| 제목 | lm-sys FastChat ≤ 0.2.36（“up to 0.2.36”） Deserialization of Untrusted Data;Improper Input Validation |
|---|
| 설명 | 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. |
|---|
| 원천 | ⚠️ Advisories: nvd.nist.gov/vuln/detail/CVE-2025-3677; github.com/lm-sys/FastChat/issues/3713. Exploit: no public PoC; private video on request. |
|---|
| 사용자 | Tianrui Song (UID 92554) |
|---|
| 제출 | 2025. 11. 12. AM 07:22 (11 개월 ago) |
|---|
| 모더레이션 | 2025. 11. 16. PM 05:04 (4 days later) |
|---|
| 상태 | 중복 |
|---|
| VulDB 항목 | 304966 [lm-sys fastchat 까지 0.2.36 apply_delta.py split_files/apply_delta_low_cpu_mem 권한 상승] |
|---|
| 포인트들 | 0 |
|---|