Submit #693710: lm-sys FastChat ≤ 0.2.36(“up to 0.2.36”) Deserialization of Untrusted Data;Improper Input Validationinfo

Titellm-sys FastChat ≤ 0.2.36(“up to 0.2.36”) Deserialization of Untrusted Data;Improper Input Validation
BeschreibungA 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.
Quelle⚠️ Advisories: nvd.nist.gov/vuln/detail/CVE-2025-3677; github.com/lm-sys/FastChat/issues/3713. Exploit: no public PoC; private video on request.
Benutzer
 Tianrui Song (UID 92554)
Einreichung12.11.2025 07:22 (vor 11 Monaten)
Moderieren16.11.2025 17:04 (4 days later)
StatusDuplikat
VulDB Eintrag304966 [lm-sys fastchat bis 0.2.36 apply_delta.py split_files/apply_delta_low_cpu_mem erweiterte Rechte]
Punkte0

Interested in the pricing of exploits?

See the underground prices here!