13445 matches found
CVE-2025-25183
A flaw was found in the vllm package. Maliciously constructed statements can lead to hash collisions, resulting in cache reuse, which can interfere with subsequent responses and cause unintended behavior. The impact of a collision would be using a cache that was generated using different content...
PYSEC-2025-62
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-i...
PYSEC-2025-62
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-i...
CVE-2025-25183
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-i...
CVE-2025-25183 vLLM using built-in hash() from Python 3.12 leads to predictable hash collisions in vLLM prefix cache
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-i...
CVE-2025-25183 vLLM using built-in hash() from Python 3.12 leads to predictable hash collisions in vLLM prefix cache
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-i...
CVE-2025-25183 vLLM using built-in hash() from Python 3.12 leads to predictable hash collisions in vLLM prefix cache
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-i...
vLLM 安全漏洞
vLLM is a high throughput and memory efficient inference and service engine for LLM from the vLLM open source. A security vulnerability exists in vLLM that stems from a maliciously constructed statement that could lead to a hash collision, which could lead to cache reuse, which could interfere wi...
Use of Weak Hash
Overview vllm is an A high-throughput and memory-efficient inference and serving engine for LLMs Affected versions of this package are vulnerable to Use of Weak Hash due to the use of a predictable constant value in the Python 3.12 built-in hash function. An attacker can interfere with subsequent...
vLLM uses Python 3.12 built-in hash() which leads to predictable hash collisions in prefix cache
Summary Maliciously constructed prompts can lead to hash collisions, resulting in prefix cache reuse, which can interfere with subsequent responses and cause unintended behavior. Details vLLM's prefix caching makes use of Python's built-in hash function. As of Python 3.12, the behavior of hashNon...
GHSA-RM76-4MRF-V9R8 vLLM uses Python 3.12 built-in hash() which leads to predictable hash collisions in prefix cache
Summary Maliciously constructed prompts can lead to hash collisions, resulting in prefix cache reuse, which can interfere with subsequent responses and cause unintended behavior. Details vLLM's prefix caching makes use of Python's built-in hash function. As of Python 3.12, the behavior of hashNon...
Astra Linux - уязвимость в linux-5.10
In the Linux kernel, the following vulnerability has been resolved: crypto: algifhash - Remove bogus SGL free on zero-length error path When a zero-length message is hashed by algifhash, and an error is triggered, it tries to free an SG list that was never allocated in the first place. Fix this b...
CVE-2021-35110
Possible buffer overflow to improper validation of hash segment of file while allocating memory in Snapdragon Connectivity, Snapdragon Mobile...
CVE-2022-21198
creationtimestamp| type| source ---|---|--- 2025-02-06 02:41:39+00:00| seen| Telegram/xbf7RgubljmZeKAr0HL-VoweeZFB4txvAuNL25GKBYMSo96 2025-02-06 02:42:29+00:00| seen| Telegram/P6rbDOAjZ9dWxxqEqqfp9RCvkW7JTg1or85lYTIwDepCc6U...
CVE-2022-25652
Cryptographic issues in BSP due to improper hash verification in Snapdragon Wired Infrastructure and Networking...
PT-2025-6000 · Vllm +1 · Vllm +1
Name of the Vulnerable Software and Affected Versions: vLLM versions prior to 0.7.2 Description: Maliciously constructed statements can lead to hash collisions, resulting in cache reuse, which can interfere with subsequent responses and cause unintended behavior. The issue arises from the use of...
The vulnerability of the NTLMv2 authentication protocol implemented in Windows operating systems allows a hacker to carry out a Pass-the-hash attack.
The vulnerability of the NTLMv2 authentication protocol for Windows operating systems is related to the disclosure of hashes due to improper external manipulation of the name or file. Exploiting this vulnerability can allow a remote attacker to execute a Pass-the-hash attack...
CVE-2022-24798
Internet Routing Registry daemon version 4 is an IRR database server, processing IRR objects in the RPSL format. IRRd did not always filter password hashes in query responses relating to mntner objects and database exports. This may have allowed adversaries to retrieve some of these hashes, perfo...
CVE-2020-5229
Opencast before 8.1 stores passwords using the rather outdated and cryptographically insecure MD5 hash algorithm. Furthermore, the hashes are salted using the username instead of a random salt, causing hashes for users with the same username and password to collide which is problematic especially...