Lucene search
+L

183 matches found

Packet Storm News
Packet Storm News
added 2025/04/14 12:0 a.m.6 views

Research on CNN-BiLSTM Network Traffic Anomaly Detection Model Based on MindSpore

With the widespread adoption of the Internet of Things IoT and Industrial IoT IIoT technologies, network architectures have become increasingly complex, and the volume of traffic has grown substantially. This evolution poses significant challenges to traditional security mechanisms, particularly ...

7AI score
SaveExploits0
CNNVD
CNNVD
added 2025/03/20 12:0 a.m.7 views

ONNX 安全漏洞

ONNX Open Neural Network Exchange is an open standard for machine learning interoperability open-sourced by ONNX. A security vulnerability exists in ONNX 1.16.1 and earlier versions, which stems from a path traversal attack that could lead to arbitrary file overwrites...

9.1CVSS7.8AI score0.01357EPSS
SaveExploits1References2
Schneier on Security
Schneier on Security
added 2024/07/29 11:2 a.m.10 views

New Research in Detecting AI-Generated Videos

The latest in what will be a continuing arms race between creating and detecting videos: The new tool the research project is unleashing on deepfakes, called "MISLnet", evolved from years of data derived from detecting fake images and video with tools that spot changes made to digital video or...

7.3AI score
SaveExploits0
BDU FSTEC
BDU FSTEC
added 2024/06/07 12:0 a.m.10 views

The vulnerability of the download_model_with_test_data() function in the software library for building deep learning neural networks, Open Neural Network Exchange (ONNX), allows a hacker to execute arbitrary code.

The vulnerability of the downloadmodelwithtestdata function in the software library for building deep learning neural networks, Open Neural Network Exchange ONNX, is related to an incorrect path name limitation for accessing restricted directories. Exploiting this vulnerability could allow a...

10CVSS8.1AI score0.01178EPSS
SaveExploits1References3Affected Software1
CNNVD
CNNVD
added 2024/06/06 12:0 a.m.7 views

Open Neural Network Exchange Path Traversal Vulnerability

Open Neural Network Exchange ONNX is an open ecosystem that enables AI developers to choose the right tools as their projects evolve. A path traversal vulnerability exists in Open Neural Network Exchange version 1.16.0, which stems from insufficient protection against path traversal attacks in...

8.8CVSS7AI score0.01178EPSS
SaveExploits1References4
CNNVD
CNNVD
added 2024/02/23 12:0 a.m.7 views

Open Neural Network Exchange Buffer Error Vulnerability

The Open Neural Network Exchange ONNX is an open ecosystem that enables AI developers to choose the right tools for their projects as they evolve. A buffer error vulnerability exists in Open Neural Network Exchange 1.15.0 and prior versions, which stems from the ONNXASSERT and ONNXASSERTM functio...

9.1CVSS7AI score0.00594EPSS
SaveExploits0References6
CNNVD
CNNVD
added 2024/02/23 12:0 a.m.5 views

Open Neural Network Exchange Path Traversal Vulnerability

Open Neural Network Exchange ONNX is an open ecosystem that enables AI developers to choose the right tools as their projects evolve. A security vulnerability exists in Open Neural Network Exchange versions 1.15.0 and earlier, which stems from a field in the externaldata tensor prototype that may...

7.5CVSS6.8AI score0.01189EPSS
SaveExploits0References6
IBM Security Bulletins
IBM Security Bulletins
added 2023/12/12 5:35 p.m.66 views

Security Bulletin: Mutiple Vulnerabilties in Open Source packages affecting IBM Watson Machine Learning Accelerator on Cloud Pak for Data

Summary IBM Watson Machine Learning Accelerator on Cloud Pak for Data is vulnerable to several open source vulnerabilites. This bulletin identifies the steps to take to address the vulnerabilities. Vulnerability Details CVEID:CVE-2022-1996 DESCRIPTION: go-restful could allow a remote attacker to...

9.8CVSS9.8AI score0.09501EPSS
SaveExploits17Affected Software1
SUSE CVE
SUSE CVE
added 2023/02/18 2:21 a.m.3 views

SUSE CVE-2022-26076

Uncontrolled search path element in the IntelR oneAPI Deep Neural Network oneDNN before version 2022.1 may allow an authenticated user to potentially enable escalation of privilege via local access...

7.3CVSS7.2AI score0.00233EPSS
SaveExploits0References3
NVD
NVD
added 2023/02/16 8:15 p.m.29 views

CVE-2022-26076

Uncontrolled search path element in the IntelR oneAPI Deep Neural Network oneDNN before version 2022.1 may allow an authenticated user to potentially enable escalation of privilege via local access...

7.3CVSS7AI score0.00233EPSS
SaveExploits0References1
OSV
OSV
added 2023/02/16 8:15 p.m.10 views

UBUNTU-CVE-2022-26076

Uncontrolled search path element in the IntelR oneAPI Deep Neural Network oneDNN before version 2022.1 may allow an authenticated user to potentially enable escalation of privilege via local access...

7.3CVSS7.1AI score0.00233EPSS
SaveExploits0References2
CVE
CVE
added 2023/02/16 7:59 p.m.50 views

CVE-2022-26076

Intel oneAPI Deep Neural Network (oneDNN) before 2022.1 contains an uncontrolled search path element that may allow an authenticated user to escalate privileges via local access. Public sources (Red Hat CVE entry and Intel advisory) confirm the affected component and the local-privilege escalatio...

7.3CVSS7.3AI score0.00233EPSS
SaveExploits0References1Affected Software1
Vulnrichment
Vulnrichment
added 2023/02/16 7:59 p.m.13 views

CVE-2022-26076

Uncontrolled search path element in the IntelR oneAPI Deep Neural Network oneDNN before version 2022.1 may allow an authenticated user to potentially enable escalation of privilege via local access...

6.7CVSS7.4AI score0.00233EPSS
SaveExploits0References1
CNNVD
CNNVD
added 2023/02/16 12:0 a.m.7 views

Intel OneApi Toolkits 代码问题漏洞

Intel OneApi Toolkits is a set of core tools and libraries from the United States Intel Intel. for developing high-performance, data-centric applications across different architectures. A security vulnerability exists in Intel oneAPI Deep Neural Network oneDNN versions prior to 2022.1, which stem...

7.3CVSS7.3AI score0.00233EPSS
SaveExploits0References2
Securelist
Securelist
added 2023/02/15 10:0 a.m.41 views

IoC detection experiments with ChatGPT

ChatGPT is a groundbreaking chatbot powered by the neural network-based language model text-davinci-003 and trained on a large dataset of text from the Internet. It is capable of generating human-like text in a wide range of styles and formats. ChatGPT can be fine-tuned for specific tasks, such a...

7.6AI score
SaveExploits0
PyPA
PyPA
added 2023/01/26 9:15 p.m.6 views

PYSEC-2023-38

Versions of the package onnx before 1.13.0 are vulnerable to Directory Traversal as the externaldata field of the tensor proto can have a path to the file which is outside the model current directory or user-provided directory, for example "../../../etc/passwd"...

7.5CVSS7AI score0.01608EPSS
SaveExploits1References7Affected Software1
CNNVD
CNNVD
added 2023/01/26 12:0 a.m.10 views

Open Neural Network Exchange 路径遍历漏洞

The Open Neural Network Exchange ONNX is an open ecosystem that enables AI developers to choose the right tools as their projects evolve. A security vulnerability exists in Open Neural Network Exchange version 1.13.0, which stems from the fact that the externaldata field of a tensor proto may poi...

7.5CVSS6.3AI score0.01608EPSS
SaveExploits1References8
Github Security Blog
Github Security Blog
added 2022/05/13 1:7 a.m.21 views

Sony Neural Network Libraries reliance on untrusted inputs prior to v1.0.10

nbla/logger.cpp in libnnabla.a in Sony Neural Network Libraries aka nnabla prior to v1.0.10 relies on the HOME environment variable, which might be untrusted...

9.8CVSS2AI score0.01552EPSS
SaveExploits0References7Affected Software1
OSV
OSV
added 2022/05/13 1:7 a.m.46 views

GHSA-4Q2W-RW7M-XQW6 Sony Neural Network Libraries reliance on untrusted inputs prior to v1.0.10

nbla/logger.cpp in libnnabla.a in Sony Neural Network Libraries aka nnabla prior to v1.0.10 relies on the HOME environment variable, which might be untrusted...

9.8CVSS9.4AI score0.01552EPSS
SaveExploits0References8
Schneier on Security
Schneier on Security
added 2021/08/06 11:44 a.m.50 views

Using “Master Faces” to Bypass Face-Recognition Authenticating Systems

Fascinating research: "Generating Master Faces for Dictionary Attacks with a Network-Assisted Latent Space Evolution." Abstract: A master face is a face image that passes face-based identity-authentication for a large portion of the population. These faces can be used to impersonate, with a high...

0.8AI score
SaveExploits0
Rows per page
Query Builder