- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper analyzes multi-turn jailbreak trajectories using BGE-M3 embeddings and an SVM safety proxy. Across two datasets and five models, it examines candidate-path coverage, localization of safety-crossing points, and the utility of exit-related information for attack reconstruction.
Critical strengths
-
Relevant problem and accessible analysis framework. Studying how jailbreak behavior changes across dialogue turns is worthwhile. Using observable responses makes the framework applicable to close-sourced models without access to internal activations.
-
Complementary behavioral evaluation. The independent model-based audit provides evidence beyond the embedding-based safety proxy. Crossing-region context shows the most consistent benefit among the evaluated information sources.
-
Explicit acknowledgment of limitations. The paper distinguishes the proxy boundary from the model’s internal safety boundary and acknowledges the retrospective nature of reconstruction and the limited interpretation of candidate-set monotonicity.
Critical weaknesses
-
Limited validation across embedding models. The main geometric findings rely on BGE-M3, which is used for safety classification, crossing-event selection, and geometric analysis. Varying truncation and aggregation within the same encoder does not establish cross-representation robustness. Replicating RQ2 with an alternative encoder, such as Qwen3-Embedding, and independently assigned safety labels would strengthen the conclusions.
-
The detector does not explicitly incorporate dialogue context. The safety proxy takes individual assistant responses as input, whereas the paper studies multi-turn safety dynamics. A response’s safety can depend on the preceding requests and conversation history. The authors should compare response-only and context-aware safety judgments and examine whether the detected crossing events remain consistent.
-
The breadth–depth comparison may disadvantage depth. Attack_600 contains pregenerated paths whose later prompts may depend on successful progression in earlier turns. Continuing an unchanged path after an early failure may consume queries without effectively advancing the attack. The authors should clarify failure handling, report later success conditional on earlier failure, and include a failure-aware restart baseline under matched query budgets.
-
RQ3 evaluates single-turn reconstruction rather than multi-turn attack improvements. Although the information is extracted from multi-turn trajectories, the reconstructed attacks are single-turn queries.
Questions for authors
-
Do the localization and alignment findings persist with an alternative encoder, such as Qwen3-Embedding, particularly when crossing events are determined using independent safety labels?
-
How consistent are response-only safety judgments with judgments that incorporate dialogue history? Does context-aware evaluation change the detected crossing turns or the RQ2 conclusions?
-
In the breadth–depth comparison, how are early refusals or failed steps handled? What proportion of paths succeed after an earlier failure, and does the breadth advantage remain against a failure-aware restart baseline?
5 comments
Response to Q2: Including earlier dialogue turns reduced the number of dialogues with a detected behavioral crossing from 31 to 18, although the two evaluations agreed on 463 of 500 turn-level safety judgments (92.6%). Both evaluations used Doubao 2.0 lite and the same rubric. In both, the judge saw the current user request and the current assistant response. The only difference in the inputs was whether the judge could also see earlier dialogue turns.
Turn-level judgments and dialogue-level crossings
Among the 400 responses with earlier dialogue turns, the two evaluations agreed on 365 of 400 judgments (91.25%). With history included, 33 judgments changed from unsafe to safe and two changed from safe to unsafe. On the 100 first turns, where the inputs were identical, two judgments differed. Repeated scoring therefore contributed some variability to the comparison.
Sixteen dialogues had a crossing under both protocols. With history included, the first crossing occurred on the same turn in 11 of these dialogues and later in five. Fifteen dialogues had a crossing only under current-turn evaluation, and two had a crossing only under history-aware evaluation.
Localization and alignment across all first crossings
We evaluated all first crossings identified under each protocol: 31 under current-turn evaluation and 18 under history-aware evaluation. The table reports the mean localization gap at the first unsafe response. A positive gap means that the response was closer to the reference center than its matched safe control.
| Encoder | Current-turn evaluation (31 events) | History-aware evaluation (18 events) |
|---|---|---|
| BGE-M3 | +0.0078 | +0.0494 |
| Doubao Embedding | +0.0270 | +0.0626 |
The mean localization gap was positive for both encoders under both protocols. For each encoder, the 95% interval excluded zero only under history-aware evaluation. Mean alignment differences were close to zero under both protocols, and all four alignment intervals included zero.
Exploratory comparison of the same crossing steps
Of the 31 first crossings under current-turn evaluation, 15 had a positive BGE-M3 alignment difference. When history was included, eight of these 15 retained the same first-crossing turn, two shifted to a later turn, and five no longer had a detected crossing. We compared the eight events with the same first-crossing turn under both protocols. Localization was not a selection criterion.
| Measure for the eight selected events | Encoder | Current-turn evaluation | History-aware evaluation |
|---|---|---|---|
| Mean alignment difference | BGE-M3 | +0.0911 | +0.0688 |
| Mean alignment difference | Doubao Embedding | +0.0138 | +0.0366 |
| Mean post-crossing localization gap | BGE-M3 | +0.0378 | +0.0777 |
| Mean post-crossing localization gap | Doubao Embedding | +0.0583 | +0.0937 |
The positive alignment means apply to a subset selected for positive BGE-M3 alignment under current-turn evaluation. For localization, the same eight post-crossing responses were, on average, closer to the reference center than their matched safe controls under both protocols and in both embedding spaces. Because we re-estimated the controls and reference centers under each label set, this comparison supports consistency in the direction of the localization gap for these eight events.
Response to Q3: Thank you for pointing out that the handling of early refusals may affect the breadth–depth comparison. The original experiment replayed pregenerated dialogue paths. In the supplementary analysis, we retained the Table 8 hit criterion: a query counts as a hit if the SVM classifies the response as unsafe. We examined how often continuing after a first-turn miss yielded a later hit and compared breadth-first allocation with a failure-aware restart policy under a six-query budget.
1. How did the original experiment handle early refusals or failures?
In Table 8, we replayed the paths in a predetermined order. If a turn produced a valid response that triggered the refusal rule or failed to meet the SVM hit criterion, the depth-first policy continued to the next recorded turn on the same path. An early failure did not trigger an automatic restart. The original implementation skipped empty responses. In the supplementary budget comparison, we preserved the original turn positions and counted each empty or invalid response as one query.
We distinguished a miss from a refusal. A miss means that the turn yielded no response classified as unsafe by the SVM. We identified refusals separately using a text-based rule.
2. What proportion of paths yielded a later hit after an early failure?
We defined early failure as a first-turn miss and examined subsequent recorded responses on the same path. Each percentage below is the proportion of paths in that row with at least one SVM hit during the indicated window.
| Paths with a first-turn miss | Number of paths | Hit in turns 2–3 | Hit in turns 2–5 |
|---|---|---|---|
| Attack_600 | 2,072 | 757 (36.5%) | 1,093 (52.8%) |
| Attack_600 subset whose first turn also triggered the refusal rule | 27 | 9 (33.3%) | 12 (44.4%) |
| Both datasets combined | 3,442 | 39.6% | 55.1% |
The turns 2–3 window corresponds directly to the original depth allocation of up to three turns per path. Across both datasets, 39.6% of paths with a first-turn miss yielded a hit within that allocation.
3. Does breadth-first allocation outperform failure-aware restart under a six-query budget?
We compared two policies on the same three recorded paths. The breadth-first policy allocated two queries to each path. The restart policy continued along the current path until it obtained a hit. If no hit had occurred, it switched to the next untried path when a response triggered the refusal rule, a response was invalid, or the current path had used three queries. Once all three paths had been started, the policy spent any remaining budget on the last path. We averaged the paired comparison over all six path orderings and gave equal weight to each of the ten model–dataset settings.
Table 8 reported hit rates of 76.26% for breadth and 75.25% for depth. In the supplementary replay, the hit rates were 76.35% for breadth-first allocation and 75.50% for failure-aware restart. The paired breadth-minus-restart difference was +0.85 percentage points, with the interval obtained by resampling source intents.
In a sensitivity analysis, we changed the restart rule so that any miss triggered a switch to an untried path. Under that rule, the breadth-minus-restart difference was +1.53 percentage points. In both comparisons, restart means switching to another recorded path for the same intent.
Scope of RQ3
The region information in Section 4.6 comes from multi-turn trajectories. The generator uses the supplied region information to produce a new single-turn query, and we evaluate the target model’s response to that query. This experiment measures retrospective reconstruction given an observed crossing region.
Response to Q1: With independently labeled behavioral crossings, the first unsafe response showed a positive localization gap in both BGE-M3 and Doubao Embedding. The result depended on how we defined the crossing location. When we used the segment midpoint, the interval included zero in both spaces. The original small positive alignment effect also did not replicate across all 18 events.
Encoding sensitivity in the original manuscript
Appendix D.2, Table 9 examines five ways of encoding responses with BGE-M3. For Doubao 1.6 responses on Attack_600, the main configuration yielded 242 SVM-defined crossing points and eight non-noise clusters. Encoding only the first 512 tokens yielded 339 crossing points and six clusters. Averaging embeddings across 512-token chunks yielded 347 crossing points and two clusters. Table 9 thus shows how response truncation and aggregation affect crossing detection and clustering within BGE-M3. The supplementary analysis below addresses the cross-encoder question directly.
Localization and alignment across all 18 behavioral crossings
We used Doubao Embedding (
doubao-embedding-vision-251215) as the alternative encoder. An independent judge with access to the dialogue history identified 18 first behavioral crossings, 16 on Crescendo and two on Attack_600. We evaluated the same events in both embedding spaces, matched them to Safe-to-Safe controls, and constructed a single reference center in each space using other intents. A positive localization gap means that the observed location was closer to the reference center than its matched control.The localization result in this pilot applies to the first unsafe response in a judge-identified transition, measured relative to a single reference center. The original analysis located each crossing by interpolation at the SVM boundary and measured its distance to the nearest cluster centroid.
Event-level agreement and the selected nine-event subset
Across all 18 events, the alignment differences were positively correlated between encoders (Pearson’s r = 0.73), and the two encoders agreed on the sign for 13 of 18 events. This correlation describes how alignment differences varied from event to event across the two spaces. The overall mean difference was close to zero in each space.
In a descriptive subset analysis, we selected the nine events with a positive alignment difference under BGE-M3. Holding those events and their matched controls fixed, the mean difference was +0.0972 under BGE-M3 and +0.0560 under Doubao Embedding.