| Título | lm-sys FastChat ≤ 0.2.36（“up to 0.2.36”） Deserialization of Untrusted Data;Improper Input Validation |
|---|
| Descripción | A deserialization vulnerability exists in fastchat/model/apply_delta.py (functions split_files / apply_delta_low_cpu_mem) in FastChat ≤ 0.2.36. In our controlled tests, exploitation led to modification of model inference behavior (altered logits), and in multi-process environments persisted weight files were modified such that other processes observed integrity changes (Scope: Changed). The reported observations were performed in a controlled environment and are documented in a private demonstration video. No PoC is published publicly; encrypted evidence can be provided to CNA/NVD on request. |
|---|
| Fuente | ⚠️ Advisories: nvd.nist.gov/vuln/detail/CVE-2025-3677; github.com/lm-sys/FastChat/issues/3713. Exploit: no public PoC; private video on request. |
|---|
| Usuario | Tianrui Song (UID 92554) |
|---|
| Sumisión | 2025-11-12 07:22 (hace 11 meses) |
|---|
| Moderación | 2025-11-16 17:04 (4 days later) |
|---|
| Estado | Duplicado |
|---|
| Entrada de VulDB | 304966 [lm-sys fastchat hasta 0.2.36 apply_delta.py split_files/apply_delta_low_cpu_mem escalada de privilegios] |
|---|
| Puntos | 0 |
|---|