- Rating
- 1
- Confidence
- 4
- Informativeness
- 1
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
The paper proposes CDIM, a three-stage black-box attack framework that rewrites harmful requests into alternative semantic domains, queries a target model, and uses an auxiliary model to generate the final answer from the target response and original request. Experiments on AdvBench and miniHarmBench report improved end-to-end attack success and query efficiency.
Critical strengths
None
Critical weaknesses
-
The experiment evaluation fails to establish that the target models were actual jailbroken. ASR is computed on answers generated by a separate recovery model that receives the original harmful query and can provide the harmful information itself. The results show that the full pipeline can produce harmful answers, but fail to show that the critical harmful information is actually provided by the target model.
-
The “isomorphic” property is neither enforced nor independently validated. Matching entity names does not ensure that the rewritten task preserves the original rules and constraints. A correct final answer cannot establish this either, because the recovery model may fill in information lost during rewriting.
Questions for authors
-
How does performance change when the target response is removed or replaced with unrelated text, holding other inputs and the recovery budget fixed? Please provide complete representative traces identifying which critical harmful information originates in the target response.
-
How is the relation-preservation condition in Equation 3 independently verified? What evidence shows that preserving this structure improves performance over ordinary semantic rewriting under matched settings?
-
Why does CDIM use Qwen3-Max while the baselines use Mixtral with reduced search settings? Do the reported gains persist with the same auxiliary models and comparable search budgets?