Lucene search
+L

1793 matches found

ATTACKERKB
ATTACKERKB
added 2026/05/12 7:58 p.m.12 views

CVE-2026-44223

vLLM is an inference and serving engine for large language models LLMs. From 0.18.0 to before 0.20.0, the extracthiddenstates speculative decoding proposer in vLLM returns a tensor with an incorrect shape after the first decode step, causing a RuntimeError that crashes the EngineCore process. The...

6.5CVSS5.9AI score0.00367EPSS
SaveExploits0References3Affected Software1
CVE
CVE
added 2026/05/12 7:58 p.m.76 views

CVE-2026-44223

vLLM contains a vulnerability (CVE-2026-44223) where the extract_hidden_states speculative decoding pathway can crash the EngineCore process if any request uses penalty parameters (repetition_penalty, frequency_penalty, or presence_penalty). The issue arises from an incorrect tensor shape after t...

6.5CVSS5.9AI score0.00367EPSS
SaveExploits0References2Affected Software1
Cvelist
Cvelist
added 2026/05/12 7:58 p.m.49 views

CVE-2026-44223 vLLM: extract_hidden_states speculative decoding crashes server on any request with penalty parameters

vLLM is an inference and serving engine for large language models LLMs. From 0.18.0 to before 0.20.0, the extracthiddenstates speculative decoding proposer in vLLM returns a tensor with an incorrect shape after the first decode step, causing a RuntimeError that crashes the EngineCore process. The...

6.5CVSS0.00367EPSS
SaveExploits0References2
Vulnrichment
Vulnrichment
added 2026/05/12 7:58 p.m.11 views

CVE-2026-44223 vLLM: extract_hidden_states speculative decoding crashes server on any request with penalty parameters

vLLM is an inference and serving engine for large language models LLMs. From 0.18.0 to before 0.20.0, the extracthiddenstates speculative decoding proposer in vLLM returns a tensor with an incorrect shape after the first decode step, causing a RuntimeError that crashes the EngineCore process. The...

6.5CVSS5.9AI score0.00367EPSS
SaveExploits0References2
Wired Threat Level
Wired Threat Level
added 2026/05/12 7:06 p.m.18 views

Iran Is Using Tiny ‘Mosquito’ Boats to Shut Down the Strait of Hormuz

Iran’s traditional naval fleet has been almost completely destroyed by US-Israeli raids. But Iran’s military has put a fleet of small vessels on the water that is crippling every passageway...

5.8AI score
SaveExploits0
Lenovo
Lenovo
added 2026/05/12 6:01 p.m.20 views

Intel NPU Driver Advisory - Lenovo Support US

No description provided...

5.8AI score
SaveExploits0
Lenovo
Lenovo
added 2026/05/12 5:39 p.m.16 views

Intel EMA Software Advisory - Lenovo Support US

No description provided...

5.8AI score
SaveExploits0
Lenovo
Lenovo
added 2026/05/12 5:19 p.m.17 views

AMD Chipset Driver Vulnerabilities - Lenovo Support US

No description provided...

5.8AI score
SaveExploits0
Lenovo
Lenovo
added 2026/05/12 5:09 p.m.21 views

AMD Graphics Vulnerabilities - Lenovo Support US

No description provided...

5.8AI score
SaveExploits0
Lenovo
Lenovo
added 2026/05/12 4:59 p.m.19 views

AMD RAID Driver Vulnerability - Lenovo Support US

No description provided...

5.8AI score
SaveExploits0
Lenovo
Lenovo
added 2026/05/12 4:16 p.m.18 views

MediaTek Tablet Vulnerabilities, May 2026 - Lenovo Support US

No description provided...

5.8AI score
SaveExploits0
Lenovo
Lenovo
added 2026/05/12 4:10 p.m.19 views

Qualcomm WLAN Vulnerabilities - Lenovo Support US

No description provided...

5.8AI score
SaveExploits0
CNNVD
CNNVD
added 2026/05/12 12:00 a.m.17 views

vLLM 安全漏洞

vLLM is an open-source LLM-based inference and service engine that features high throughput and efficient memory usage. Versions of vLLM prior to 0.20.0 contained a security vulnerability. This vulnerability stemmed from the extracthiddenstates speculative decoding proposal, which returned tensor...

6.5CVSS5.8AI score0.00367EPSS
SaveExploits0References1
RedHat Linux
RedHat Linux
added 2026/05/11 6:45 p.m.14 views

webkitgtk: Processing maliciously crafted web content may disclose internal states of the app

A flaw was found in WebKitGTK. Processing malicious web content can cause a memory initialization issue due to improper memory handling and result in the disclosure of the internal states of the application...

4.3CVSS5.7AI score0.00309EPSS
SaveExploits0References5
HackRead
HackRead
added 2026/05/11 1:11 p.m.33 views

Romanian Man Faces Up to 30 Years in US Prison Over Vishing Scams

Romanian national Gavril Sandu faces up to 30 years in a US prison after extradition over a VOIP vishing and fake debit card fraud scheme...

5.7AI score
SaveExploits0
HackRead
HackRead
added 2026/05/10 7:54 p.m.45 views

Two US Men Jailed for Helping North Korean Hackers Infiltrate US Firms

Matthew Knoot and Erick Prince have been jailed for 18 months each for helping North Korean hackers infiltrate US firms through remote laptop farms...

5.8AI score
SaveExploits0
RedHat Linux
RedHat Linux
added 2026/05/07 6:01 a.m.11 views

webkitgtk: Processing maliciously crafted web content may disclose internal states of the app

A flaw was found in WebKitGTK. Processing malicious web content can cause a memory initialization issue due to improper memory handling and result in the disclosure of the internal states of the application...

4.3CVSS5.7AI score0.00309EPSS
SaveExploits0References5
Snyk
Snyk
added 2026/05/06 9:45 p.m.15 views

Incorrect Type Conversion or Cast

Overview vllm is an A high-throughput and memory-efficient inference and serving engine for LLMs Affected versions of this package are vulnerable to Incorrect Type Conversion or Cast through the extracthiddenstates speculative decoding. An attacker can cause the server to crash and disrupt servic...

6.5CVSS5.8AI score0.00367EPSS
SaveExploits0References3
Github Security Blog
Github Security Blog
added 2026/05/06 9:45 p.m.21 views

vLLM: extract_hidden_states speculative decoding crashes server on any request with penalty parameters

Summary The extracthiddenstates speculative decoding proposer in vLLM returns a tensor with an incorrect shape after the first decode step, causing a RuntimeError that crashes the EngineCore process. The crash is triggered when any request in the batch uses sampling penalty parameters...

6.5CVSS5.8AI score0.00367EPSS
SaveExploits0References5Affected Software1
OSV
OSV
added 2026/05/06 11:28 a.m.13 views

CVE-2026-43226 net/rds: No shortcut out of RDS_CONN_ERROR

In the Linux kernel, the following vulnerability has been resolved: net/rds: No shortcut out of RDSCONNERROR RDS connections carry a state "rdsconnpath::cpstate" and transitions from one state to another and are conditional upon an expected state: "rdsconnpathtransition." There is one exception t...

7.5CVSS6.5AI score
SaveExploits0References11
Rows per page
Query Builder