Lucene search
+L

2711 matches found

Akamai Blog
Akamai Blog
added 2025/03/26 10:20 a.m.9 views

Why AI Inference is Driving the Shift from Centralized to Distributed Cloud Computing

...

7AI score
SaveExploits0
Positive Technologies
Positive Technologies
added 2025/03/26 12:00 a.m.20 views

PT-2025-12890 · Discourse · Discourse

Name of the Vulnerable Software and Affected Versions: Discourse versions prior to 3.3.4 on the stable branch and prior to 3.4.0.beta5 on the beta branch Description: The issue affects an open-source discussion platform, where a race condition allows someone about to reach the user limit in a gro...

4.3CVSS6.9AI score0.0021EPSS
SaveExploits0References10
Akamai Blog
Akamai Blog
added 2025/03/25 3:00 p.m.6 views

Distributed Cloud Solutions and AI: Key Findings from Forrester's 2024 Study

...

7AI score
SaveExploits0
RedhatCVE
RedhatCVE
added 2025/03/22 11:47 a.m.10 views

CVE-2024-9052

A flaw was found in the vLLM distributed training API. This vulnerability allows remote code execution via unsafe deserialization, which uses pickle.loads without sanitization...

2.6CVSS9.7AI score
SaveExploits0References5
CNNVD
CNNVD
added 2025/03/22 12:00 a.m.10 views

SnailJob 代码问题漏洞

SnailJob is a flexible, reliable and efficient distributed task retrying and task scheduling platform from aizuda open source. A code issue vulnerability exists in SnailJob version 1.4.0, which stems from a deserialization vulnerability...

8.8CVSS6.5AI score0.00718EPSS
SaveExploits1References5
OSV
OSV
added 2025/03/20 12:32 p.m.11 views

GHSA-XQGJ-R6XV-9CW4 Withdrawn Advisory: Dask Vulnerable to Command Injection

Withdrawn Advisory This advisory has been withdrawn because it describes intended functionality. This link is maintained to preserve external references. Original Description Dask versions =2024.8.2 contain a vulnerability in the Dask Distributed Server where the use of pickle serialization allow...

9.8CVSS7.3AI score
SaveExploits0References3
NVD
NVD
added 2025/03/20 10:15 a.m.31 views

CVE-2024-9052

Rejected reason: This CVE ID has been rejected or withdrawn by its CVE Numbering Authority...

SaveExploits0
NVD
NVD
added 2025/03/20 10:15 a.m.11 views

CVE-2024-10096

Rejected reason: This CVE ID has been rejected or withdrawn by its CVE Numbering Authority...

SaveExploits0
Vulnrichment
Vulnrichment
added 2025/03/20 10:09 a.m.7 views

CVE-2024-9052

...

6.4AI score
SaveExploits0
CVE
CVE
added 2025/03/20 10:09 a.m.1378 views

CVE-2024-9052

Summary: CVE-2024-9052 relates to a deserialization flaw in the vLLM project’s distributed training API. The issue enables remote code execution via unsafe deserialization of object bytes using pickle.loads() without sanitization, specifically within the vllm.distributed.GroupCoordinator.recv_obj...

9.7AI score
SaveExploits0
Cvelist
Cvelist
added 2025/03/20 10:09 a.m.16 views

CVE-2024-9052

...

SaveExploits0
CNNVD
CNNVD
added 2025/03/20 12:00 a.m.10 views

Apache Seata 安全漏洞

Apache Seata is an open source project from the Apache Foundation that provides high-performance and easy-to-use distributed transaction services in a microservices architecture. A security vulnerability exists in Apache Seata version 2.2.0 and earlier, which stems from improper handling of highl...

4.3CVSS6.5AI score0.00625EPSS
SaveExploits0References2
CNNVD
CNNVD
added 2025/03/20 12:00 a.m.8 views

H2O 安全漏洞

H2O is an in-memory platform for distributed, scalable machine learning open-sourced by H2O.ai. A security vulnerability exists in H2O version 3.46.0, which stems from a custom encryption tool endpoint that does not restrict encrypted files, potentially leading to ransomware behavior...

6.5CVSS6.4AI score0.00344EPSS
SaveExploits1References1
OSV
OSV
added 2025/03/19 4:15 p.m.7 views

PYSEC-2025-63

vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. When vLLM is configured to use Mooncake, unsafe deserialization exposed directly over ZMQ/TCP on all network interfaces will allow attackers to execute remote code on distributed hosts. This is a remote code...

9CVSS8.3AI score0.00728EPSS
SaveExploits0References3
NVD
NVD
added 2025/03/19 4:15 p.m.21 views

CVE-2025-29783

vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. When vLLM is configured to use Mooncake, unsafe deserialization exposed directly over ZMQ/TCP on all network interfaces will allow attackers to execute remote code on distributed hosts. This is a remote code...

9CVSS0.00728EPSS
SaveExploits0References3
OSV
OSV
added 2025/03/19 3:55 p.m.28 views

GHSA-X3M8-F7G5-QHM7 vLLM Allows Remote Code Execution via Mooncake Integration

Summary When vLLM is configured to use Mooncake, unsafe deserialization exposed directly over ZMQ/TCP will allow attackers to execute remote code on distributed hosts. Details 1. Pickle deserialization vulnerabilities are well documented. 2. The mooncake pipe is exposed over the network by design...

9CVSS9.5AI score0.01667EPSS
SaveExploits1References6
Github Security Blog
Github Security Blog
added 2025/03/19 3:55 p.m.41 views

vLLM Allows Remote Code Execution via Mooncake Integration

Summary When vLLM is configured to use Mooncake, unsafe deserialization exposed directly over ZMQ/TCP will allow attackers to execute remote code on distributed hosts. Details 1. Pickle deserialization vulnerabilities are well documented. 2. The mooncake pipe is exposed over the network by design...

9CVSS9.6AI score0.00728EPSS
SaveExploits0References6Affected Software1
CVE
CVE
added 2025/03/19 3:33 p.m.298 views

CVE-2025-29783

CVE-2025-29783 affects vLLM when Mooncake is configured for KV distribution across distributed hosts. The root cause is unsafe deserialization via pickle in the mooncake_pipe path exposed over ZMQ/TCP on all network interfaces, allowing remote code execution on affected distributed hosts. Public ...

9CVSS9.8AI score0.00728EPSS
SaveExploits0References3Affected Software1
The Hacker News
The Hacker News
added 2025/03/18 1:11 p.m.22 views

New Ad Fraud Campaign Exploits 331 Apps with 60M+ Downloads for Phishing and Intrusive Ads

Cybersecurity researchers have warned about a large-scale ad fraud campaign that has leveraged hundreds of malicious apps published on the Google Play Store to serve full-screen ads and conduct phishing attacks. "The apps display out-of-context ads and even try to persuade victims to give away...

7.2AI score
SaveExploits0
The Hacker News
The Hacker News
added 2025/03/17 1:12 p.m.38 views

Unpatched Edimax Camera Flaw Exploited for Mirai Botnet Attacks Since Last Year

An unpatched security flaw impacting the Edimax IC-7100 network camera is being exploited by threat actors to deliver Mirat botnet malware variants since at least May 2024. The vulnerability in question is CVE-2025-1316 CVSS v4 score: 9.3, a critical operating system command injection flaw that a...

9.3CVSS9.1AI score0.73236EPSS
SaveExploits3
Rows per page
Query Builder