| --- |
| base_model: TIGER-Lab/BrowserAgent-RFT |
| library_name: peft |
| tags: [lora, web-agent, adversarial-co-evolution, prompt-injection] |
| license: apache-2.0 |
| --- |
| |
| # BrowserAgent Adversarial Co-Evolution — LoRA adapters |
|
|
| LoRA adapters (r=16, alpha=32) over **TIGER-Lab/BrowserAgent-RFT** (Qwen2.5-7B) from a |
| 6-iteration **adversarial co-evolution** loop on multi-turn web form-filling tasks. An |
| ADVERSARY learns to prompt-inject a frozen world model to derail a web EXECUTOR; both update |
| each iteration (reactive attack: injection lands on the page the executor's action produces). |
|
|
| ## Adapters |
| - `exec_v1` … `exec_v6` — the EXECUTOR (defender) at each iteration. |
| - `adv_v1` … `adv_v6` — the ADVERSARY (attacker) at each iteration. |
|
|
| Load: `PeftModel.from_pretrained(base, "GussailRaat/browseragent-adversary-coevo", subfolder="exec_v5")`. |
|
|
| ## Key results (harder-100 multi-turn benchmark, exact-match) |
| Under the strongest adversary `adv_v6` (3 seeds): clean capability rises across iters |
| (0.70 -> 0.95, peak exec_v5), but adv_v6 floors every executor to ~0.15-0.22 under attack — |
| co-evolution converged to a dominant adversary. Best executor = **exec_v5** (0.950 clean / |
| 0.217 attacked). Under the weaker `adv_v3`, exec_v2 held 0.516 attacked. |
| |
