Abstract
Existing text-to-video (T2V) jailbreak methods mainly seek more effective or stealthier attack candidates. In guarded T2V systems, however, video generation and security evaluation are costly, so an attacker often cannot test a large candidate pool. We therefore formulate T2V jailbreak as a query-constrained candidate allocation and ranking problem and propose TempQ-Jail. The method combines heterogeneous attack mechanisms to expand candidate coverage, estimates each candidate's end-to-end attack value from security-gate passage, dangerous visual generation, preservation of the original intent, and temporal validity, and ranks candidates so that high-value attacks appear early in a limited query trajectory. We evaluate TempQ-Jail on CogVideoX-5B using 70 common viable intents derived from T2VSafetyBench and compare it with six representative T2V jailbreak methods under a unified protocol. TempQ-Jail achieves TP-ASR@5 and TP-ASR@10 of 48.9% and 65.4%, improving over the strongest baselines by 4.6 and 4.0 percentage points, respectively. It also obtains the highest AUC-TP (0.469) and the lowest AvgQ (6.3). Analyses of query trajectories, candidate allocation, failure attribution, and ablations show that TempQ-Jail more effectively identifies and prioritises candidates with complete attack potential under limited query budgets.
Keywords
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Fang, T., Wang, J., Wang, C., Wang, L., Wang, W., Liu, J., & Cao, X. (2026). TempQ-Jail: Query-Constrained Candidate Ranking for Text-to-Video Jailbreak Attacks. https://omanscience.com/en/articles/tempq-jail-query-constrained-candidate-ranking-for-text-to-video-jailbreak-attacks
MLA 9
Fang, Tianmeng, et al. "TempQ-Jail: Query-Constrained Candidate Ranking for Text-to-Video Jailbreak Attacks." https://omanscience.com/en/articles/tempq-jail-query-constrained-candidate-ranking-for-text-to-video-jailbreak-attacks.
Chicago (author–date)
Fang, Tianmeng, Jiancheng Wang, Chen Wang, Liming Wang, Wei Wang, Jiayang Liu, and Xiaochun Cao. 2026. "TempQ-Jail: Query-Constrained Candidate Ranking for Text-to-Video Jailbreak Attacks." https://omanscience.com/en/articles/tempq-jail-query-constrained-candidate-ranking-for-text-to-video-jailbreak-attacks.
Harvard
Fang, T., Wang, J., Wang, C., Wang, L., Wang, W., Liu, J. and Cao, X. (2026) 'TempQ-Jail: Query-Constrained Candidate Ranking for Text-to-Video Jailbreak Attacks', Available at: https://omanscience.com/en/articles/tempq-jail-query-constrained-candidate-ranking-for-text-to-video-jailbreak-attacks.
Vancouver
Fang T, Wang J, Wang C, Wang L, Wang W, Liu J, et al. TempQ-Jail: Query-Constrained Candidate Ranking for Text-to-Video Jailbreak Attacks. https://omanscience.com/en/articles/tempq-jail-query-constrained-candidate-ranking-for-text-to-video-jailbreak-attacks
IEEE
T. Fang, J. Wang, C. Wang, L. Wang, W. Wang, J. Liu, and X. Cao, "TempQ-Jail: Query-Constrained Candidate Ranking for Text-to-Video Jailbreak Attacks," https://omanscience.com/en/articles/tempq-jail-query-constrained-candidate-ranking-for-text-to-video-jailbreak-attacks.