# MLA-Trust

Unified evaluation framework measuring truthfulness, controllability, safety, and privacy of multimodal LLM agents across interactive web and mobile GUI tasks.

- Catalog URL: https://awesomecua.github.io/resources/github-thu-ml-mla-trust/
- Original source: https://github.com/thu-ml/MLA-Trust
- Kind: benchmark
- Review: curated
- Scope: core
- Environments: web, android, cross-platform
- Topics: safety-security, evaluation, robustness
- Evidence checked: 2026-10-18T10:59:55Z
- ID: github:thu-ml/mla-trust

## Limitations

Inclusion does not establish reproducibility or endorsement.

- Record JSON: https://awesomecua.github.io/resources/github-thu-ml-mla-trust/record.json

## License declarations

- code: MIT — https://raw.githubusercontent.com/thu-ml/MLA-Trust/HEAD/LICENSE
- data: not recorded
- document: not recorded
- weights: not recorded

## Primary evidence

- https://raw.githubusercontent.com/thu-ml/MLA-Trust/HEAD/README.md (retrieved 2026-10-18T10:59:55Z; SHA-256 d69da19edaed185ad3071a97db3bb3fcfbdb14c0b514b7d27794b39fbe8e2541)
- https://raw.githubusercontent.com/thu-ml/MLA-Trust/HEAD/LICENSE (retrieved 2026-10-18T11:03:46Z; SHA-256 240fb6820e7bcb0753617bcad6ffbd4a9ba83ca98e1e6aaa06c7b197b244bf16)