- Rating
- 2
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
LipMamba combines constraints on selective state-space dynamics with robustness-oriented fine-tuning to mitigate hidden-state poisoning. The paper provides theoretical analyses and reports substantial improvements on RoBench-25 and HarmBench with a modest perplexity cost.
Critical strengths
- The paper addresses a concrete vulnerability in selective SSMs and proposes a defense that directly modifies the underlying state dynamics.
- The reported robustness gains are substantial at both 130M and 370M scales. Component ablations, step-size sensitivity analysis, and measurements of clean performance and latency provide useful initial evidence about the method’s benefits and costs.
Critical weaknesses
-
A matched fine-tuned unconstrained baseline is missing. Section 6 evaluates unconstrained Mamba as released, while LipMamba receives additional WikiText-103 adaptation. The “without adversarial training” ablation still evaluates an adapted constrained model, rather than an unconstrained model receiving equivalent fine-tuning. Consequently, attributing the improvement from 23.4% to 61.9% to “the architecture alone” is not sufficiently supported. The comparison provides evidence for the overall pipeline, but does not isolate the constraints’ contribution. An unconstrained Mamba baseline under matched fine-tuning conditions is needed.
-
The evaluation is unclear about attacks adapted to the defense. Table 1 and the limitations section refer to published HiSPA triggers, but do not clearly establish whether they were reoptimized against each trained LipMamba model. Since the defense modifies the mechanism targeted by the original attacks, resistance to existing triggers may not imply resistance to adapted attacks. The authors should specify the target checkpoints, attack objectives, budgets, and restarts, including whether attacks optimize downstream answer errors. Embedding-space PGD addresses a different threat model and does not resolve this uncertainty.
-
The experimental coverage does not adequately characterize the robustness–utility trade-off. The discrete-attack evidence centers on HiSPA, while clean utility is assessed mainly through RoBench-25 accuracy and WikiText-103 perplexity. These measurements are useful, but do not directly test whether constraining state updates impairs useful forgetting, revision of previously supplied information, or context switching. Such effects are plausible because input-dependent information selection is central to Mamba’s functionality; they are not established failures of LipMamba. A focused evaluation of normal information-update behavior would help determine whether the reported perplexity cost adequately reflects the practical trade-off.
-
The presentation makes the central contribution difficult to assess. State-retention analysis, continuous-input sensitivity, GloRo-style training, and PAC-Bayesian regularization are introduced without a sufficiently clear account of how each supports the primary discrete-poisoning objective. Figure 2 further juxtaposes local-radius-based LL-Acc with direct PGD accuracy for SpectralGuard. Although disclosed in the caption, these metrics measure different properties. A concise overview connecting design choices, theoretical scope, and evaluation metrics would substantially improve clarity.
Minor comments.
- The proof of Theorem 3 on page 14 is densely typeset. Separate displayed equations and explanations of the main steps would improve readability.
- Page 2 promises scripts to regenerate all tables and figures, whereas docs/REPRODUCIBILITY.md in anomyous github states that Table 1’s numbers were not produced by this repository at the time of writing. Please clarify how the released code relates to the reported experiments. This issue has not influenced my rating.
Questions for authors
- Matched training controls: How does unconstrained Mamba perform under the same fine-tuning conditions? What improvement remains attributable to the proposed constraints?
- Adaptive attack evaluation: Were HiSPA triggers reoptimized against each trained LipMamba checkpoint? Please specify the objectives, budgets, and restarts, including whether optimization targets downstream answer errors.
- Robustness–utility trade-off: How do the constraints affect normal information revision and context switching? Can the authors provide a focused evaluation beyond perplexity and clean retrieval accuracy?
4 comments
Thanks for the additional experiments and clarifications. The matched baselines, adaptive attacks, and fact-update test address most of my original concerns. However, the new results leave me less convinced about the benefit of the constraints.
The reported mean results at 130M are:
| Model and training | PACC@8 ↑ | ASR@8 ↓ |
|---|---|---|
| Unconstrained, clean fine-tuning | 20.8% | 79.2% |
| Constrained (calibrated), clean fine-tuning | 5.6% | 94.4% |
| Unconstrained, adversarial fine-tuning | 71.5% | 28.5% |
| Constrained (calibrated), adversarial fine-tuning | 56.3% | 43.7% |
Adversarial training helps both models, but the constrained model has lower mean accuracy in both comparisons. These results do not show an additional behavioral robustness benefit from the constraints.
I understand the revised emphasis on state-level guarantees, and I think these are worth studying. However, it remains unclear how preserving the state helps protect the final predictions. With the earlier attribution of robustness gains to the architecture withdrawn, this connection becomes important to assessing the remaining contribution.
For now, I will keep my score.
what the constraints do and do not protect
Thank you for reading the new results closely and for the clear follow-up. We agree with your reading of the table, and we would rather answer the question you raise directly than argue with the numbers.
On the table. You are right: under matched training the constrained model does not have higher accuracy under adapted triggers, with or without adversarial fine-tuning. The revision does not claim a behavioural robustness benefit from the constraints, and we withdrew the earlier attribution for exactly this reason. (The constrained adversarial arm has two seeds so far; the third is being added, and we do not expect it to change this conclusion.)
How does preserving the state relate to protecting the prediction? The prediction is read from the state through a projection that itself depends on the current input. A trigger can therefore change the answer through three channels:
- Erasure: shrinking the state so that earlier context is lost. This is the mechanism that defines hidden-state poisoning.
- Injection: adding new content to the state.
- Readout steering: changing how the state is read, without changing much of what it holds.
The retention bound closes channel 1, and only channel 1. That is a necessary condition for protecting the prediction, not a sufficient one, and our matched results show the difference in practice: at 130M a search that minimises the state norm changes no answer of any fine-tuned model, while a search on the answer margin, which works through channels 2 and 3, changes most of them. We consider this separation one of the useful outcomes of the experiments you asked for: it shows that defences and evaluations aimed at state collapse alone address the wrong channel once a model is fine-tuned.
What connects the two, and what is missing. The paper already bounds the other quantities that enter the prediction: the component of the state along its pre-trigger direction (Corollary 5), the norm of what a trigger can inject per token, and the gain of the readout projection. Together these give a condition of the form "if the answer margin exceeds a bound built from these three quantities, a trigger of that length cannot change the answer". With the constants a pretrained model admits, that bound is not yet informative, and we say so. Making it informative is the concrete next step, and it is the purpose of the experiment we are running now: fine-tuning while the step and eigenvalue bounds are tightened gradually to the regime of the stated constants, to measure whether a non-trivial bound can coexist with the pretrained model's utility.
What we think remains as the contribution. A closed-form analysis of the selective scan with the exact condition for a bounded state; a guarantee, confirmed by measurement when training from scratch, that removes the erasure channel; a calibration procedure that adds the constraints to a pretrained model at no cost in accuracy or perplexity; and a training-matched protocol with adapted attacks that shows which channel is actually binding. We agree that this is a narrower claim than the submission made, and we appreciate that your questions are what made it precise.
We understand your decision to keep the score, and we thank you again for the time you have put into this paper.
Thanks for the clarification. I appreciate the state-level contribution. However, the bound connecting these guarantees to robust predictions is not yet informative with the pretrained model’s constants, and the matched experiments show no additional robustness benefit from the constraints.
I will keep my current score for now, but would be happy to reconsider when the constraint-tightening results are available.
Matched fine-tuning control, attack protocol, fact-revision test and corrected reproducibility statement
Thank you for the careful review and for checking the repository. Your questions shaped the new experiments directly.
W1 / Q1. Matched training controls.
We ran the control you asked for. An unconstrained Mamba-130M and the constrained model are fine-tuned from the same public checkpoint with the same data, optimiser, steps and seeds, with and without adversarial training (general response, Table 2 of the revision). Under adapted triggers of length 8, accuracy is 20.8% (unconstrained) and 5.6% (constrained) with clean fine-tuning, and 71.5% and 56.3% with adversarial fine-tuning. The improvement is therefore attributable to adversarial training, and we withdraw the sentence about the 61.9% row. What the constraints contribute is the state-level guarantee, which we confirm by measurement when training from scratch (retention 0.64 against 0.03). One detail: at 130M the constrained arms use constants calibrated to the checkpoint, a procedure the revision introduces so that the constraints can be added to a pretrained model without changing its function.
W2 / Q2. Were triggers re-optimised?
In the revision, yes, always. Target: each fine-tuned checkpoint and each example separately. Vocabulary: all tokens except names, answer words and special tokens. Attacks: eight random triggers; a zero-shot trigger repeating the largest-step token among 1024 candidates; greedy coordinate gradient search on the answer margin (40 iterations, 32 exactly evaluated candidates each) and on the state norm. Evaluation: 48 held-out examples per seed and trigger length in {8, 16, 32}; an example is robust only if all four attacks fail. The earlier comparison under published triggers has been removed.
W3 / Q3. Useful forgetting, revision and context switching.
Both studies test this directly, and the answer is encouraging. Every context contains a sentence that re-assigns one fact, and in "update" examples the question is about that fact, so the model must return the revised value. Fact-update accuracy is 100% for the constrained and the unconstrained model alike at 130M, with the same WikiText perplexity (17.7 against 17.6), and 100% in the small study. Bounding the step does not impair revision of stored information in these tasks. A broader revision benchmark in natural language is part of the evaluation we are extending for the camera-ready version.
W4. Presentation.
The method section now opens with an overview table: for each component, the quantity it controls, the formal result, the threat surface (token insertion or continuous perturbation), and whether it is proved or measured. The experiments are reorganised around the two matched studies, and the figure that mixed a detector's PGD accuracy with our radius has been removed.
Minor: proof of Theorem 3. Rewritten as four displayed steps: error recurrence, term-by-term bounds, unrolling, readout.
Minor: reproducibility.
You are right, and we apologise: the sentence on page 2 promised more than the repository delivered. We corrected this in two ways. First, the results that the repository could not regenerate (Tables 1 and 2 of the submission and the figures from the same runs) are no longer in the paper. Second, the revised statement lists exactly what the released scripts regenerate: every derived constant, the analytical depth curve, and both matched studies with per-seed outputs (the small one on a CPU in about two hours, the 130M one on a single 16 GB GPU).
In progress for the camera-ready version: the remaining seed and the full ablation at 130M, tightened constants that make the retention bound informative at scale, and adapted-attack evaluation on RoBench-25 and HarmBench.