoint loads reproduce intermediate and final features in numerical precision. We also provide a speaker-disjoint audio–transcript retrieval probe using 200 recordings from 20 speakers, with training/validation/test partitions of 12/4/4 speakers (Appendix A.10, Tables A14–A17). For ten within-speaker candidate transcripts, the full surrogate and codec-only features each obtain R@1 $=0.10$ (Top-1 Recall), equal to chance among ten candidates, and all permutation $p$-values exceed $0.10$. This reports the actual transcript-discrimination behavior of the temporally pooled linear probe. The revised methodology uses the precise description **contextual audio representations**, while content effects are evaluated directly through transcription and transcript-order measurements on generated speech.