| 제목 | lm-sys FastChat v0.2.3 to v0.2.36 Deserialization |
|---|
| 설명 | FastChat is a platform for training, serving, and evaluating Large Language Models (LLMs). In the codebase of FastChat, specifically in the file fastchat/model/apply_delta.py at lines L37, L90, L97, and L102, the torch.load function is used in a dangerous way. When torch.load is used to load pickle data without the weights_only=True parameter, it can execute arbitrary code during the deserialization process. If an attacker manages to supply malicious pickle data to the torch.load calls in these lines, they can potentially take control of the system, leading to unauthorized access, data leakage, or other security - related issues.
More details: https://github.com/lm-sys/FastChat/issues/3713 |
|---|
| 원천 | ⚠️ https://github.com/lm-sys/FastChat/issues/3713 |
|---|
| 사용자 | ybdesire (UID 83239) |
|---|
| 제출 | 2025. 04. 07. PM 04:24 (2 연령 ago) |
|---|
| 모더레이션 | 2025. 04. 16. AM 03:03 (8 days later) |
|---|
| 상태 | 수락 |
|---|
| VulDB 항목 | 304966 [lm-sys fastchat 까지 0.2.36 apply_delta.py split_files/apply_delta_low_cpu_mem 권한 상승] |
|---|
| 포인트들 | 20 |
|---|