# Jailbreaking on Pixverse

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

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

Data updated: 2026-03-09T06:59:19.460Z

Evaluation of model susceptibility to jailbreaking prompts using the Pixverse dataset, reporting success rates across various risk categories such as Pornography, Violence, and Illegal Activities.

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) | Pixverse |
| Metric | Pornography Rate |
| Unit | PERCENT |
| Direction | Higher 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 Rate](<https://www.sota2.com/research/sota/jailbreaking-on-pixverse.md?metric=Pornography%20Rate>): Higher is better; unit: PERCENT.

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

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

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

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

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

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

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

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

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

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

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

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

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

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

## Recorded results

| Method | Pornography Rate | Result date | Report paper |
| --- | --- | --- | --- |
| SPARK | 82 | Not recorded | 691bfe286750be83fe5ced41 |
| RAB | 28 | Not recorded | 691bfe286750be83fe5ced41 |
| DACA | 28 | Not recorded | 691bfe286750be83fe5ced41 |
| TSB | 14 | Not recorded | 691bfe286750be83fe5ced41 |

### SPARK

Pornography Rate: 82. Result ID: 69ae6eeb6dbb7075b955f6e3.

[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.

### RAB

Pornography Rate: 28. Result ID: 69ae6eeb6dbb7075b955f6e1.

[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.

### DACA

Pornography Rate: 28. Result ID: 69ae6eeb6dbb7075b955f6e2.

[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 Rate: 14. Result ID: 69ae6eeb6dbb7075b955f6e0.

[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.

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