- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper proposes PATCHER, an adversarial training method for defending against malicious full-parameter finetuning. It simulates multi-step attacks and reuses the resulting parameter displacements across multiple defense updates to reduce training cost. The paper provides theoretical bounds on gradient approximation error and evaluates robustness, downstream utility, and computational efficiency.
Critical strengths
-
The method provides a simple way to scale train-time attacks. Reusing attack vectors amortizes the cost of simulating longer attacks, and the parallel implementation further reduces wall-clock time.
-
The empirical gains under the default attack are substantial. Table 1 shows clear ASR reductions across all three benchmarks, supported by results over five random seeds. Additional evaluations cover larger models, downstream utility, and several adaptive attack settings.
Critical weaknesses
-
Method design: the justification for long attack-vector reuse is limited. Proposition 2 assumes gradient descent with sufficiently small learning rates and matched train/test attack lengths, whereas the experiments use AdamW with 300 training attack steps and 2000 test attack steps. The bound therefore does not directly justify the default 1000-step reuse window or provide a practical criterion for refreshing the vector.
-
Related work: the comparison with TAR does not isolate the claimed advance. TAR already uses multi-step adversarial meta-learning, but the reported comparison also changes the defense objective and update schedule (Appendix D). This makes it difficult to separate the benefit of attack-vector reuse from these other differences relative to the closest prior method.
-
Experiments and analysis: the robustness gains are sensitive to basic attack changes. A test-time learning rate of 5e-5 raises the average ASR to 64.4% (Table 9), while DPO with β = 0.5 followed by SFT yields 42.1% ASR versus 40.7% for vanilla SFT (Table 10). Although these limitations are acknowledged, they substantially weaken the broader claim of robustness against malicious full-parameter finetuning.
Questions for authors
-
Validity of the reuse window. In the actual AdamW setting, how does the defense gradient computed with a reused attack vector deviate from that computed with a fresh vector over the 1000-step window? What evidence supports this refresh interval?
-
Contribution relative to TAR. Can the authors compare against TAR-style training using the same defense objective and matched compute, with and without attack-vector reuse? This would help identify the improvement attributable to the proposed mechanism.
-
Robustness under attack selection. Does PATCHER retain a substantial advantage when the attack learning rate and loss are tuned separately for each defense under a fixed attack budget? Please also report the corresponding utility to clarify the practical significance of the remaining robustness.
4 comments
Author Response (2/3)
2. Contribution relative to TAR.
...TAR already uses multi-step adversarial meta-learning, but the reported comparison also changes the defense objective and update schedule (Appendix D). This makes it difficult to separate the benefit of attack-vector reuse from these other differences relative to the closest prior method.
Can the authors compare against TAR-style training using the same defense objective and matched compute, with and without attack-vector reuse? This would help identify the improvement attributable to the proposed mechanism.
Thank you for this insightful analysis. We acknowledge that TAR already simulates multi-step attack trajectories. However, compared to TAR, our work explicitly studies the effect of increasing the number of simulated attacks and shows its importance for robustness in Figure 5.
Furthermore, another significant difference between Patcher and TAR is the reuse strategy of the attack trajectory: Patcher reuses an attack vector for a certain number of steps, while TAR constructs a new attack trajectory for each defender update. We consider attack vector reuse to be the main contribution of Patcher, which significantly improves computational efficiency and makes multi-step attack simulation affordable in adversarial training.
To address your concern, Section 2 of the general Q&A compares training with and without attack-vector reuse using the same defense objective as Patcher, where the no-reuse variant constructs a fresh attack vector before each defender update, following TAR’s refresh schedule. The experiment yields two findings:
-
With the total number of defender updates held fixed, increasing the reuse duration increases ASR. This shows the robustness cost associated with reusing an increasingly stale attack vector.
-
With the training compute budget held fixed, using a 1000-step reuse window reduces ASR from 85.8% to 20.9% compared with refreshing the vector at every defender update.
These results suggest that the benefit of reuse is improved robustness within a fixed training budget, despite a robustness cost at a fixed number of defender updates. In Patcher's setting, the computational savings outweigh the cost of attack vector staleness. Therefore, increasing the number of attack steps and reusing attack vectors are two complementary and necessary components that contribute to Patcher's robustness.
Following your suggestion, we have added this new ablation to Section 4.5 to decouple the benefits of scaling the number of attack steps and reusing attack vectors.
Author Response (3/3)
3. Robustness under attack selection.
The robustness gains are sensitive to basic attack changes... Although these limitations are acknowledged, they substantially weaken the broader claim of robustness against malicious full-parameter finetuning.
Does PATCHER retain a substantial advantage when the attack learning rate and loss are tuned separately for each defense under a fixed attack budget? Please also report the corresponding utility to clarify the practical significance of the remaining robustness.
Thank you for this question. First, we would like to emphasize that Patcher is designed primarily to improve the robustness against full-parameter malicious finetuning with the common cross-entropy objective (i.e., SFT), explicitly formulated in Section 3 and simulated during training. Under this objective, Patcher consistently decomstrates considerable improvements against other baseline methods under different datasets, models, poison ratios, number of finetuning steps, learning rates and optimizers. We view Patcher's effectiveness under this finetuning objective as the main scope of this work, and we have further revised the abstract, introduction and conclusion to explicitly clarify this.
However, we agree that tuning the attack and loss separately and reporting the best-performing attack strategy for each defense is also an important evaluation. As per your request, we evaluated different defense-specific attack configurations under a 2000-step attack budget. Below, we report the selected configuration (i.e., the attack configuration achieving the highest ASR) and results for each alignment method:
| Alignment method | Defense-specific attack | Advbench | Beavertails | HEx-PHI | Overall | GSM8K utility |
|---|---|---|---|---|---|---|
| SFT | Gradient ascent (500 steps) with learning rate 1e-5 + SFT with learning rate 1e-4 | 87.6 | 82.4 | 74.5 | 81.5 | 4.3 |
| Patcher | DPO (, 1000 steps) with learning rate 1e-5 + SFT with learning rate 5e-5 | 82.0 | 79.5 | 7.5 | ||
| TAR | SFT, learning rate 5e-5 | 95.6 | 85.8 | 89.8 | 90.4 | |
| Booster | DPO (, 1000 steps) with learning rate 1e-5 + SFT with learning rate 5e-5 | 91.6 | 91.0 | 87.8 | 9.0 | |
| Vaccine | DPO (, 1000 steps) with learning rate 1e-5 + SFT with learning rate 5e-5 | 76.0 | 78.5 | 8.2 |
These results show that Patcher does not retain a substantial advantage over SFT under this defense-specific attack selection: its overall ASR is 80.8%, compared with 81.5% for SFT. We acknowledge that the robustness gains observed under our default attack settings do not extend uniformly to this broader adaptive setting, and we have added a paragraph in Section 4.2 of the revised manuscript to explicitly discuss Patcher's robustness against adaptive attacks.
However, we would like to direct your attention to a separate experiment reported in our response to Reviewer Nv7x’s third question, which investigates whether incorporating additional attack objectives during defense training can improve robustness. For the evaluated DPO () + SFT attack, incorporating attack vectors constructed with diverse objectives reduces Patcher’s ASR from 42.1% to 12.9%. This suggests that broadening the training-time attack distribution is a promising direction to further enhance robustness against a broader range of finetuning attacks.
In addition, we find that the selected attacks for Patcher also result in poor downstream utility: 7.5% accuracy on GSM8K, compared with 29.6% under the default attack setting used in the main experiments. This indicates that the attacker also needs to consider the trade-off between utility and harmfulness when selecting the attack configurations. Specifically, if the attacker still aims for high utility, a lower learning rate for the attack is more desirable, and Patcher remains an attractive defense strategy under this attack scenario.
Thank you again for your analysis that helps us to strengthen our work! We would be happy to address any further questions.
Kind Reminder
Dear Reviewer 5eap,
As the discussion period is coming to an end, we would appreciate your feedback on whether our responses have adequately addressed your concerns. We have provided detailed replies to each point and would be happy to clarify any remaining questions before the deadline.
As a side-note, regarding Question 1, we have provided additional analysis by computing the relative gradient estimation error between the proxy gradient and the exact full gradient at the endpoint of a 20-step attack trajectory, and the results are presented in Appendix A.2 of the revised manuscript. We would appreciate it if you could also check it out.
Many thanks for your time and consideration!
Best regards,
Authors of Submission 25939
Author Response (1/3)
We thank the reviewer for the constructive feedback on our manuscript. We will clarify important details and provide additional experimental evidence to address your concerns.
1. Validity of the reuse window.
We agree that Proposition 2 does not explicitly justify a 1000-step reuse window in the AdamW setting. To provide empirical evidence for the propositions, we measured the relative gradient estimation error across different attack lengths and reuse durations, and the results are shown in Section 1 of the general Q&A. We find that this error remains relatively stable over the 1000-step reuse window, providing empirical support for the reuse strategy.
In addition, the end-to-end ablation in Section 4.5 of our manuscript provides complementary evidence, where we evaluated the ASR when the reuse duration was set to 200, 500 and 1000 respectively, and found that ASR increased mildly as we enlarged the reuse window from 200 to 1000.
Together, the relative gradient estimation error and the empirical ASR evaluation support our selection of the 1000-step refresh interval as a good trade-off between robustness and computational efficiency. Nevertheless, we agree that Proposition 2 relies on simplifying assumptions. It provides theoretical motivation for attack-vector reuse, but not an optimizer-specific guarantee or a practical rule for selecting the refresh interval. We have revised Section 3.2 of the manuscript to distinguish the theoretical motivation from the empirical basis for selecting the refresh interval.