# Jailbreaking on Hailuo

Source: [Jailbreaking on Hailuo](<https://www.sota2.com/research/sota/jailbreaking-on-hailuo>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-03-09T06:59:19.493Z

Evaluation of model safety and robustness against jailbreaking attacks using the Hailuo dataset, measuring success rates across specific categories of harmful content such as Pornography, Violence, Illegal Activities, and Misinformation.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Jailbreaking |
| Dataset (including any stated split) | Hailuo |
| Metric | Pornography Success Rate |
| Unit | PERCENT |
| Direction | Lower is better |
| Results loaded | 4 of 4 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [Pornography Success Rate](<https://www.sota2.com/research/sota/jailbreaking-on-hailuo.md?metric=Pornography%20Success%20Rate>): Lower is better; unit: PERCENT.

- [Borderline Pornography Success Rate](<https://www.sota2.com/research/sota/jailbreaking-on-hailuo.md?metric=Borderline%20Pornography%20Success%20Rate>): Lower is better; unit: PERCENT.

- [Violence Success Rate](<https://www.sota2.com/research/sota/jailbreaking-on-hailuo.md?metric=Violence%20Success%20Rate>): Lower is better; unit: PERCENT.

- [Gore Success Rate](<https://www.sota2.com/research/sota/jailbreaking-on-hailuo.md?metric=Gore%20Success%20Rate>): Lower is better; unit: PERCENT.

- [Disturbing Content Success Rate](<https://www.sota2.com/research/sota/jailbreaking-on-hailuo.md?metric=Disturbing%20Content%20Success%20Rate>): Lower is better; unit: PERCENT.

- [Public Figures Success Rate](<https://www.sota2.com/research/sota/jailbreaking-on-hailuo.md?metric=Public%20Figures%20Success%20Rate>): Lower is better; unit: PERCENT.

- [Discrimination Success Rate](<https://www.sota2.com/research/sota/jailbreaking-on-hailuo.md?metric=Discrimination%20Success%20Rate>): Lower is better; unit: PERCENT.

- [Political Sensitivity Success Rate](<https://www.sota2.com/research/sota/jailbreaking-on-hailuo.md?metric=Political%20Sensitivity%20Success%20Rate>): Lower is better; unit: PERCENT.

- [Copyright Success Rate](<https://www.sota2.com/research/sota/jailbreaking-on-hailuo.md?metric=Copyright%20Success%20Rate>): Lower is better; unit: PERCENT.

- [Illegal Activities Success Rate](<https://www.sota2.com/research/sota/jailbreaking-on-hailuo.md?metric=Illegal%20Activities%20Success%20Rate>): Lower is better; unit: PERCENT.

- [Misinformation Success Rate](<https://www.sota2.com/research/sota/jailbreaking-on-hailuo.md?metric=Misinformation%20Success%20Rate>): Lower is better; unit: PERCENT.

- [Sequential Action Success Rate](<https://www.sota2.com/research/sota/jailbreaking-on-hailuo.md?metric=Sequential%20Action%20Success%20Rate>): Lower is better; unit: PERCENT.

- [Dynamic Variation Success Rate](<https://www.sota2.com/research/sota/jailbreaking-on-hailuo.md?metric=Dynamic%20Variation%20Success%20Rate>): Lower is better; unit: PERCENT.

- [Coherent Contextual Success Rate](<https://www.sota2.com/research/sota/jailbreaking-on-hailuo.md?metric=Coherent%20Contextual%20Success%20Rate>): Lower is better; unit: PERCENT.

- [Average Success Rate](<https://www.sota2.com/research/sota/jailbreaking-on-hailuo.md?metric=Average%20Success%20Rate>): Lower is better; unit: PERCENT.

## Recorded results

| Method | Pornography Success Rate | Result date | Report paper |
| --- | --- | --- | --- |
| DACA | 12 | Not recorded | 691bfe286750be83fe5ced41 |
| TSB | 22 | Not recorded | 691bfe286750be83fe5ced41 |
| RAB | 40 | Not recorded | 691bfe286750be83fe5ced41 |
| SPARK | 94 | Not recorded | 691bfe286750be83fe5ced41 |

### DACA

Pornography Success Rate: 12. Result ID: 69ae6eeb6dbb7075b955f6e6.

[Reporting paper](<https://www.sota2.com/research/paper/691bfe286750be83fe5ced41.md>)

Recorded evaluation configuration: {"Attack Method":"DACA"}. This record does not assert independent reproduction.

### TSB

Pornography Success Rate: 22. Result ID: 69ae6eeb6dbb7075b955f6e4.

[Reporting paper](<https://www.sota2.com/research/paper/691bfe286750be83fe5ced41.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74bb1e209131cea63572.md>)

Recorded evaluation configuration: {"Attack Method":"TSB"}. This record does not assert independent reproduction.

### RAB

Pornography Success Rate: 40. Result ID: 69ae6eeb6dbb7075b955f6e5.

[Reporting paper](<https://www.sota2.com/research/paper/691bfe286750be83fe5ced41.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa738e1e209131cea5d34e.md>)

Recorded evaluation configuration: {"Attack Method":"RAB"}. This record does not assert independent reproduction.

### SPARK

Pornography Success Rate: 94. Result ID: 69ae6eeb6dbb7075b955f6e7.

[Reporting paper](<https://www.sota2.com/research/paper/691bfe286750be83fe5ced41.md>)

[Method origin paper](<https://www.sota2.com/research/paper/691bfe286750be83fe5ced41.md>)

Recorded evaluation configuration: {"Attack Method":"SPARK"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.