- Rating
- 3
- Confidence
- 1
- Informativeness
- 3
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper proposes IUC, a one-shot defense method against quantization-activated attacks on large language models. The method constructs parameter reference intervals across different quantization configurations, uses intersection width to determine correction priorities, and employs union constraints and two-stage optimization to limit parameter modifications while preserving model utility. The authors evaluate IUC across multiple models, quantization configurations, and attack scenarios, including advertisement injection, over-refusal, and jailbreak. Experimental results show that IUC significantly reduces attack success rates while largely preserving model performance and demonstrates generalization to the unseen GPTQ quantization configuration.
Critical strengths
- The paper is clearly written, well organized, and easy to follow.
- The proposed method has strong practical value, as it requires only a single correction of the full-precision model to support multiple quantization configurations.
- The method demonstrates good generalization across different quantization configurations, including the unseen GPTQ setting.
Critical weaknesses
I have the following concerns about this paper:
- I have some doubts about the theoretical justification for using intersection width as the correction priority. Section 3.1 states that, once the GGUF residual interval is included, the current weight lies at an endpoint of the intersection. By Proposition 1, its Intersection Exit Cost is therefore 0 regardless of the intersection width. Appendix D.1 also notes that $ a_i^\cap=\rho_i=0 $ when a feasible outward correction direction exists (Eq. 25). Since the default reference set includes GGUF Q4_K_M, this is not merely an isolated edge case. Although Proposition 1 shows that narrower intersections have a smaller worst-case exit-cost bound, it does not directly explain why they should still be prioritized when the actual exit cost is already zero. The gradient analysis in Appendix D.1 explains how the coverage objective encourages parameter updates, but does not fully justify the choice of intersection width as the priority criterion in this setting. I would appreciate further clarification of this design.
- I have concerns about the connection between leaving the intersection and changing the actual quantized mapping. For GGUF, the reference interval is constructed from the quantization residual rather than decision boundaries, and the authors acknowledge in Appendix D.1 that whether the quantized value changes still depends on the quantizer's decision boundaries. Even for INT8, NF4, and FP4, the reference intervals are shrunk inward from the full decision intervals ($ I_i^{(q)}\subseteq\bar{I}_i^{(q)} $, Appendix C.3), while the guarantee in Eq. (18) applies only to the full intervals. Although Table 19 reports quantized-mapping change rates for INT8, NF4, and FP4, it does not directly establish how often leaving the reference intersection leads to actual mapping changes, nor does it include GGUF. Since disrupting malicious quantized mappings is central to IUC's motivation, I believe this relationship requires further validation.
- The main text lacks an end-to-end workflow figure illustrating the complete IUC correction pipeline.
- I believe the ablation studies on the key components are insufficient. Although the authors evaluate different quantizer combinations and parameter selection strategies, they do not independently ablate the Union Penalty, the Hidden-State Constraint, or the Two-stage Optimization. In addition, in the single-quantizer experiment in Appendix F, the authors not only change the number of reference quantizers but also remove the union-specific penalty and constraints. While this modification is understandable given the degenerate intersection–union geometry in the single-quantizer setting, the performance differences may not be entirely attributable to joint quantizer modeling. More controlled ablations would help clarify the contribution of each component.
- I have concerns about the limited coverage of the adaptive attack experiments. Although the authors consider a defense-aware attack in Appendix E.6, the experiment covers only the Jailbreak scenario on Qwen2.5-1.5B and includes only INT8, NF4, and FP4 ($ Q_{\mathrm{atk}}={\mathrm{INT8},\mathrm{NF4},\mathrm{FP4}} $). However, one of the main contributions of this paper is a unified defense across quantization configurations, with particular emphasis on complex quantization methods such as GGUF. The current results therefore do not establish whether IUC can withstand targeted adaptive attacks under these configurations. Furthermore, the main text mentions the adaptive attack experiment at the end of the GGUF paragraph in Section 4.2, without explicitly distinguishing the two experimental settings. This could give readers the impression that the adaptive attack evaluation also covers GGUF. I suggest clarifying this distinction and extending the adaptive attack evaluation to more complex quantization configurations.
Questions for authors
See the weakness.
4 comments
Response to Reviewer TCag (2 of 2)
W4. Ablation Analysis of Key IUC Components and Single-Quantizer Settings
Union Penalty constrains the magnitude of parameter corrections, while Hidden-State Constraint limits changes in hidden representations on clean samples. Stage B further reduces correction magnitudes while maintaining Intersection Exit Coverage. We conduct ablation experiments by separately removing these three components. As shown in Table 2, removing any component reduces MMLU and MC2, with the most pronounced utility degradation observed when Union Penalty is removed. Together, these three components constrain parameter corrections and preserve normal model utility.
Table 2. Ablation of Key IUC Components.
| Metric | Origin | Full IUC | w/o Union Penalty | w/o Hidden-State | w/o Stage B |
|---|---|---|---|---|---|
| ASR (%) ↓ | 86.78 | 0.78 | 0.24 | 0.96 | 0.62 |
| MMLU (%) ↑ | 57.60 | 58.00 | 48.72 | 55.68 | 53.72 |
| MC2 (%) ↑ | 41.99 | 45.11 | 36.47 | 40.53 | 40.28 |
Both Intersection and Union in IUC are constructed from the same set of reference quantizers. Since the Union interval depends on the reference quantizer set, the two are inherently geometrically related. In the single-quantizer setting, Intersection and Union coincide, and the original correction bound cannot satisfy the Intersection Exit requirement. Therefore, the Union constraint must be adjusted.
In the Qwen2.5-1.5B jailbreak experiment, INT8-only, NF4-only, and FP4-only reduce the average ASR from 86.78% to 22.11%, 21.00%, and 19.22%, respectively. In a separate Qwen2.5-0.5B over-refusal experiment, we further evaluate the contribution of joint multi-quantizer modeling through a Remove-one Quantizer ablation. This experiment preserves the Union construction rule and optimization settings, removing only one reference quantizer at a time. Full IUC achieves an average ASR of 3.67%, which increases to 7.22%, 25.78%, and 25.11% when INT8, NF4, and FP4 are removed, respectively, demonstrating the advantages of joint multi-quantizer modeling.
W3 & W5. IUC Defense Flowchart and Evaluation of Adaptive Attacks Under GGUF
We have uploaded the revised manuscript and replaced the original Figure 2 with a flowchart illustrating the IUC defense process. For the Defense-Aware Adaptive Attack, we extend the attack scenarios to include Advertisement Injection and Over-refusal, and incorporate GGUF into the set of target quantizers for adaptive attacks. As shown in Table 3, across three attack scenarios and four quantization configurations (INT8, NF4, FP4, and GGUF), the average ASR decreases from 52.27% to 6.82%, further demonstrating the effectiveness of IUC against adaptive attacks under different quantization configurations. In addition, we have added a Defense-Aware Adaptive Attacks paragraph in Section 4.2 of the revised manuscript, with the corresponding experimental results reported in Table 4 of the main text.
Table 3. Defense Effectiveness Against Adaptive Attacks.
| Attack Scenario | ASR Before (%) ↓ | ASR After IUC (%) ↓ | MMLU After (%) ↑ | MC2 After (%) ↑ |
|---|---|---|---|---|
| Advertisement Injection | 30.85 | 4.67 | 57.12 | 47.63 |
| Over-refusal | 34.53 | 7.42 | 56.38 | 47.86 |
| Jailbreak | 91.43 | 8.37 | 56.12 | 44.79 |
| Avg. | 52.27 | 6.82 | 56.54 | 46.76 |
Thank you for your response. I’ll keep my score as it is.
We sincerely thank the reviewer again for their time and careful review of our work. We greatly appreciate your feedback and will carefully organize the relevant experimental results and analyses and incorporate them into the main text in a subsequent revision.
Response to Reviewer TCag (1 of 2)
We thank the reviewer for the positive evaluation of IUC. We address the reviewer's questions below.
W1. Rationale for Intersection Width-Based Correction Prioritization Under GGUF
When GGUF is included in the reference set, its residual interval has the current weight as an endpoint. Consequently, the Intersection Exit Cost is zero for parameters with a feasible outward correction direction, making it difficult to distinguish correction priorities using this metric. However, Intersection Width is still jointly determined by the GGUF residual reference and the local intervals of other quantizers, preserving geometric scale differences across parameters. Based on Intersection Width, IUC computes si and determines the correction strength through xi=clip(αgsiγg,0,xmax), prioritizing parameters with narrower intersections. Under the same parameter budget, Smallest, Random, and Largest achieve average ASRs of 0.00%, 22.13%, and 41.31%, respectively, validating the effectiveness of Intersection Width in guiding parameter corrections under the joint reference set.
W2. Relationship Between Intersection Exit and Actual Quantization Mapping Changes
For INT8/NF4/FP4, IUC constructs shrunken reference intervals within the full quantization decision intervals. Actual changes in quantized weights depend on whether the corrections cross the full decision boundaries. By fixing the extremal weights in each group and constraining the remaining weights, IUC preserves the quantization scales and decision boundaries when the grouping and codebooks remain unchanged. For GGUF, IUC uses reconstruction residuals from actual block-wise quantization to determine local correction directions and scales. Moving along the residual direction increases the error relative to the original quantized reconstruction. To verify actual quantization changes, we re-quantize the corrected model. In the advertisement injection experiment, the actual quantized weight change rates among selected parameters are 32.01%, 9.81%, and 12.17% for INT8, NF4, and FP4, respectively, with ASR reduced to 0.00% in all three configurations. As shown in Table 1, the average actual quantized weight change rate across five GGUF configurations is 17.92%, while the average ASR decreases from 88.17% to 2.89%. These results demonstrate that IUC induces actual quantization changes across different configurations and effectively suppresses quantization-triggered malicious behavior.
Table 1. Actual Quantized Weight Change Rates Across GGUF Configurations.