vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Maliciously constructed statements can lead to hash collisions, resulting in cache reuse, which can interfere with subsequent responses and cause unintended behavior. Prefix caching makes use of Python's built-in hash() function. As of Python 3.12, the behavior of hash(None) has changed to be a predictable constant value. This makes it more feasible that someone could try exploit hash collisions. The impact of a collision would be using cache that was generated using different content. Given knowledge of prompts in use and predictable hashing behavior, someone could intentionally populate the cache using a prompt known to collide with another prompt in use. This issue has been addressed in version 0.7.2 and all users are advised to upgrade. There are no known workarounds for this vulnerability.
| Métrique | Valeur | Interprétation |
|---|---|---|
|
AV (Vecteur d'Attaque)
Attack Vector
|
Network (N)
|
Exploit possible à distance via réseau (HTTP, API, etc.) |
|
AC (Complexité d'Attaque)
Attack Complexity
|
High (H)
|
Conditions spécifiques doivent être réunies pour exploiter |
|
PR (Privilèges Requis)
Privileges Required
|
Low (L)
|
Authentifié avec compte utilisateur basique |
|
UI (Interaction Utilisateur)
User Interaction
|
Required (R)
|
Nécessite une action utilisateur (clic lien, ouverture fichier, etc.) |
|
S (Périmètre)
Scope
|
Unchanged (U)
|
Impact reste dans le périmètre du composant compromis |
|
C (Impact Confidentialité)
Confidentiality Impact
|
None (N)
|
Aucune divulgation d'informations |
|
I (Impact Intégrité)
Integrity Impact
|
Low (L)
|
Modification limitée des données possible |
|
A (Impact Disponibilité)
Availability Impact
|
None (N)
|
Aucune interruption de service |
vLLM uses Python 3.12 built-in hash() which leads to predictable hash collisions in prefix cache