- Rating
- 2
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 1
- Soundness
- 2
Read review
Paper summary
The existing defense methods suffer from two limitations: 1) Lack of policy agility: existing methods can only support a fixed set of harmful concepts, making it difficult to adapt them into dynamic policies. 2) Stateless safety pipelines: current designs can only evaluate independently of previous interactions and perform poorly on multi-turn attacks. To address this issue, this paper proposes a stateful defense framework that can be used to defend against multi-turn text-to-image jailbreaks. The contributions are as follows: 1) It uses cross-modal concept scoring to project text and image information into a shared embedding space to enable customizable concept vectors. 2) It formulates the prompt evaluation as a semantic matching problem to guide fine-grained editing operations. 3). It uses a lightweight intent recognizer to effectively detect harmful behaviors.
Critical strengths
-
The proposed pipeline is useful in defending against multi-turn text-to-image jailbreaks.
-
Empirical results show that the proposed text filter and image evaluator have SOTA or near-SOTA performance.
-
The computational cost of the online version is low.
Critical weaknesses
Overall, this paper is hard to follow due to a lack of clarity.
In general, most figures and tables are not self-explanatory enough. Some parts of figures and tables remain unclear even after the explanation in the main text. Specifically,
- In Fig. 2: what is the setting of w/ and w/o concept?
- Fig. 3 is very unclear to me. What are the x and y axes? What is the difference among the three subplots?
- The use of terms in Fig.4 is very inconsistent with the explanation in Section 3.2. E.g., the terms “Sensitive Vector Scoring”, “Cross-Modal Projection”, “Temporal Prompt Parsing”, “Session Intent Recognition”, “Online Defense Pipeline” are not mentioned in the explanation of Fig. 4.
- The Sensitive Vector Scoring, Temporal Prompt Parsing, and Session Intent Recognition in Fig. 4 look somewhat disconnected. It is not clear to me how these components interact with each other.
- Tables 1- 7: It would be better to describe the key components in these tables. The current version is not self-explanatory enough.
- In Fig. 5, what are B, S, and V?
- In Fig. 6, the meaning of SP, JF, and IN should also be mentioned in the caption.
Algorithm 1 is not in a good format. It would be better to use a single-column layout that only takes half the page width. Also, the meaning of K, M, D, and A should be described in the algorithm.
In Section 3.1, the threat model is only introduced at a high level, although it is introduced in later sections. Here, an appropriate cross-reference to further details about the threat model should be provided.
It is not clear to me how the Cross-Modal Concept Scoring component compares with SOTA scoring methods.
Tables 2 and 3 compare the text filter and image evaluator components with SOTA methods. I wonder how the overall online defense pipeline compares with SOTA methods. It is also not clear to me which parts of the proposed pipeline correspond to the text filter and image evaluator.
This framework features a training-free concept scoring method but still requires training in Session Intent Recognition. Thus, emphasizing the training-free nature of one component of the pipeline is somewhat misleading.
Why are some categories not supported in Tables 3, 4, and 12? The explanation is missing.
It would be nice to compare the computational cost of the proposed method with SOTA methods.
Questions for authors
Please see Critical Weaknesses for my questions.
10 comments
Response for Reviewer LSji (2/3)
W2: Cross-references for the threat model
In Section 3.1, the threat model is only introduced at a high level, although it is introduced in later sections. Here, an appropriate cross-reference to further details about the threat model should be provided.
Thank you for the suggestion. We added cross-references in Sec. 3.1 that link the threat model to the detailed settings:
- the attack methods and dataset construction in Sec. 5.1 and Appendix C.3;
- the online defense protocol and attack-success criteria in Sec. 5.4 and Appendix C.4;
- the defense-aware adaptive attack evaluation in Appendix D.
These links let readers see how the attacker's interaction capabilities, the system feedback, the attack budgets, and the evaluation procedure are instantiated in the experiments.
W3: Comparison with SOTA scoring methods and the overall pipeline
It is not clear to me how the Cross-Modal Concept Scoring component compares with SOTA scoring methods.
Tables 2 and 3 compare the text filter and image evaluator components with SOTA methods. I wonder how the overall online defense pipeline compares with SOTA methods. It is also not clear to me which parts of the proposed pipeline correspond to the text filter and image evaluator.
Thank you for pointing out this unclear correspondence between components and evaluations.
Our Cross-Modal Concept Scoring applies the same concept vectors to text prompts and to generated images. It therefore is the text filter and the image evaluator in our pipeline. Tables 2 and 3 compare it directly with SOTA text and image filters. It achieves an average text AUROC of 0.9610 and image AUROCs of 0.9689 / 0.9722 on Sexual / Violence.
At the system level, IntentTrace consists of three detection stages: (1) pre-generation text filtering (concept scoring on the prompt), (2) CAT-based session intent recognition, and (3) post-generation image filtering (concept scoring on the generated image). Stages 1 and 2 can block a request before the T2I generator is invoked.
For pipeline-level comparison, no existing baseline is a directly comparable stateful multi-turn defense pipeline to the best of our knowledge. We therefore ran a controlled stateless vs. stateful comparison on SD1.4. The stateless variant uses only request-level filtering (text and image filters), and the stateful variant adds session intent recognition. Adding it reduces the T2I invocation rate from 58.14% to 24.18% and the ASR from 1.12% to 0.47%.
W4: "Training-free" claim
This framework features a training-free concept scoring method but still requires training in Session Intent Recognition. Thus, emphasizing the training-free nature of one component of the pipeline is somewhat misleading.
We agree that the original wording could suggest that the whole framework is training-free. We revised the relevant statements in the Abstract and Introduction to say that the advantage of concept scoring is its support for flexible policy customization. Appendix E also shows that a new concept (Cat) needs only a new concept vector and threshold calibration, with CAT not retrained.
W5: Unsupported categories in tables
Why are some categories not supported in Tables 3, 4, and 12? The explanation is missing.
Thank you for pointing this out. We now explain every "–" entry in the table notes and in Appendix C.2. (Table numbers below follow the revised manuscript; the ablation table and the per-dataset image table you refer to as Tables 4 and 12 are now Tables 5 and 13.)
- Tables 3 and 13: "–" means the category is outside the baseline's original detection scope. Some image safety detectors are designed for specific content categories only (e.g., SD Checker and Falconsai target Sexual content, and Q16 targets Violence). We therefore compare each baseline only on the categories it supports, to keep the comparison fair. Supported categories and implementation details are given in Appendix C.2.2.
- Table 5: "–" under Benign means "not applicable". Detection Prefix is the position of the first positive prediction, which is defined only for malicious sessions.
Response for Reviewer LSji (3/3)
W6: Computational cost comparison with SOTA methods
It would be nice to compare the computational cost of the proposed method with SOTA methods.
Thank you for the suggestion. We added a cost comparison for the text filters, the image evaluators, and the session-level intent recognition pipeline. We report p50/p95 latency, peak system memory, and peak GPU memory, all measured on the same hardware (Appendix H, Tables 21–23).
1. Text filters and image evaluators
Text filters (Table 21):
| Method | p50 (ms) | p95 (ms) | Peak memory (MiB) | Peak GPU memory (MiB) |
|---|---|---|---|---|
| TextMatch | 0.07 | 0.08 | 150.73 | 0.00 |
| TextClassifier | 1.52 | 1.58 | 1610.39 | 610.00 |
| Detoxify | 2.61 | 2.71 | 1839.08 | 1436.00 |
| GuardT2I | 176.17 | 296.14 | 1889.31 | 3058.00 |
| IntentTrace (Ours) | 3.36 | 3.39 | 1500.20 | 1276.00 |
Image evaluators (Table 22):
| Method | p50 (ms) | p95 (ms) | Peak memory (MiB) | Peak GPU memory (MiB) |
|---|---|---|---|---|
| Falconsai | 11.29 | 11.79 | 1535.35 | 714.00 |
| MHSC | 73.76 | 74.55 | 1655.93 | 2016.00 |
| Q16 | 19.11 | 19.65 | 1722.30 | 2016.00 |
| SD Checker | 20.78 | 21.38 | 1847.41 | 1518.00 |
| IntentTrace (Ours) | 15.47 | 16.02 | 1700.67 | 1312.00 |
Our text filter runs at a median of 3.36 ms, on the same order as lightweight classifiers such as TextClassifier and Detoxify, and about 52× faster than GuardT2I (176.17 ms). Its peak GPU memory (1,276 MiB) is also well below GuardT2I's (3,058 MiB). Our image evaluator runs at a median of 15.47 ms with 1,312 MiB of peak GPU memory, faster than MHSC, Q16, and SD Checker. Overall, the cross-modal concept scoring supports both text and image screening at a small per-request cost.
2. Complete session-level intent recognition pipeline
No directly comparable stateful multi-turn T2I intent-recognition baseline exists, so we use the stronger Qwen3.8-27B History LLM as the reference. For IntentTrace, the measurement covers the whole path from raw prompt to final intent score: semantic chunking, embedding encoders, UOT alignment, action-token construction, and CAT inference.
Session-level intent recognition (Table 23):
| Method | p50 (ms) | p95 (ms) | Peak memory (GiB) | Peak GPU memory (GiB) |
|---|---|---|---|---|
| Qwen3.8-27B History LLM | 433.16 | 634.05 | 14.51 | 13.12 |
| IntentTrace (Qwen3.5-9B LLM chunker) | 462.52 | 676.49 | 4.36 | 9.54 |
| IntentTrace (MiniLM-L6 student chunker) | 34.28 | 37.38 | 1.92 | 3.76 |
With the original 9B chunker, IntentTrace has latency comparable to the 27B History LLM while using less memory (9.54 vs. 13.12 GiB GPU, 4.36 vs. 14.51 GiB system).
3. Lightweight student chunker
Most of the overhead comes from LLM-based chunking, so we further investigate a deployment configuration that replaces the LLM chunker with a lightweight MiniLM-L6 sequence model. The student pipeline reduces the median latency of the complete intent recognition from 462.52 ms to 34.28 ms (about 92.59% lower) and the peak GPU memory from 9.54 to 3.76 GiB (60.59% lower). Session accuracy stays comparable (94.95% vs. 94.99%), and attack-session accuracy is 96.36%.
In summary, IntentTrace's text and image scoring is low-cost, and its structured edit representation also allows a lightweight session-level detector. Detailed measurements for every component are in Appendix H of the revised manuscript.
Response for Reviewer LSji (1/3)
Dear Reviewer LSji,
Thank you for your detailed feedback, and for acknowledging that our pipeline is a useful and low-cost defense against multi-turn T2I jailbreaks. Please see our point-by-point responses to your comments below.
W1: Clarity of figures, tables, and algorithm
Thank you for the detailed and specific feedback. We clarify Figs. 2 and 3 below and have revised the remaining figures, tables, and algorithm for clarity.
Fig. 2 (meaning of "w/ concept" and "w/o concept"). "w/ concept" and "w/o concept" denote the two sides of our contrastive prompt pairs, which share similar subjects, scenes, and styles and differ mainly in whether the target sensitive concept is present. The figure visualizes the concept-related displacement of these pairs in the BLIP embedding space, together with benign prompts from MSCOCO and malicious prompts from DREAM.
Fig. 3 (axes and subplots). We added the missing y-axis labels. The x-axis is the normalized request order within a session. The three vertically arranged panels show the text toxicity score, the image toxicity score, and the cosine similarity between consecutive prompt embeddings. Each colored trajectory is one real-user session, and each point is one request. The axes and panels are now defined in both the figure and the caption.
Fig. 4 and Sec. 3.2 (terminology and component interaction). We redesigned the figure with consistent module names, explicit data-flow arrows, and execution-order labels, and updated Sec. 3.2 to use exactly the same terms. The interaction between the modules is now described as follows:
Tables 1–7 and Figs. 5–6 (definitions and abbreviations). We expanded the table notes and figure captions to define the key components, metrics, and abbreviations. B / S / V denote Benign / Sexual / Violence, and SP / JF / IN denote SneakyPrompt / JailFuzzer / Inception. The original Fig. 5 has also been replaced with a more comprehensive Table 4, which presents a unified comparison of different intent recognition baselines.
Algorithm 1 (layout and notation). We reformatted the algorithm into a single-column layout and defined K, M, D, and A in the algorithm as the sets of chunks assigned the Keep, Modify, Delete, and Add actions, respectively.