- Rating
- 3(+1)
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper investigates dual-conditional backdoors in vision-language models: the model is triggered to insert specific text only when both a visual trigger and a textual trigger are present, while otherwise continuing to provide the correct answers for standard tasks. The proposed method integrates dual-conditional training, ReLU-gated visual residuals, full-sequence constrained in-context learning (DKICL), and partially-supervised trigger training (PUDT). Furthermore, the authors examine whether the model will still generate the complete target text when one of the trigger conditions is missing, by providing the prefix of the target text as a prompt.
Critical strengths
- Prefix experiments reveal behaviors not captured by standard trigger tests: when DKICL is removed, the model maintains a low leakage rate with an empty prefix; however, once the first target token is provided, the worst-case single-condition leakage rises to 83.92%, compared to 0.42% when using the full method.
- The authors validated this phenomenon using four training seeds, two additional sets of target texts, suffix probability calculations, actual sampling, and interventions involving the disabling of residual connections.
- The experiments cover five model backends, with results reported for joint triggers, single-condition leakage, and performance on clean tasks.
Critical weaknesses
- DKICL encompasses four components: a four-condition interaction term, high-probability constraints under joint conditions, low-probability constraints for cases where conditions are absent, and a "shortcut" constraint that activates when the residual path is disabled. Removing the entire DKICL mechanism only demonstrates that these constraints collectively influence the model's continuation behavior; it does not establish whether the interaction term itself is necessary.
- The "clean" reference model for Qwen2.5-VL has not undergone additional task adaptation, whereas the attack model has. The performance gains derived from task adaptation may mask the performance degradation caused by the backdoor injection. Please include a control experiment that utilizes the same data, model architecture, and training budget, but without the backdoor injection.
- In the experiments, the first one or two tokens of the target text are manually provided at the beginning of the assistant's response, after which the subsequent leakage is measured. While this setup allows for the assessment of conditional continuation, it fails to account for the frequency with which these specific prefixes appear during standard, legitimate tasks.
Questions for authors
see Weaknesses
4 comments
Response to Reviewer pSC3 — Part II
W3 — Natural prefix frequency and continuation control
Thank you for asking about the natural occurrence of these openings. Our goal is a covert targeted backdoor that activates in a designated image–question context and suppresses unintended exposure elsewhere. In the paper's financial-report scenario, a targeted recommendation should remain dependent on the designated conditions throughout generation. The prefix experiment tests whether this dependency persists after a short opening, or is concentrated at the first token.
We added a frequency analysis of two public human-authored response corpora: English assistant messages in OASST1 (Köpf et al., 2023), filtered to reviewed, undeleted, non-synthetic messages, and all responses in Dolly-15k. No prefix is supplied. The table counts case-sensitive, response-initial word sequences, with a separate check using the paper's tokenizer. Each entry reports matching responses / total responses (percentage).
Table E. Natural response-initial prefix frequency.
| Opening | OASST1 | Dolly-15k |
|---|---|---|
| I | 1,618/24,258 (6.67%) | 100/15,011 (0.67%) |
| I have | 17/24,258 (0.070%) | 6/15,011 (0.040%) |
“I” occurs naturally in both corpora; “I have” is rare. Supplying just “I” allows frequent single-key target completion without DKICL, while GenLock suppresses it (the paper’s §6.3 and App. I.1).
To test continuation control beyond the response boundary, we added a third-word insertion experiment using the GenLock and no-DKICL checkpoints from App. I. We retained the first two words of GenLock's clean answer, supplied “I have”, and regenerated the continuation. Of 300 sources, 160 had two leading word units containing letters. Both models received the same source-specific context in all four input conditions. The table reports complete-target hits in the reconstructed greedy response.
Table F. Complete-target hits after third-word prefix insertion.
| Model | Clean | Visual only | Text only | Joint |
|---|---|---|---|---|
| GenLock | 0/160 | 0/160 | 1/160 | 154/160 |
| Without DKICL | 124/160 | 134/160 | 128/160 | 159/160 |
Table G. Mean exact suffix probabilities after third-word prefix insertion.
Temperature = 1.
| Model | Clean | Visual only | Text only | Joint |
|---|---|---|---|---|
| GenLock | 0.0021% | 0.0017% | 0.6216% | 92.4011% |
| Without DKICL | 59.8173% | 66.4700% | 66.0348% | 69.4485% |
GenLock retains low missing-key completion and high joint-key activation after the supplied prefix moves beyond the response boundary. Removing DKICL allows frequent target completion without both keys. On the same sources, GenLock's missing-key hit counts remain unchanged from the boundary intervention. This supports continuation control beyond the first token in the tested setting. Table 3 and Appendix O.2, Tables 40–41 report this diagnostic for the evaluated position and preceding contexts.
The corpus counts quantify the use of the openings in reference responses. The intervention tests measure conditional target completion. Appendix O reports both analyses and keeps these quantities distinct from deployment leakage rates.
Thank you for the detailed response and explanations! Most of my concerns and questions have been addressed, and I will raise my score accordingly.
Thank you for your thoughtful feedback and for updating your review. Your comments helped us strengthen the paper.
Response to Reviewer pSC3 — Part I
We thank the reviewer for the valuable suggestions. GenLock studies conjunctive backdoors that activate only when the visual and textual keys appear together, while retaining normal task performance. We appreciate your recognition of the prefix-continuation analysis, its validation across seeds and target texts, and the evaluation on five backends. We address the three concerns below.
W1 — DKICL and gate ablations
DKICL suppresses payload continuation after a supplied prefix when either key is missing. To identify which terms support this control, we added one-term-off and one-term-on ablations with the same training trace, seed, and evaluation protocol, keeping all components outside DKICL unchanged. We separate DKICL's interaction margin, absolute-score anchors, residual-mediated interaction, and shortcut penalty. The prefix columns below report selectivity.
Table A. DKICL anchor ablation.
Removing the anchors breaks control under the two-token prefix, while retaining them alone preserves it. This identifies the anchors as a key contributor to continuation control. In this matched setting, the interaction margin is not required to retain the measured prefix control.
We also retain only the interaction margin within DKICL.
Table B. Interaction-only comparison.
The interaction-only trial maintains high ASR but has lower prefix selectivity than the full method.
The individual removals of the residual-mediated interaction and shortcut penalty do not establish a separate behavioral gain in this matched setting.
We also performed fine-grained ablations of the gate group under the same matched protocol, keeping the other components unchanged. The table isolates gate supervision and the adapter.
Table C. Gate-group ablation.
Removing either increases text-only false triggering and modestly reduces prefix selectivity. Visual-only false triggering remains zero in these trials. Appendix H.3, Tables 17–18 report the full fine-grained ablation results for both DKICL and the gate group.
Additional control: four-cell CE-only (no added adapter or auxiliary losses).
Prefix columns report selectivity.
We tested a four-cell CE-only control with all GenLock components removed and observed clear gaps in both unprefixed and prefix-conditioned selectivity relative to full GenLock.
W2 — Matched benign adaptation on Qwen2.5-VL
Thank you for requesting this control. We added clean fine-tuning on the same ordered source examples and answers, using the same adapter/LoRA architecture and a matched 6,144-draw training budget. All inputs are clean, and only task-answer supervision is enabled. Both models are evaluated on the same clean-task cohorts and scoring protocol.
Table D. Matched benign-adaptation comparison on Qwen2.5-VL.
GenLock retains comparable clean-task utility against the adapted benign reference. Appendix L, Table 31 reports this matched comparison, with the pre-adaptation model reported separately.
Continued in Part II.