- Rating
- 2
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
The paper proposes VIVID, an image-only black-box attack against multimodal agent memory. It combines scene-dominant target construction, a cross-family encoder ensemble, and delivery-aware optimization. Evaluation covers five memory backends and four victim models across three memory benchmarks and an additional query-time benchmark. The results demonstrate false-content insertion, retrieval changes, and subsequent false assertions. The paper also evaluates image purification and memory-level detection, including their effects on benign content and genuine memory.
Critical strengths
-
A meaningful threat model with evidence of memory corruption. The attacker controls image pixels, and an explicit information barrier separates attack construction from evaluation queries. Results on description-based stores show that false content can enter stored text before recall, providing concrete evidence of corruption during memory ingestion.
-
Substantial robustness and defense evaluation. The paper includes competitive transfer baselines, documented implementation checks, and delivery transformations outside the optimization distribution. The delivery-aware ablation shows a substantial effect. Defense experiments also report false alarms, benign-content degradation, and genuine memory lost through isolation.
Critical weaknesses
-
Some stage metrics appear inconsistent with their definitions. In Table 19, GPT-5.6-Luna with MMMemory on WMA-Embodied has 4/10 final hits, 69.2% retention, and 86.7% image-level transfer. Under the stated 15-goal evaluation, 13 goals transfer; Equation 11 would therefore imply approximately nine joint transfer-and-memory successes, exceeding the four reported final hits. The evaluation populations, exclusions, or reported values need reconciliation before retention and bottleneck conclusions can be assessed.
-
Comparative effectiveness is established mainly at the image level. Figures 2–3 compare attacks through isolated-image transfer, while Table 1 reports full memory-pipeline ASR only for VIVID. Its delivery columns also contain image-level rates shared across backends. Since writing, retrieval, and generation substantially affect success, matched end-to-end comparisons are needed to establish the advantage in the paper’s central memory setting.
-
The future-query and dormancy claims need tighter empirical support. Evaluation recall questions often explicitly name the selected hazard. The information barrier and clean/noise controls support a conditional vulnerability under these probes; independently specified questions would establish broader query generalization. Furthermore, ordinary-answer degradation reaches 14.5–24.5 percentage points on MemLens. This requires reconciliation with the dormancy constraint in Equation 4, even when text-grounded memory diagnostics remain stable.
Questions for authors
-
Can you reconcile the hit counts and retention values in Table 19, specifying the exact populations and exclusion rules used for each metric?
-
Does VIVID outperform the strongest transfer baseline through the complete memory pipeline under both unchanged and transformed delivery?
-
Is each memory run evaluated with exactly one poisoned image? How do results vary with independently specified recall questions and the delay between ingestion and recall?
4 comments
W2: Comparative effectiveness is established mainly at the image level.
Thank you for this suggestion. We ran the requested matched end-to-end comparison: VIVID outperforms the strongest transfer baseline, M-Attack-V2, through the complete memory pipeline on every backend; pooled, the margin is large under transformed delivery and small under unchanged delivery.
Setup: MemLens (our primary benchmark) at ε = 16/255, four backends (MMMemory, UniversalRAG, AUGUSTUS, ViLoMem) and two victims (Gemma-3-27B, GPT-5.6-Luna). M-Attack-V2 is compute-matched as in Appendix D.2, and delivery is unchanged, JPEG30 or RESIZE80 (both held out; Table 16). To isolate where the gain comes from, we also report M-Attack-V2 with VIVID's delivery-aware term added (VIVID without its SigLIP surrogate, Table 14).
| Delivery | VIVID | M-Attack-V2 | M-Attack-V2 + delivery-aware | VIVID gain over M-Attack-V2 |
|---|---|---|---|---|
| Unchanged | 26.7 | 23.2 | 18.9 | +3.5 |
| JPEG30 | 23.2 | 7.0 | 17.3 | +16.2 |
| RESIZE80 | 10.5 | 1.9 | 10.8 | +8.6 |
ASR (%), pooled over 4 backends × 2 victims × 47 goals.
As the above table shows, VIVID's advantage carries through the memory pipeline. Under unchanged delivery, the gain matches the modest 2.7 to 4.5-point image-level margin of Figs. 2 and 3. Under transformed delivery, M-Attack-V2's poison rarely survives, while VIVID's survives far more often at each stage: under RESIZE80, VIVID's poisoned record is still retrieved first on UniversalRAG for 55% of goals (M-Attack-V2: 30%; Table 19) and still written into ViLoMem's stored descriptions (6% vs 0%). The transformed-delivery gain holds for each victim separately (8.1 to 18.8 points). Adding VIVID's delivery-aware term to M-Attack-V2 recovers most of this robustness (17.3% and 10.8%), so the gain comes from VIVID's delivery-aware design, and VIVID's cross-family surrogate adds strength on unaltered pixels (26.7% vs 18.9%), as in the image-level ablation (Fig. 9). This is the delivery robustness VIVID is designed for (Sec. 5.2).
Paper Revision: The revised version adds this comparison to the evaluation in the main paper (Sec. 7), with per-backend and per-victim results in the appendix, and clarifis in Table 1's caption that its delivery columns report image-level transfer.
W3a: Is each memory run evaluated with exactly one poisoned image?
Yes on MemLens, our primary evaluation benchmark: each of its 47 memories holds exactly one poisoned image. WMA-Personal and WMA-Embodied memories hold several (15 to 18 and 3 to 4), each with its own recall question. Mem-Gallery attaches the poisoned image at query time and stores none.
W3b: How do results vary with independently specified recall questions?
Thank you for raising this. Eq. 4 requires the false content to surface only for queries that depend on the poisoned observation, supp(Q). Our recall questions are such queries: a user checks the image for a type of content (“What X, if any, is visible?”). The question names the poison type (Table 5 in the revised version), not the false content: for a climber photo poisoned with a crossbow, it asks “What weapon, if any, is visible?”. Our threat model assumes the user to ask it, not the attacker.
We added questions written without access to the hazard or the poison, five wordings each (MemLens, five backends, same judge and ASR):
| Question type | Gemma-3-27B | GPT-5.6-Luna |
|---|---|---|
| Names the type ("What {type}, if any, is visible?") | 44.9 | 38.5 |
| Type removed ("What hazards, if any, are visible?") | 14.0 | 16.9 |
| Generic safety | 6.4 | 6.3 |
| Planned activity + safety | 3.6 | 5.3 |
| Other tasks about the scene | 0.6 | 0.1 |
ASR (%); a memory counts if any of its five answers asserts the false content (Table 40).
As shown, the false memory surfaces without being specificlaly named, most often when the user checks for its type, and fades as the question depends less on the poisoned attribute, although the record is retrieved for nearly all other-task questions. This is what dormancy requires: a record that surfaced for any question about the scene would expose itself in ordinary use.
W3c: How do results vary with the delay between ingestion and recall?
They change little. We re-asked the recall question after the rest of each memory's history was ingested (median 6, 17.5 and 8 further sessions on MemLens, WMA-Personal and WMA-Embodied). ASR changes by −4.5 points on average for Gemma-3-27B and −2.8 for GPT-5.6-Luna, and the change does not grow with delay (correlation 0.05 and 0.12). No backend scores or evicts memories by time, so delay acts only through the records added in between.
W3d: Ordinary-answer degradation on MemLens and Eq. 4.
This degradation is the cost of changing the queried image, not a leak outside supp(Q): on MemLens, 47 of 50 ordinary questions per run ask about the poisoned image. Pooled over victims, the effect is omission, not fabrication: QA-O rises by 11 to 21 points while QA-H moves by at most 5 (Table 1). Where most ordinary questions concern other images (WMA-Embodied), degradation stays at −2.4 to +5.2 points, and the memory diagnostics stay flat.
Paper Revision: The revised version adds the query-generalization results, question wordings and delay analysis to the appendix (F.10, F.11), and clarifies in Sec. 7 that MemLens collateral measures ordinary visual questions about the attacked image.
Dear Reviewer bhD1,
Since the Author/Reviewer discussion period concludes today, we would be happy to address any remaining concerns or questions.
Thank you.
We sincerely appreciate the reviewer's valuable comments. We have incorporated the results of these comments to improve our paper. We hope that our response can address the raised concerns. Please let us know if there are any further questions.
W/Q1: Reconciling hit counts and retention in Table 19 (Table 24 in the revision).
We thank the reviewer for the careful check. The two columns use different goal populations by design. ASR (the hits column) measures whether the attack causes the answer: it counts testable goals and excludes any goal whose clean-run answer already asserts the target, since such a hit cannot be attributed to the attack. Retention measures how often the image-level effect survives the memory pipeline, so its denominator must be the goals that transfer at image level, and is identical across the five backends of a victim. Additionally, similar to image-level transfer, it does not apply clean-hit exclusion as each backend has its own clean run, so the exclusion would give each backend a different denominator.
For the example you raise (GPT-5.6-Luna, MMMemory, WMA-Embodied), 13 of the 15 goals transfer. Five goals are excluded from ASR because their clean-run answer already matches the target, so ASR is 4/10. All five also transfer and are asserted in the attacked run, so retention counts 4 ASR + 5 transfer = 9 of 13, the 69.2% reported in Table 24.
This exclusion is uncommon and makes ASR conservative. It removes 1.2% of goals on MemLens, 0.5% on Mem-Gallery, 5.6% on WMA-Personal and 10.3% on WMA-Embodied, and without it ASR would be equal or higher on every benchmark. GPT-5.6-Luna on WMA-Embodied is where it matters most: its clean run matches the target on 24% of goals, against at most 12% for any other victim on this WMA-Embodied benchmark. These are false alarms on hazard questions: in the the GPT-5.6-Luna on WMA-Embodied cell, four of the five clean answers name a hazard the scene does not contain, and the benchmark’s own judge labels all five as hallucinations.
The population and exclusion rule of each stage metric:
Our conclusions do not depend on this choice. Counting only ASR hits in retention, MemLens retention still spans 25.9 to 53.4% (reported 25.9 to 55.2%), and the Qwen3-VL vs Gemma-3 comparison of Appendix F.3 is unchanged; the bottleneck conclusions of Sec. 7 rest on write-ASR, rank promotion and ASR rather than retention.
Paper Revision: The revised version states each metric's population in Eq. 11 and Appendix E, reports the retained count next to each retention value and the number of transferring goals next to Table 1's transfer band, and adds retention restricted to ASR hits as an additional column.