Lucene search
K

7 matches found

EUVD
EUVD
added 2025/10/03 8:7 p.m.3 views

EUVD-2025-16189

Malicious code in bioql PyPI...

2.6CVSS6.3AI score0.00177EPSS
Exploits0References4
Veracode
Veracode
added 2025/06/02 4:45 a.m.6 views

Timing Side-channel Attacks

vllm is vulnerable to Timing side-channel attacks. The vulnerability is due to timing discrepancies during the prefill phase by the PageAttention mechanism reusing matching prefix chunks, which speeds up token generation and allows an attacker to infer prompt similarity or presence...

2.6CVSS3.7AI score0.00177EPSS
Exploits0References6Affected Software1
NVD
NVD
added 2025/05/29 5:15 p.m.8 views

CVE-2025-46570

vLLM is an inference and serving engine for large language models LLMs. Prior to version 0.9.0, when a new prompt is processed, if the PageAttention mechanism finds a matching prefix chunk, the prefill process speeds up, which is reflected in the TTFT Time to First Token. These timing differences...

2.6CVSS0.00177EPSS
Exploits0References3
CVE
CVE
added 2025/05/29 4:32 p.m.165 views

CVE-2025-46570

The CVE-2025-46570 entry concerns vLLM (inference/serving engine). The concrete detail across connected records shows a vulnerability in the PageAttention-based prefill path: when a new prompt is processed, a matching prefix chunk can accelerate prefill, creating timing differences (TTFT) that co...

2.6CVSS3.6AI score0.00177EPSS
Exploits0References3Affected Software1
OSV
OSV
added 2025/05/29 4:32 p.m.2 views

CVE-2025-46570 vLLM’s Chunk-Based Prefix Caching Vulnerable to Potential Timing Side-Channel

vLLM is an inference and serving engine for large language models LLMs. Prior to version 0.9.0, when a new prompt is processed, if the PageAttention mechanism finds a matching prefix chunk, the prefill process speeds up, which is reflected in the TTFT Time to First Token. These timing differences...

2.6CVSS6.5AI score0.00177EPSS
Exploits0References5
CNNVD
CNNVD
added 2025/05/29 12:0 a.m.1 views

vLLM 安全漏洞

vLLM is a vLLM open source high throughput and memory efficient inference and service engine for LLM. A security vulnerability exists in vLLM versions prior to 0.9.0 that stems from a timing difference in the PageAttention mechanism that could be exploited...

2.6CVSS6.3AI score0.00177EPSS
Exploits0References4
Github Security Blog
Github Security Blog
added 2025/05/28 6:2 p.m.8 views

Potential Timing Side-Channel Vulnerability in vLLM’s Chunk-Based Prefix Caching

This issue arises from the prefix caching mechanism, which may expose the system to a timing side-channel attack. Description When a new prompt is processed, if the PageAttention mechanism finds a matching prefix chunk, the prefill process speeds up, which is reflected in the TTFT Time to First...

2.6CVSS6.5AI score0.00177EPSS
Exploits0References6Affected Software1
Rows per page
Query Builder