- Rating
- 3
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper studies how imperfect privacy guards should be composed and placed in multi-agent workflows. The authors introduce GuardCircuits, a framework that models guards as components with privacy, utility, latency, and cost signatures. They derive composition laws for serial, parallel, and switched guard circuits, including a high-reliability min-plus law that explains depth-width tradeoffs. They also study global placement, showing that ideal guard placement reduces to a directed minimum cut and that stochastic guards can form ordered barriers across repeated executions. Experiments on three privacy benchmarks evaluate serial vs. parallel guard composition and min-cut vs. random guard placement.
Critical strengths
- Privacy guards are often imperfect, and their placement in agent workflows can matter as much as the guard model itself. The research question is interesting.
- The theoretical framework is clean and potentially useful.
- The distinction between local guard composition and global workflow placement is valuable.
Critical weaknesses
- The empirical validation is relatively limited compared with the scope of the theoretical claims. The experiments mostly confirm intuitive monotonic trends, and does not convincingly show that the proposed signatures can be accurately calibrated and then used to predict performance of unseen guard circuits or new workflows.
- The placement experiments use constructed workflows with known two-edge minimum cuts and relatively simple topology. This supports the proof-of-concept, but it is unclear whether the method improves over practical baselines in real agent systems where the communication graph, information origins, and tool side effects may be only partially observed.
- The evaluation measures leakage only on released outputs in several experiments, while the motivation is system-level privacy in multi-agent workflows. This creates a gap between the stated concern about internal paths, memories, and tool channels and the empirical metric used to validate the framework.
Questions for authors
See the Weaknesses.
4 comments
Response 2/2
Q3. Why measure only released outputs when the motivation includes internal leakage?
Thank you for raising this point. Our motivation is indeed to prevent leakage from protected origins to unauthorized recipients , and both can be internal components of the workflow. We would like to clarify that, given the privacy policy, an unauthorized internal node is no different from an external user. Leakage is defined by the policy label (Section 3), not by where a component sits in the graph: any agent, tool, or memory with belongs to , and Theorem 18 cuts every path from to all of . For example, a shared memory that must not store medical information is protected in exactly the same way as an external user. In both cases, we measure leakage on the messages that enter the unauthorized recipient.
The external benchmarks used in the experiments were designed to measure leakage with respect to the final released output, which is why that is the main focus for the evaluation. We will make this connection between the motivation and experiments more explicit in the revised manuscript.
References
[7] L. R. Ford Jr. and D. R. Fulkerson. Maximal Flow Through a Network. Canadian Journal of Mathematics, 8:399–404, 1956. https://doi.org/10.4153/CJM-1956-045-5
Thank you very much for the response; it has addressed my concerns. I will maintain my original positive score.
Thank you for your thoughtful question and valuable suggestion, which have helped us improve the quality of our paper.
Response 1/2
Thank you for your thoughtful feedback on our paper. We are encouraged that you found the research question interesting and the theoretical framework clean and potentially useful, and that you appreciate the distinction between local guard composition and global workflow placement. Below we have provided responses to your questions, including new experiments that compare the circuit-law predictions with observed results. Please let us know if you have any follow-up questions.
Q1. Do calibrated signatures predict unseen circuits and workflows, rather than only monotone trends?
Thank you for this suggestion. Based on your feedback, we have added two experiments that test exactly this: we calibrate the signature of a single primitive guard, and then use the circuit law (Theorem 4) to predict the behavior of circuits that were never used for calibration (App. F.8 in the revised manuscript). In both experiments, the signatures are estimated only from single-guard (k=1) calls on each case, using the GPT-5-mini censoring guard.
Pure series and pure parallel circuits (App. F.8.1, Figure 17). We predict leakage, task success, latency, and token cost for series and parallel circuits with k=2,…,5 guards on all three datasets. The predicted curves closely track the observed curves in most settings. The main exception is the pure series circuit on ACIB, where observed latency and token cost fall below the prediction: the first guard removes much of the input's complexity, so later guards process shorter messages and are faster and cheaper than the k=1 calls used for calibration.
Unseen mixed circuits (App. F.8.2, Figures 18–20). We then consider circuits that interleave series and parallel blocks under a budget of six guards. We randomly sample 18 of the 64 distinct circuits and run them on all 117 ACIB cases. Using only the k=1 calibration, the circuit law predicts both the ordering and the level of the observed values:
As in the pure series case, observed latency is somewhat lower than predicted for the slowest circuits, likely for the same reason. Overall, these results show that calibrated signatures predict the performance of unseen circuits quantitatively, not only the monotone trends.
We note that these experiments test circuit composition at a fixed placement. Predicting end-to-end leakage for new workflows additionally depends on the placement assumptions discussed in Q2 below.
Q2. Are simple constructed two-edge-cut workflows too limited for real systems?
Thank you for raising this point. We agree that the Early-Cut (EC) and Late-Cut (LC) topologies in Experiment 2 are small and constructed. We designed them this way on purpose, to isolate the placement principle. Each topology has a unique two-edge minimum cut, and the cut sits at a different stage in each one: between the propose and review stages in EC, and between the review and resolve stages in LC (Figure 8, App. E.4). The minimum cut outperforms random placement on both topologies and for every guard model (Table 3), so the effect does not depend on one particular structure.
We would also like to clarify that the placement principle does not depend on the size of the graph. A minimum cut only contains edges that lie on some path from a protected origin in Oq to an unauthorized recipient in Uq: removing any other edge from a cut leaves a valid cut with lower cost. In a large agentic system, Theorem 18 therefore only needs the subgraph of components that are reachable from Oq and can reach Uq, and EC and LC can be read as examples of such a subgraph. Computing the cut is a standard max-flow problem that runs in polynomial time [7], so graph size is not the bottleneck.
We agree that the harder issue is the one the reviewer identifies: Theorem 18 assumes that every channel between Oq and Uq is represented in G. If a tool side effect, shared memory, or log is missing from the design-time graph, the computed cut may leave a path unguarded. We currently state this assumption under "Structural channel completeness" in App. G, and we will expand that paragraph to address partially observed workflows directly. One conservative fallback is to guard the edges entering Uq. This remains a valid cut as long as those edges are known, even if the internal structure of the workflow is only partially observed, but it can cost more than the true minimum cut (in EC and LC it requires 3 guards rather than 2). Designing placements that remain robust under partial observability is an interesting direction for future work.