- Rating
- 2(+1)
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
FAME is a black-box multimodal jailbreak method that selects images from a pre-generated pool. It combines two within-query filters—a neighborhood constraint around failed candidates and an energy-based constraint aggregating previous failures—with a classifier trained on historical attack outcomes to rank candidates for a target model. The selected image is combined with a typographic rendering of the query. The paper evaluates four benchmarks and eight MLLMs, reports an average ASR of 67.4%, compared with 58.3% for the strongest baseline in terms of average ASR, and provides component-wise ablations and a six-round comparison with HADES on Qwen-VL-Chat
Critical strengths
-
The paper addresses a practical problem: allocating limited target-model queries more effectively during multimodal safety evaluation. The association between visual proximity and attack outcomes reported in Figure 3 provides an empirical motivation for avoiding similar candidates. Using actual target-response outcomes also differs meaningfully from optimizing an image-harmfulness proxy.
-
The reported gains are substantial and span several datasets and model families. Table 1 reports average ASRs of 67.4% for FAME and 58.3% for VRP, although VRP remains stronger on Gemini across all four benchmarks. On Qwen-VL-Chat/HADES, Table 2 reports 52.9% for random selection, 82.5% for neighborhood filtering, and 88.9% for the full method; Figure 4 also shows an advantage over HADES across multiple rounds. These results suggest that the selection heuristic can be useful.
Critical weaknesses
-
The methodological increment and its attribution remain insufficiently established. HADES (Li et al., 2024; https://arxiv.org/html/2403.09792v3#S3.SS2) already uses feedback-driven image refinement, although its image-generation feedback concerns a harmfulness proxy rather than the victim outcomes used here. FAME's distinct contribution is therefore the particular failure-based filtering and historical scoring scheme. Under the stated fixed-pool, binary-feedback, stop-on-success protocol, with a fixed classifier and fixed selection randomness, every continuing history consists only of failures. Assuming no response-text feedback or within-query classifier updates, its candidate order can be computed in advance along this all-failure history. This is a property of the stated protocol, not a proof that the heuristic is ineffective; a good fixed ordering can itself be useful. However, the current experiments do not establish what is gained beyond diversity-aware candidate selection and additional historical supervision. Table 2 lacks a matched diversity-selection control and target-specific versus pooled or cross-model classifier comparisons. It also does not isolate the energy constraint's contribution when both neighborhood filtering and the classifier are present. Given the limited methodological novelty, the available attribution evidence is insufficient to establish a compelling contribution.
-
The evaluation protocol does not adequately substantiate model adaptation or performance under comparable resources. Section 3.2.2 describes a discriminator trained for each target using that target's historical outcomes, whereas Section 4.1 describes one open-weight surrogate and transfer evaluation on the remaining models. Their relationship needs clarification: which model supplies the historical labels and the online feedback for each result? The historical dataset's size, source, separation from test queries, and label-acquisition cost are unspecified. These details determine whether the results demonstrate target adaptation, transfer, or benefits from additional supervision. Figure 4 provides useful six-round evidence for one model/dataset, but does not establish matched target-query budgets and stopping rules for all Table 1 baselines; the random-selection protocol in Table 2 is also insufficiently described. Without these details, I cannot confidently attribute the reported gains to the proposed search strategy under comparable resources. These are unresolved protocol questions, not evidence of leakage or proven budget inequality.
-
Given the dual-use nature of the proposed jailbreak method, the paper would benefit from an explicit discussion of potential misuse and responsible release of code, attack examples, and historical attack data. The current limitations discussion primarily addresses technical constraints.
Questions for authors
-
For each evaluated model, which model supplies the proxy-training labels and which supplies feedback during search? Please reconcile Sections 3.2.2 and 4.1, and report the historical training-set size, source, query-level separation from evaluation, and acquisition cost.
-
Do the main baselines and random selection receive the same target-query budget and stop-on-success rule? For the random control, are candidates sampled without replacement from the same image pool? Please distinguish online target queries from historical-data acquisition and image-generation costs.
-
What evidence distinguishes failure-aware selection from a fixed diversity-based ordering under the same pool and query budget, and the target-specific classifier from one trained on pooled or other-model outcomes? The neighborhood-plus-classifier ablation without the energy constraint would additionally clarify the contribution of that component.
3 comments
Thank you for your response, but since you do not have an updated version of the paper, I am maintaining my score.
Updated Manuscript with Revisions Highlighted in Blue
Thank you for your feedback. We apologize that the revised manuscript was not available earlier, as we were still incorporating the revisions. We have now uploaded the updated version, with all changes highlighted in blue for clarity. We would greatly appreciate it if you could review the revised manuscript and reconsider your assessment. Thank you for your time and consideration.
Response to Reviewer MReA Comments
W1: We thank the reviewer for the feedback. Unlike HADES, which relies on image-harmfulness feedback, FAME exploits victim-model failures and historical outcomes for candidate selection. We clarify that the proxy discriminator is not fixed: to mitigate cold-start issues, we first pretrain a shared discriminator, assign an independent copy to each target model, and update each copy every 50 attack rounds using target-specific feedback. These updates enable adaptation across queries. To further validate our contributions, we provide matched-budget comparisons against diversity-based selection and classifiers trained on different model outcomes (Table 1), together with an additional ablation isolating the energy constraint (Table 2).
Table 1. Diversity selection and classifier adaptation (Qwen-VL-Chat / HADES, ASR %).ICC: Inter-Class Constraint.
Table 2. Contribution of energy attenuation (Qwen-VL-Chat / HADES, ASR %).ICC: Inter-Class Constraint. NC: Neighborhood Constraint. EAC: Energy Attenuation Constraint.
W2: To mitigate cold starts, we pretrain a shared discriminator Dθ on 200 labeled Do-Not-Answer samples, disjoint from the four evaluation benchmarks, requiring 200 offline surrogate queries. Each target MLLM maintains an independent copy, updated every 50 attack rounds using only its prior feedback. Thus, target-specific updates enable model adaptation without future-label leakage. We will clarify this in Sections 3.2.2 and 4.1.
We clarify that FigStep, MMSB, VRP, and BAP are evaluated under their original single-shot protocols, while HADES and FAME allow up to six attempts. To ensure fair comparisons, we provide equal-budget ASR@1–6 results under a consistent stop-on-success rule, including Best-of-N, HIMRD, and MIRAGE, as shown in Table 3. Random selection samples without replacement from the same 20-image pool under an identical query budget and stopping rule. We will clarify these protocols and separately report offline costs.
Table 3.
W3: We acknowledge FAME's dual-use risks and will expand the limitations to address potential misuse. Our responsible release strategy will share aggregate results and sanitized examples while restricting sensitive attack data, harmful outputs, and reusable attack materials to support reproducibility while minimizing misuse.
Q1: To avoid cold starts, we pretrain a shared discriminator Dθ on 200 labeled Do-Not-Answer samples, disjoint from all four evaluation benchmarks, using 200 offline queries. Each target MLLM maintains an independent copy, updated every 50 attack rounds using only its prior feedback. Thus, shared pretraining and target-specific updates enable model adaptation. We will clarify this in Sections 3.2.2 and 4.1.
Q2: We clarify that FigStep, MMSB, VRP, and BAP were originally evaluated under their single-shot protocols, while HADES and FAME allow up to six attempts. Random selection uses the same 20-image pool, samples without replacement, and follows the same query budget and stop-on-success rule as FAME. Following the reviewer's suggestion, we additionally provide equal-budget ASR@1–6 comparisons under a consistent stop-on-success rule, as shown in Table 3.
Q3: To isolate the contribution of failure-aware selection, we compare FAME with fixed farthest-point diversity ordering under identical candidate pools and query budgets(Table 4). We further compare target-specific, and cross-model classifiers under matched training budgets (Table 4). Additionally, we remove the energy constraint while retaining neighborhood filtering and the classifier to quantify its independent contribution (Table 5).
Table 4. Diversity selection and model-specific adaptation (Qwen-VL-Chat / HADES, ASR %). ICC: Inter-Class Constraint.
Table 5. Contribution of energy attenuation (Qwen-VL-Chat / HADES, ASR %).