Perplexity AI Web Application 安全漏洞

Perplexity AI Web Application is a big data search engine application utilizing a big language model from Perplexity, Inc. in the United States. A security vulnerability exists in Perplexity AI Web Application GPT-4 version 2.51.0, which stems from mishandling of the token component and could lea...

CVE-2025-49847

CVE-2025-49847 affects llama.cpp: prior to v5662, an attacker-supplied GGUF vocabulary can trigger a buffer overflow in the vocabulary-loading path. The root cause is in llama_vocab::impl::token_to_piece(), where a large size_t token length is cast to int32_t, bypassing the length check and causi...

VulBinLLM: LLM-Powered Vulnerability Detection for Stripped Binaries

Recognizing vulnerabilities in stripped binary files presents a significant challenge in software security. Although some progress has been made in generating human-readable information from decompiled binary files with Large Language Models LLMs, effectively and scalably detecting vulnerabilitie...

CVE-2024-34359

llama-cpp-python is the Python bindings for llama.cpp. llama-cpp-python depends on class Llama in llama.py to load .gguf llama.cpp or Latency Machine Learning Models. The init constructor built in the Llama takes several parameters to configure the loading and running of the model. Other than NUM...

CVE-2025-43850 GHSL-2025-020_Retrieval-based-Voice-Conversion-WebUI

Retrieval-based-Voice-Conversion-WebUI is a voice changing framework based on VITS. Versions 2.2.231006 and prior are vulnerable to unsafe deserialization. The ckptdir variable takes user input e.g. a path to a model and passes it to the changeinfo function in export.py, which uses it to load the...

FastChat 代码问题漏洞

FastChat is an open source platform from LMSYS for training, deploying and evaluating chatbots based on large language models. A code issue vulnerability exists in FastChat version 0.2.36 and earlier, which stems from a deserialization issue in the splitfiles/applydeltalowcpumem function in the...

CVE-2024-6854 Arbitrary File Overwrite in h2oai/h2o-3

In h2oai/h2o-3 version 3.46.0, the endpoint for exporting models does not restrict the export location, allowing an attacker to export a model to any file in the server's file structure, thereby overwriting it. This vulnerability can be exploited to overwrite any file on the target server with a...

Vulnerability of the __xdp_reg_mem_model() function (net/core/xdp.c) in the Linux operating system kernel, which allows a hacker to cause a service failure

The vulnerability of the xdpregmemmodel function net/core/xdp.c in the Linux operating system’s kernel is related to the unlimited distribution of resources. Exploiting this vulnerability could allow an attacker to cause a service failure...

CVE-2025-1550

The Keras Model.loadmodel function permits arbitrary code execution, even with safemode=True, through a manually constructed, malicious .keras archive. By altering the config.json file within the archive, an attacker can specify arbitrary Python modules and functions, along with their arguments, ...

Siemens Tecnomatix Plant Simulation

SUMMARY Siemens Tecnomatix Plant Simulation do not properly limit the access of the simulation model to the filesystem. This could allow an unauthorized attacker to read or delete arbitrary files or the entire filesystem of the device. Siemens has released new versions for the affected products...

UBUNTU-CVE-2024-22018

A vulnerability has been identified in Node.js, affecting users of the experimental permission model when the --allow-fs-read flag is used. This flaw arises from an inadequate permission model that fails to restrict file stats through the fs.lstat API. As a result, malicious actors can retrieve...

LoLLMs Security Vulnerabilities

LoLLMs is a Web UI for a large language multimodal system by the individual developer Saifeddine ALOUI. A security vulnerability exists in LoLLMs that stems from the installmodel function in lollmscore/lollms/binding.py that does not properly clean up the file protocol and other inputs, resulting...

CVE-2024-31837

DMitry Deepmagic Information Gathering Tool 1.3a has a format-string vulnerability, with a threat model similar to CVE-2017-7938...

UBUNTU-CVE-2024-3660

A arbitrary code injection vulnerability in TensorFlow's Keras framework 2.13 allows attackers to execute arbitrary code with the same permissions as the application using a model that allow arbitrary code irrespective of the application...

CVE-2024-3660 Arbitrary code injection vulnerability in Keras framework < 2.13

A arbitrary code injection vulnerability in TensorFlow's Keras framework 2.13 allows attackers to execute arbitrary code with the same permissions as the application using a model that allow arbitrary code irrespective of the application...

llama.cpp Input Validation Error Vulnerability

llama.cpp is a multimodal model by Georgi Gerganov Personal Developer. An input validation error vulnerability exists in llama.cpp, which stems from a specially crafted .gguf file that could lead to code execution...

@backstage/backend-app-api (>=0.0.0-nightly-20241117023529 <=0.0.0-nightly-20260519032312), @backstage/backend-defaults (>=0.0.0-nightly-20241117023529 <=0.0.0-nightly-20260519032312) +274 more potentially affected by CVE-2023-25571 via @backstage/catalog-model (>=0.0.0-nightly-20220708025041 <=1.1.5)

@backstage/catalog-model NPM version =0.0.0-nightly-20220708025041, =0.0.0-nightly-20241117023529, =0.0.0-nightly-20241117023529, =0.0.0-nightly-20241117023529, =0.0.0-nightly-20241117023529, =0.0.0-nightly-20241117023529, =0.0.0-nightly-20241117023529, =0.0.0-nightly-2021442275,...

Bluecms has an unspecified vulnerability

BlueCMS is a PHP and MySQL based content management system CMS. a security vulnerability exists in BlueCMS version 1.6, which stems from an SQL injection in line 55 of admin/model.php. No details of the vulnerability are currently available...

CVE-2022-22261

CVE-2022-22261 concerns Huawei HarmonyOS HiAIserver. Multiple connected sources confirm a vulnerability where the system fails to strictly validate the weights used in a model, allowing exploitation that can cause AI service anomalies or denial of service. The issue is described as a weight-valid...

The vulnerability in the web interface of the microprogramming software for Cisco Analog Telephone Adapter (ATA) model 190 allows a perpetrator to cause a service failure.

The vulnerability of the web interface of the microprogramming software for Cisco Analog Telephone Adapter ATA series 190 devices is related to deficiencies in rate-limiting mechanisms when sending ICMP packets. Exploiting this vulnerability could allow a malicious actor to cause service...