# Physical Red Teaming on RedVLA Cumulative-Level Scenarios

Source: [Physical Red Teaming on RedVLA Cumulative-Level Scenarios](<https://www.sota2.com/research/sota/physical-red-teaming-on-redvla-cumulative-level-scenarios>)

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

Data updated: 2026-04-27T07:39:51.156Z

Evaluation of model performance on the RedVLA Cumulative-Level Scenarios dataset using Physical Red Teaming protocols, measured by Attack Success Rate (ASR) and Success Rate (SR).

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 | Physical Red Teaming |
| Dataset (including any stated split) | RedVLA Cumulative-Level Scenarios |
| Metric | Attack Success Rate (ASR) |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 18 of 18 |
| 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

- [Attack Success Rate (ASR)](<https://www.sota2.com/research/sota/physical-red-teaming-on-redvla-cumulative-level-scenarios.md?metric=Attack%20Success%20Rate%20(ASR)>): Higher is better; unit: PERCENT.

- [Success Rate (SR)](<https://www.sota2.com/research/sota/physical-red-teaming-on-redvla-cumulative-level-scenarios.md?metric=Success%20Rate%20(SR)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Attack Success Rate (ASR) | Result date | Report paper |
| --- | --- | --- | --- |
| OpenVLA | 100 | Not recorded | 69eeed6a55a3c32af89f9657 |
| OpenVLA-OFT | 100 | Not recorded | 69eeed6a55a3c32af89f9657 |
| VLA-Adapter | 100 | Not recorded | 69eeed6a55a3c32af89f9657 |
| VLA-Adapter-Pro | 100 | Not recorded | 69eeed6a55a3c32af89f9657 |
| π0 | 100 | Not recorded | 69eeed6a55a3c32af89f9657 |
| π0.5 | 100 | Not recorded | 69eeed6a55a3c32af89f9657 |
| π0.5 | 98.5 | Not recorded | 69eeed6a55a3c32af89f9657 |
| OpenVLA | 97.7 | Not recorded | 69eeed6a55a3c32af89f9657 |
| π0 | 97.7 | Not recorded | 69eeed6a55a3c32af89f9657 |
| VLA-Adapter-Pro | 96.9 | Not recorded | 69eeed6a55a3c32af89f9657 |
| π0 | 96.7 | Not recorded | 69eeed6a55a3c32af89f9657 |
| OpenVLA-OFT | 95.4 | Not recorded | 69eeed6a55a3c32af89f9657 |
| VLA-Adapter | 95.4 | Not recorded | 69eeed6a55a3c32af89f9657 |
| VLA-Adapter | 95 | Not recorded | 69eeed6a55a3c32af89f9657 |
| π0.5 | 91.7 | Not recorded | 69eeed6a55a3c32af89f9657 |
| VLA-Adapter-Pro | 88.3 | Not recorded | 69eeed6a55a3c32af89f9657 |
| OpenVLA-OFT | 70 | Not recorded | 69eeed6a55a3c32af89f9657 |
| OpenVLA | 61.7 | Not recorded | 69eeed6a55a3c32af89f9657 |

### OpenVLA

Attack Success Rate (ASR): 100. Result ID: 69ef115947f34ce924d4ef40.

[Reporting paper](<https://www.sota2.com/research/paper/69eeed6a55a3c32af89f9657.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74c31e209131cea63a36.md>)

[Implementation](<https://openvla.github.io/>)

Recorded evaluation configuration: {"Scenario":"Dangerous Item Misuse"}. This record does not assert independent reproduction.

### OpenVLA-OFT

Attack Success Rate (ASR): 100. Result ID: 69ef115947f34ce924d4ef41.

[Reporting paper](<https://www.sota2.com/research/paper/69eeed6a55a3c32af89f9657.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78471e209131cea7794b.md>)

Recorded evaluation configuration: {"Scenario":"Dangerous Item Misuse"}. This record does not assert independent reproduction.

### VLA-Adapter

Attack Success Rate (ASR): 100. Result ID: 69ef115947f34ce924d4ef42.

[Reporting paper](<https://www.sota2.com/research/paper/69eeed6a55a3c32af89f9657.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b861e209131cea88e51.md>)

Recorded evaluation configuration: {"Scenario":"Dangerous Item Misuse"}. This record does not assert independent reproduction.

### VLA-Adapter-Pro

Attack Success Rate (ASR): 100. Result ID: 69ef115947f34ce924d4ef43.

[Reporting paper](<https://www.sota2.com/research/paper/69eeed6a55a3c32af89f9657.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b861e209131cea88e51.md>)

Recorded evaluation configuration: {"Scenario":"Dangerous Item Misuse"}. This record does not assert independent reproduction.

### π0

Attack Success Rate (ASR): 100. Result ID: 69ef115947f34ce924d4ef44.

[Reporting paper](<https://www.sota2.com/research/paper/69eeed6a55a3c32af89f9657.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75aa1e209131cea6929a.md>)

Recorded evaluation configuration: {"Scenario":"Dangerous Item Misuse"}. This record does not assert independent reproduction.

### π0.5

Attack Success Rate (ASR): 100. Result ID: 69ef115947f34ce924d4ef45.

[Reporting paper](<https://www.sota2.com/research/paper/69eeed6a55a3c32af89f9657.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa783a1e209131cea774f1.md>)

Recorded evaluation configuration: {"Scenario":"Dangerous Item Misuse"}. This record does not assert independent reproduction.

### π0.5

Attack Success Rate (ASR): 98.5. Result ID: 69ef115947f34ce924d4ef3f.

[Reporting paper](<https://www.sota2.com/research/paper/69eeed6a55a3c32af89f9657.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa783a1e209131cea774f1.md>)

Recorded evaluation configuration: {"Scenario":"Resource Damage"}. This record does not assert independent reproduction.

### OpenVLA

Attack Success Rate (ASR): 97.7. Result ID: 69ef115947f34ce924d4ef3a.

[Reporting paper](<https://www.sota2.com/research/paper/69eeed6a55a3c32af89f9657.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74c31e209131cea63a36.md>)

[Implementation](<https://openvla.github.io/>)

Recorded evaluation configuration: {"Scenario":"Resource Damage"}. This record does not assert independent reproduction.

### π0

Attack Success Rate (ASR): 97.7. Result ID: 69ef115947f34ce924d4ef3e.

[Reporting paper](<https://www.sota2.com/research/paper/69eeed6a55a3c32af89f9657.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75aa1e209131cea6929a.md>)

Recorded evaluation configuration: {"Scenario":"Resource Damage"}. This record does not assert independent reproduction.

### VLA-Adapter-Pro

Attack Success Rate (ASR): 96.9. Result ID: 69ef115947f34ce924d4ef3d.

[Reporting paper](<https://www.sota2.com/research/paper/69eeed6a55a3c32af89f9657.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b861e209131cea88e51.md>)

Recorded evaluation configuration: {"Scenario":"Resource Damage"}. This record does not assert independent reproduction.

### π0

Attack Success Rate (ASR): 96.7. Result ID: 69ef115947f34ce924d4ef4a.

[Reporting paper](<https://www.sota2.com/research/paper/69eeed6a55a3c32af89f9657.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75aa1e209131cea6929a.md>)

Recorded evaluation configuration: {"Scenario":"Robot Damage"}. This record does not assert independent reproduction.

### OpenVLA-OFT

Attack Success Rate (ASR): 95.4. Result ID: 69ef115947f34ce924d4ef3b.

[Reporting paper](<https://www.sota2.com/research/paper/69eeed6a55a3c32af89f9657.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78471e209131cea7794b.md>)

Recorded evaluation configuration: {"Scenario":"Resource Damage"}. This record does not assert independent reproduction.

### VLA-Adapter

Attack Success Rate (ASR): 95.4. Result ID: 69ef115947f34ce924d4ef3c.

[Reporting paper](<https://www.sota2.com/research/paper/69eeed6a55a3c32af89f9657.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b861e209131cea88e51.md>)

Recorded evaluation configuration: {"Scenario":"Resource Damage"}. This record does not assert independent reproduction.

### VLA-Adapter

Attack Success Rate (ASR): 95. Result ID: 69ef115947f34ce924d4ef48.

[Reporting paper](<https://www.sota2.com/research/paper/69eeed6a55a3c32af89f9657.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b861e209131cea88e51.md>)

Recorded evaluation configuration: {"Scenario":"Robot Damage"}. This record does not assert independent reproduction.

### π0.5

Attack Success Rate (ASR): 91.7. Result ID: 69ef115947f34ce924d4ef4b.

[Reporting paper](<https://www.sota2.com/research/paper/69eeed6a55a3c32af89f9657.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa783a1e209131cea774f1.md>)

Recorded evaluation configuration: {"Scenario":"Robot Damage"}. This record does not assert independent reproduction.

### VLA-Adapter-Pro

Attack Success Rate (ASR): 88.3. Result ID: 69ef115947f34ce924d4ef49.

[Reporting paper](<https://www.sota2.com/research/paper/69eeed6a55a3c32af89f9657.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b861e209131cea88e51.md>)

Recorded evaluation configuration: {"Scenario":"Robot Damage"}. This record does not assert independent reproduction.

### OpenVLA-OFT

Attack Success Rate (ASR): 70. Result ID: 69ef115947f34ce924d4ef47.

[Reporting paper](<https://www.sota2.com/research/paper/69eeed6a55a3c32af89f9657.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78471e209131cea7794b.md>)

Recorded evaluation configuration: {"Scenario":"Robot Damage"}. This record does not assert independent reproduction.

### OpenVLA

Attack Success Rate (ASR): 61.7. Result ID: 69ef115947f34ce924d4ef46.

[Reporting paper](<https://www.sota2.com/research/paper/69eeed6a55a3c32af89f9657.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74c31e209131cea63a36.md>)

[Implementation](<https://openvla.github.io/>)

Recorded evaluation configuration: {"Scenario":"Robot Damage"}. This record does not assert independent reproduction.

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