- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper proposes a hierarchical Transformer for multi-turn jailbreak detection. It encodes individual conversation turns using a pretrained multilingual E5 model and aggregates their representations through a conversation-level Transformer with self-attention and cross-attention to token-level features. Evaluated on 14,038 conversations, the model achieves an F1 of 0.9394, outperforming the evaluated Llama and Claude baselines. Ablation studies examine the contributions of attention components and model depth.
Critical strengths
-
Multi-turn jailbreak detection is an important problem, and the paper presents a practical supervised approach with strong reported performance across a relatively large evaluation benchmark.
-
The ablation studies provide useful evidence for the architectural components. Combining self-attention and cross-attention improves recall and reduces false positives compared with either component alone. The improvement over mean pooling also supports the usefulness of learned conversation-level aggregation.
Critical weaknesses
- Limited methodological novelty and insufficient justification for the proposed architecture.
The architecture primarily combines established techniques, including independent turn encoding, hierarchical Transformers, self-attention, cross-attention, and attentive pooling. The paper does not clearly establish what methodological insight distinguishes this combination from existing hierarchical sequence classification approaches.
More importantly, the experiments do not demonstrate why this particular architecture is especially suitable for multi-turn jailbreak detection. Although the ablations show that attention components improve classification performance, they do not establish that the model captures evolving adversarial intent or dependencies across turns. Comparisons with last-turn-only classification, turn-order perturbations, or context-dependent attack subsets would help establish whether explicit multi-turn reasoning is responsible for the improvements.
- Missing competitive detection baselines and insufficient validation of scalability.
The main comparisons use prompted general-purpose LLMs rather than specialized jailbreak or safety detectors. Relevant models such as WildGuard and Llama Guard, as well as supervised full-context classifiers trained on the same data, are missing. Moreover, the proposed model is fine-tuned on nearly 100K conversations, whereas the Llama and Claude baselines receive no comparable task-specific training. The concatenation baseline is also limited to four turns. These differences make it difficult to attribute the reported improvements to the proposed architecture.
Scalability is another central claim, but the evidence is limited to theoretical attention-complexity calculations. No empirical measurements of inference latency, GPU memory, or throughput are provided. Furthermore, the model retains only the most recent 24 turns, while the evaluation benchmark contains conversations of up to 102 turns. It remains unclear how effectively and efficiently the approach handles genuinely long conversations.
The evaluation also mixes datasets labeling successful jailbreaks with those labeling jailbreak attempts. Since previous assistant responses are included in the input, the model may exploit cues associated with prior response outcomes rather than detecting adversarial intent itself. This further complicates the interpretation of the reported performance.
Questions for authors
-
What makes the proposed hierarchical architecture particularly suitable for multi-turn jailbreak detection, beyond its general applicability to long-sequence classification? How does performance change when only the final user turn is provided or when turn order is shuffled?
-
How does the method compare with existing specialized jailbreak detectors and supervised full-context classifiers under matched training and evaluation conditions?
-
Can the authors provide measured inference latency, GPU memory usage, and throughput, along with performance broken down by conversation length, especially for conversations exceeding 24 turns?
-
How are successful jailbreaks and attempted jailbreaks distinguished across datasets? Does performance remain consistent when labels are standardized and potentially informative assistant responses are excluded?
3 comments
Response to Reviewer pFbK (2/2): LLM baselines reframed, FLOP-based efficiency, length limits, and label semantics
W2/Q2. Specialized detectors and supervised full-context classifiers
We agree that the comparison as presented conflates architecture with supervision.
- Reframing. The Llama 3.3 70B and Claude results are now presented as reference points for general-purpose models used zero-shot, not as evidence of architectural superiority. The equally supervised evidence is the ablation above. We remove A.5's phrase "compelling evidence for the effectiveness of our approach" and qualify the corresponding contribution.
- Context length. We agree the 4-turn window, chosen as a low-latency operating point (A.6), is an unfair primary comparison, and Table 2 now labels it as such. The ToT OR and ToT Majority baselines use the same Llama 3.3 70B on the full conversation and reach F1 0.61 and 0.52, against 0.51 for the 4-turn variant, so the window does not explain the gap. All prompts are now in the appendix.
- Not yet done. We have not run Llama Guard 3, WildGuard, or a flat fine-tuned long-context classifier; Sec. 9 names the last as a missing control. These are the most important missing comparisons. A flat model with our backbone is impossible (multilingual E5 has 512 positions), so the right flat control is a fine-tuned multilingual long-context encoder. Both guard models are trained mainly on prompt- and response-level harm taxonomies, not on conversation-level manipulation.
Q3. Latency, memory, throughput; performance by length
We have not measured wall-clock latency or throughput. We replace the attention count with an end-to-end FLOP count (12-layer encoder plus 4-layer ConvTransformer vs. a same-size flat encoder, tokens per turn):
| Flat / ours, single pass | Flat / ours, per new turn (streaming) | |
|---|---|---|
| 8 | 1.3× | 10× |
| 24 | 2.1× | 47× |
| 96 | 5.7× | 319× |
For one pass over 24 turns the saving is moderate, and with FlashAttention peak memory is linear in both designs. The substantial saving is in per-turn re-scoring, so we propose the title "Efficient Hierarchical Transformers…".
Beyond 24 turns. Longer conversations are truncated to the most recent 24 turns; the limit comes from the learned position table, not the architecture. Benchmark jailbreaks have at most 32 turns, while safe conversations reach 102, so truncation mainly affects safe conversations. We have not evaluated head-plus-tail retention or sliding windows (A.6), so we make no claim about longer conversations. Padding attacks against the 256-token cap remain an open risk (Sec. 9, A.6).
Q4. Successful vs. attempted jailbreaks; informative assistant responses
Training labels are success-based, and the trailing assistant turn is removed in training and inference; earlier assistant turns remain in the input. The submission states this in A.2–A.4. The revision brings it into Sec. 3 and:
- defines the task as detecting manipulation in the history up to the latest user turn;
- adds a per-source label-semantics column (attempt vs. success) to Tables 7–8;
- states that results measure conversation-level classification with earlier responses visible, not detection before the first harmful response.
We have not harmonized labels or evaluated with assistant responses removed, and we do not claim robustness to either (details in our response to kN2B, W2). The onset-training follow-up uses intent-based prefix labels, a first step toward attempt semantics.
We hope the clarified contribution and corrected framing help, and we would be grateful if you would consider them in your final assessment.
Thank you for the detailed response and for acknowledging the limitations. The clarified contributions and additional FLOP analysis are helpful. However, my main concerns remain. The ablations do not directly establish that the model captures cross-turn dependencies, and comparisons with specialized detectors and equally supervised full-context classifiers are still missing. The efficiency claims also lack empirical validation. These issues are central to assessing the proposed method's contribution, so I will maintain my original score.
Response to Reviewer pFbK (1/2): narrowed contribution claims, equally supervised evidence, and context-dependent subsets
Thank you for the constructive review and for recognizing the ablations. We could not run new training for the requested controls within the rebuttal window. Where we answer from existing results or analysis, we say so.
W1. Novelty, and why this architecture fits the task
We agree that the building blocks are established: turn encoding, hierarchical Transformers, self- and cross-attention, and attentive pooling. We do not claim a new attention primitive, and the revised introduction and contributions say so. Our claims are narrower:
All variants in our ablation are trained on the same data with the same encoder and schedule:
Adding cross-attention keeps recall and cuts FPR by 2.26 pp (95% interval ±0.60), while CA-only loses recall (78.30).
Q1. Final user turn only, and shuffled turn order
These inference-only probes are not yet run, and we prefer not to post partial numbers. The existing evidence: