- Rating
- 1
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 1
Read review
Paper summary
The paper proposes Private Mask Pre-Training (PMP) to build non-fine-tunable foundation models, which stay usable as released but gain little from unauthorized fine-tuning.
- In a 500-step warm-up, PMP forms a global top- mask from absolute gradients. It selects the first mask whose IoU with the previous mask stays at or above 0.99 for 5 steps (an early-bird lottery ticket with , so 70% of parameters are trainable).
- Pre-training then updates only , while the complement stays at its random initialization .
- Only the dense weights are released. Authorized users receive the mask and fine-tune only .
Section 3 argues, through Assumption 1 and Proposition 1, that one SGD step of fine-tuning without the mask raises the expected pre-training loss by at least . The experiments pre-train a TinyLlama-1.1B-scale model from random initialization on SlimPajama-6B (the GPT-2 setup is not described). They then fine-tune GPT-2 and TinyLlama on GLUE with LoRA and with full fine-tuning. PMP lowers the fine-tuned scores; for example, the TinyLlama full fine-tuning average is 59.55 against 68.65 without defense (Table 3). Ablations cover random masks, the mask ratio, the learning rate and the number of epochs. The appendix compares PMP with SOPHON, REPNOISE and Vaccine and reports BeaverTails harmfulness.
Critical strengths
-
The problem is relevant, and PMP is a simple, task-agnostic way to approach it. Existing defenses such as SOPHON and model immunization need the data or objective they want to restrict (Sections 1 and 6). PMP needs neither. It masks gradients during pre-training (Eq. 5) and withholds at release (Section 2.3). Tying authorized fine-tuning to possession of the mask is a concrete form of controlled release that others could build on. This framing is the main reason I see value in the work.
-
Within the tested setting, the drop in fine-tuned scores is consistent and is checked against the obvious confounds.
- Table 1 shows lower fine-tuned scores with PMP for both GPT-2 and TinyLlama, under both LoRA and full fine-tuning, on all nine tasks.
- Figure 3 replaces the early-bird mask with a random mask of the same ratio, and the fine-tuned scores become higher on every task. So the effect depends on which parameters are frozen, not only on how many.
- Figure 4 varies the mask ratio, the fine-tuning learning rate (1e-5 to 4e-5) and the number of epochs (1 to 5).
- Appendix A.2 adds SOPHON, REPNOISE, Vaccine and BeaverTails.
How much this signal means for real foundation models depends on Weakness 2.
Critical weaknesses
-
Proposition 1 does not follow from Assumption 1, and a corrected version would still not bound downstream gains.
- The first-order term is not handled. The conditional optimum only gives . The gradient with respect to , which stays at random initialization, is in general nonzero. The proof sketch notes that the first-order term "has no guaranteed sign" and then draws the conclusion from the quadratic term alone, although for small the first-order term dominates.
- Its sign actually works against the claim. By Eq. 7, . The first-order change in is therefore . With , fine-tuning without the mask is simply continued pre-training of all parameters, and a small step lowers whenever .
- A two-parameter example meets every stated condition and violates Eq. 8. Let , and with small , with released point and . One SGD step gives , and changes by for .
- Even a corrected bound would not reach the experiments. Gain is defined on (Section 3), while the experiments measure downstream accuracy, and a rise in does not mean that is hard to reduce. A standard model at a local minimum of , with positive curvature along the update, also gets the same increase, so Eq. 8 does not separate PMP from standard pre-training. The analysis also covers one SGD step, while the experiments use multi-step AdamW and LoRA.
Figure 5 does not fill the gap. It plots one random direction per curve, and the masked-direction curve reaches its minimum near , slightly below its value at , which does not fit the conditional-optimum assumption. The paper presents this analysis as the mechanism behind non-fine-tunability, so the mechanism is currently unsupported.
-
The experiments do not test capability preservation, and several signs suggest that the models are too weakly pre-trained for the fine-tuning results to be meaningful.
- The Base scores carry no information about capability. The paper does not say how Base GLUE scores are produced before fine-tuning. The reference Base row of TinyLlama gives MRPC 31.62 (= 129/408, always "not equivalent") and RTE 52.71 (= 146/277, always "entailment"). The PMP Base row is at chance level (SST-2 50.80, QNLI 50.72, MNLI-m 32.81). The three defended baselines also have higher Base averages than the undefended model (45.77, 42.86 and 41.07 vs. 38.41, Table 4). So "preserves base model performance" compares chance with chance.
- Fine-tuning itself often fails, and failure is scored as protection. Without PMP, GPT-2 full fine-tuning reaches 56.61 on QQP, below always predicting "not duplicate" (63.18). GPT-2 LoRA gives 68.38 on MRPC (= 279/408, a constant prediction). TinyLlama gives 68.36 on CoLA, below always predicting "acceptable" (69.13 = 721/1043). Because lower fine-tuned scores count as success, a PMP model that collapses to a constant prediction is scored as protected; for example, GPT-2 with PMP and full fine-tuning gives QNLI 50.54 (= 2761/5463) and RTE 47.29 (= 131/277).
- Pre-training looks too short to produce a capable model. Pre-training uses about 164M tokens (20,000 updates × 32 sequences × 256 tokens) with a learning rate of (Appendix A.1). This learning rate is low for training a 1B-scale model from scratch. The tokenizer is not stated. If the loss in Figure 5 is the mean per-token cross-entropy in nats, its value at (about 11.2) is above and . In that case the model is worse than a uniform prediction over any vocabulary smaller than about 73K tokens.
Without a language-modeling metric for matched checkpoints, and without a reference model that fine-tunes normally, the claims that PMP "preserves base model performance" and yields a non-fine-tunable foundation model are not tested. The observed suppression may not carry over to models with real pre-trained capability.
Questions for authors
-
How are the Base GLUE scores obtained: zero-shot prompting, or a classification head with no training?
- Please report held-out SlimPajama loss or perplexity for the PMP and W/O PMP checkpoints, and state the tokenizer and the loss plotted in Figure 5.
- Please confirm that is the pre-training learning rate (Figure 4 suggests the same value is also the main fine-tuning learning rate), and give the fine-tuning hyperparameters (learning rate, epochs, batch size, LoRA rank, classification head), which Appendix A does not list.
- Please also report GLUE, under the same fine-tuning protocol, for a randomly initialized model of the same architecture and for a W/O PMP checkpoint with matched pre-training loss.
If the W/O PMP model is clearly better than the random-initialization control and PMP keeps its perplexity close to W/O PMP, my main empirical concern would be much weaker.
-
Have you tested attackers who try to recover or approximate the mask? Three routes follow from the paper itself.
- Frozen parameters equal exactly (Eq. 5). An attacker who can reproduce the initialization (Appendix A.1 fixes seed 42) can compare weights directly, and any normalization weights in the complement stay at their constant initial value.
- The Figure 6 caption says that near-zero gradients come mostly from frozen parameters, so thresholding gradient magnitudes gives a candidate mask.
- An attacker can fine-tune only the top- parameters by gradient magnitude, as PMP itself does in Eq. 2. Section 5.2 assumes that the adversary does not know the mask ratio, but the paper reports it ().
Please report the composition of the mask per tensor type, the IoU between recovered and true masks, and GLUE after fine-tuning only the recovered set. A high recovery rate would lower my assessment further, and a low one with no fine-tuning benefit would raise it.
-
Under what additional condition does Eq. 8 hold, for example a sign condition on ? How would the result connect to or to downstream accuracy, and how would it compare PMP with a standard model? Please address the example in Weakness 1.
-
(Clarification) In Figure 2, authorized fine-tuning of TinyLlama reaches about 65 on QNLI and 62 on MNLI-m, against 79.37 and 71.17 for full fine-tuning without PMP (Table 1). It is also slightly below unauthorized fine-tuning on SST-2 and MRPC, although Section 4.3 and the caption say that it consistently matches or outperforms. Is this loss for mask holders expected? For Table 5, please give the harmful fine-tuning data, the number of steps and the judge model, and explain why the Defended score is 0.05 for all four defenses.