- Rating
- 2
- Confidence
- 3
- Informativeness
- 1
- Presentation
- 2
- Soundness
- 3
Read review
Paper summary
This paper studies the contextual membership and ask where membership information resides, how it differs from parameter-updated membership, and how it can be inferred under different model accesses. It introduce controlled behavioral interventions that separate target-specific exemplar information, surface-token sensitivity, and shared task abstraction. Additionally, this paper has conducted experiments to analyses the factors and get several conclusions, including ICL yields stronger pooled member-ship signal than SFT (0.869 versus 0.688) and a differently concentrated token-level signal, replacing private demonstrations with differentially private synthetic demonstrations reduces the evaluated attack to approximately chance, while increasing prediction loss.
Critical strengths
- This paper mainly analyses the factors affecting the MIA attack in in-context learning and former works have not done it previously.
- This paper is technically solid.
- This paper provides detailed experiment setups.
Critical weaknesses
- This paper is lack of novelty. There are many works including MIA attack in the ICL context and DP synthetic demonstrations generation. And from my point of view, the main contribution is that this paper mainly analysizes three factors in ICL MIA and in-context learning improvement.
- This paper only uses one model for the experiments. Since this paper main contribution is some factor discovery, the experiments should be conducted on more models such as llama3.2, qwen3.5 etc. Both thinking and non-thinking mode should be included.
- The paper is poorly written. The organization is difficult to follow and from the abstract and introduction, the reader is difficult to get to know the contribution of this paper.
- This paper mainly analyses the factors affecting the MIA attack, but there is little difference between GlobalMean and SWM, and thus I think this paper can contribute little to the MIA research community.
Questions for authors
- Can you add more experiments on more model architectures inducing qwen3.5, llama3.2 and so on. And please add more experiments on both thinking and non-thinking situation.