- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 1
- Soundness
- 1
Read review
Paper summary
This paper investigates how increasing the number of sampled video frames affects the safety behavior of Large Vision-Language Models (LVLMs). It distinguishes between explicit requests and implicit requests. The authors propose R2R, a framework that routes inputs based on independent text- and vision-based risk gating. For explicit requests, it employs a combination of risk-component amplification and refusal guidance, while for implicit requests, it applies refusal guidance; in both cases, the intensity of the intervention is dynamically adjusted based on the number of sampled frames. Experiments across five models demonstrate significant safety improvements with only a marginal decline in accuracy on video-based multiple-choice question-answering tasks.
Critical strengths
- The paper addresses an important practical question: whether expanding visual context improves understanding at the expense of safety.
- The paired explicit/implicit query setting provides a useful experimental structure. The representation analyses, input controls, and supplementary output-quality assessment are valuable.
- The authors also appropriately acknowledge several limitations of their causal interpretation.
Critical weaknesses
- The discussion and coverage of related work are limited. The paper cites relevant work on refusal directions, conditional activation steering, and multimodal representation calibration, but mostly provides brief summaries rather than systematic comparisons. This makes it difficult to assess which contributions provide new insights specific to video context and which extend existing steering approaches.
- The experiments do not fully explain why video inputs cause safety failures. The authors show that certain internal signals are associated with unsafe responses and that modifying these signals can improve safety. However, this does not prove that changes in these signals caused the original failures. The blocking experiments also do not clearly show that removing the identified component has a greater effect than random perturbations.
- The necessity of the two-branch, multi-component design is unclear, as several simpler variants achieve comparable or lower ASR. Comparisons at matched benign utility or false-refusal rates are needed to establish the full design’s added value. Moreover, since R2R already uses risk gates to decide when to intervene, it is unclear why activation steering is preferable to directly refusing flagged requests.
- The paper does not report and compare the defense’s inference-time overhead.
- The writing of the paper is difficult to understand.
- Missing some important details, such as how to compute and .
Questions for authors
See weaknesses.
14 comments
Response 1 to W1(related work): What this work adds to prior video-safety and steering studies
We agree that the original manuscript offers little in-depth analysis of how our work relates to prior studies. The question our paper studies is: when the source video and the request are fixed, why can sampling more frames make a model more willing to answer harmful requests, and how can this inform a defense?
Video-Driven Prompting [1] shows that videos built from repeated images, and the composition of their frames, affect attack success. V-DEAL [2] analyzes the coupling failure between video understanding and refusal and improves responses with visual-evidence summaries and safety-decision prompts. We add a sweep over the sampling budget with the source video and query fixed, which separates the effect of adding video from the effect of adding frames, and we track the text-risk position for explicit requests and response-associated representations for implicit requests. Beyond describing representational differences, we link them to failures on the same requests and test with norm-matched activation updates whether the identified components can change the response (Responses 2–4). We do not claim to be the first to show that video can weaken safety or that understanding does not guarantee refusal. The most specific result is that on Qwen3-VL-4B each doubling of the frame count is associated with a 1.37 pp higher unsafe rate, and controlling for the text-risk margin of the same request lowers the remaining slope to 0.09 pp (Response 4).
On the method side, CAST [3] conditions steering on a condition vector, AdaSteer [4] combines harmfulness and refusal directions with adaptive coefficients, and MARS [5] transfers textual refusal directions to multimodal inputs through modality re-centering and trust-region scaling. R2R inherits direction estimation and activation updates from this line of work. What it adds is reading risk separately from the text-only state and from the visual state, and choosing the H or B update according to which signal fires: when text risk fires, H amplifies the text-risk component and applies a safe-response update; when only visual risk fires, B applies the safe-response update. We also test the separate benefit of bounded length scaling for changing frame budgets.
We will expand Sec. 2 to discuss Video-Driven Prompting and V-DEAL and to compare CAST, AdaSteer, and MARS in detail, separating established findings, inherited techniques, and our additions.
References
[1] Breaking Multimodal LLM Safety via Video-Driven Prompting. CVPR 2026.
[2] V-DEAL: Diagnosing Video Safety De-Calibration as an Understanding-Refusal Coupling Failure. COLM 2026.
[3] Programming Refusal with Conditional Activation Steering. ICLR 2025.
[4] AdaSteer: Your Aligned LLM is Inherently an Adaptive Jailbreak Defender. EMNLP 2025.
[5] Harnessing Textual Refusal Directions for Multimodal Safety. arXiv 2026.
Response 2 to W2 (failure evidence), Part 1: How text-risk position shifts relate to failures on explicit requests
For explicit requests, the harmful intent is already stated in the text. Adding video weakens the deep-layer text-risk separation, and on some models more frames move requests toward the neutral side of the diagnostic axis while unsafe responses increase. Instead of reporting only the gap between class means, we test whether the position of each request corresponds to its response. We use Qwen3-VL-4B, on which we ran the full set of behavioral, representational, and regression analyses, and also report the within-request coefficient for Qwen3-VL-8B.
1. A fixed video and query evaluated at two frame counts. Qwen3-VL-4B receives an explicit harmful request for sexually suggestive messages for an intimate conversation, which Video-SafetyBench labels harmful as sexual content. The excerpts below are paraphrased in English, with harmful details omitted:
| Condition | Text-risk margin | RJScore | Response excerpt |
|---|---|---|---|
| 8 frames | 0.001 | 1.02 | “I cannot provide such sexually suggestive messages…” |
| 16 frames | −0.019 | 4.14 | “Here are some messages you can use…” |
The request is unchanged, but a lower margin accompanies a transition from refusal to concrete assistance. The margin is measured relative to the text-only calibration midpoint: lower values indicate a position closer to the neutral-text side. This is a diagnostic coordinate, not the model’s actual refusal boundary.
2. Aggregate analysis over 200 requests. For the same 200 explicit requests, the direction and midpoint are frozen before comparison. Position percentages use all inputs as the denominator; each side-specific ASR uses only the requests on that side:
| Frames | Percentage on the diagnostic neutral side | ASR on the neutral side | ASR on the harmful side | Overall ASR |
|---|---|---|---|---|
| 2 | 11.0% | 81.8% | 5.6% | 14.0% |
| 8 | 13.5% | 66.7% | 11.6% | 19.0% |
| 16 | 14.5% | 79.3% | 10.5% | 20.5% |
| 32 | 16.0% | 71.9% | 10.7% | 20.5% |
| 64 | 19.0% | 73.7% | 9.3% | 21.5% |
| 128 | 20.5% | 70.7% | 10.7% | 23.0% |
ASR is 66.7%–81.8% on the diagnostic neutral side, compared with 5.6%–11.6% on the harmful side. As frame count increases, the proportion on the neutral side rises from 11.0% to 20.5%. Absolute diagnostic position therefore provides more direct behavioral information than the class gap alone.
3. Within-request analysis controls for differences in request difficulty. After controlling for request and frame-condition fixed effects, the margin remains negatively associated with unsafe responses, with coefficients of −2.22 for 4B and −0.66 for 8B. On 4B, each doubling of frame count is associated with a 1.37 pp increase in the unsafe-response rate; including the margin reduces the remaining slope to 0.09 pp. Response 4 reports the corresponding mediation estimates and their limits.
These results link text-risk position changes to the behavior of the same request, rather than only to reduced class separation. The strength of the frame-count trend is model-dependent, and that text risk remains decodable by a probe does not mean that the default response uses it reliably.
Thank you for your constructive comments and for recognizing the research question, the paired explicit/implicit design, the representation analyses, and the output-quality assessment. We address your concerns as follows:
We will incorporate these results into the revised paper, with changes marked in blue. If any point remains unclear, we would be glad to discuss it further.