- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper proposes NIRA, a framework for improving the safety of black-box VLMs without modifying their parameters. It uses an additional VLM to rewrite harmful responses while preserving safe ones. The authors build an automated training pipeline using jailbreak detection, text and image augmentation, and a 235B teacher model to generate safe responses. An 8B rewriter is then trained using LoRA. Experiments on several benchmarks show that NIRA can reduce attack success rates while retaining much of the model's usefulness on benign queries.
Critical strengths
-
The paper addresses a practical problem. The method does not require access to the target VLM's weights, making it potentially useful for closed-source models.
-
The experiments cover several attack benchmarks and two target models. The ablation on Safe-to-Safe pairs is useful, as it shows their importance in reducing over-refusal.
Critical weaknesses
-
The methodological novelty is limited. The approach mainly combines existing techniques, such as data augmentation, teacher-generated supervision, and LoRA fine-tuning. The intervention gate is also learned from Safe-to-Safe training pairs rather than designed as a separate mechanism. I am not sure what the main technical contribution is beyond combining these components.
-
The contribution of the proposed augmentation is not entirely clear. The method uses a large 235B teacher to generate safe training responses, but there is no comparison with smaller teachers. Also, Table 3 shows that the model without augmentation already performs quite well. It is difficult to tell how much of the improvement comes from the proposed augmentation rather than the teacher-generated training data.
-
I have some concerns about the evaluation and practical cost. The safety results rely on a single automated evaluator, and the zero-regression claim is not independently verified. The gate recall on SIUO is only 40%, and NIRA also increases over-refusal on MOSSBench. In addition, the method requires several large models for data generation and an extra 8B model during inference, but the overall cost is not fully evaluated.
Questions for authors
-
What is the main technical difference between NIRA and existing safety rewriting methods? Could the authors better explain the novelty of the proposed framework?
-
How much does the performance depend on the 235B teacher? Could the authors compare different teacher sizes and further clarify the benefit of the two-track augmentation?
-
Could the authors evaluate NIRA using another safety evaluator or human annotations to verify whether the zero-regression results still hold?