Over 100 Malicious AI/ML Models Found on Hugging Face Platform

As many as 100 malicious artificial intelligence AI/machine learning ML models have been discovered in the Hugging Face platform. These include instances where loading a pickle file leads to code execution, software supply chain security firm JFrog said. "The model's payload grants the attacker a...

Various GL.iNet products Security Breach

GL.iNet MT6000 and others are products of China's GL.iNet GL.iNet. GL.iNet MT6000 is a router. GL.iNet XE3000 is an intelligent router. A security vulnerability exists in several GL.iNet products, which stems from a vulnerability that allows an attacker to obtain critical user information by...

Three Tips to Protect Your Secrets from AI Accidents

Last year, the Open Worldwide Application Security Project OWASP published multiple versions of the "OWASP Top 10 For Large Language Models," reaching a 1.0 document in August and a 1.1 document in October. These documents not only demonstrate the rapidly evolving nature of Large Language Models,...

Siemens Simcenter Femap Out-of-Bounds Write Vulnerability (CNVD-2024-09332)

Simcenter Femap is an advanced simulation application for creating, editing and checking finite element models of complex products or systems. An out-of-bounds write vulnerability exists in Siemens Simcenter Femap, which can be exploited by an attacker to execute code in the context of the curren...

PT-2024-5545 · D Link · D-Link Dir-882-Us +9

Name of the Vulnerable Software and Affected Versions: D-Link DIR-1960-US, DIR-2640-US, DIR-2660-US, DIR-3040-US, DIR-3060-US, DIR-867-US, DIR-878, DIR-882-US, DIR-882/RE, DIR-882-CA and DIR-882-US/RE affected versions not specified Description: The issue exists due to the lack of measures to...

Tenda AX12 and Tenda AX9 Security Vulnerabilities

Tenda AX12 and Tenda AX9 are both products of Tenda China.Tenda AX12 is a dual-band Gigabit Wifi 6 wireless router.Tenda AX9 is a Wi-Fi 6 router. A security vulnerability exists in the Tenda TX9 V1 V22.03.02.54, Tenda AX3 V3 V16.03.12.11, Tenda AX9 V1 V22.03.01.46, and Tenda AX12 V1 V22.03.01.46...

Fedora: Security Advisory for firecracker (FEDORA-2024-f2305d485f)

The remote host is missing an update for the SPDX-FileCopyrightText: 2024 Greenbone AG Some text descriptions might be excerpted from a referenced sources, and are Copyright C by the respective right holders. SPDX-License-Identifier: GPL-2.0-only ifdescription...

RICOH SP C250 Series Buffer Overflow (CVE-2019-14308)

Several Ricoh printers have multiple buffer overflows parsing LPD packets, which allow an attacker to cause a denial of service or code execution via crafted requests to the LPD service. Affected firmware versions depend on the printer models. One affected configuration is...

PT-2024-19678

Name of the Vulnerable Software and Affected Versions Autodesk AutoCAD affected versions not specified Description A maliciously crafted MODEL 3DM, STP, or SLDASM file, when parsed through Autodesk applications using opennurbs.dll, can lead to a memory corruption issue by write access violation...

[SECURITY] Fedora 39 Update: firecracker-1.6.0-6.fc39

Firecracker is an open source virtualization technology that is purpose-built for creating and managing secure, multi-tenant container and function-based services that provide serverless operational models. Firecracker runs workloads in lightweight virtual machines, called microVMs, which combine...

Teaching LLMs to Be Deceptive

Interesting research: "Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training": Abstract: Humans are capable of strategically deceptive behavior: behaving helpfully in most situations, but then behaving very differently in order to pursue alternative objectives when given th...

Canon Multiple Products Buffer Error Vulnerability

Canon Color imageCLASS is a series of printers from Canon Japan. A security vulnerability exists in several Canon products. The vulnerability can be exploited by an attacker to execute arbitrary code. The following products and versions are affected: Satera LBP670C Series, Satera MF750C Series...

Canon Multiple Products Buffer Error Vulnerability

Canon Color imageCLASS is a series of printers from Canon Japan. A security vulnerability exists in several Canon products. The vulnerability can be exploited by an attacker to execute arbitrary code. The following products and versions are affected: Satera LBP670C Series, Satera MF750C Series...

PT-2024-2323

Name of the Vulnerable Software and Affected Versions Sharp NEC Displays P403, P463, P553, P703, P801, X554UN, X464UN, X554UNS, X464UNV, X474HB, X464UNS, X554UNV, X555UNS, X555UNV, X754HB, X554HB, E705, E805, E905, UN551S, UN551VS, X551UHD, X651UHD, X841UHD, X981UHD, MD551C8 Description The issue...

Electrolink FM/DAB/TV Transmitter (login.htm/mail.htm) - Credentials Disclosure

Electrolink FM/DAB/TV Transmitter login.htm/mail.htm Credentials Disclosure Vendor: Electrolink s.r.l. Product web page: https://www.electrolink.com Affected version: 10W, 100W, 250W, Compact DAB Transmitter 500W, 1kW, 2kW Medium DAB Transmitter 2.5kW, 3kW, 4kW, 5kW High Power DAB Transmitter 100...

Multiple Devices Information Disclosure / Path Traversal Vulnerabilities - Active Check

Multiple devices are prone to information disclosure and / or path traversal vulnerabilities. SPDX-FileCopyrightText: 2024 Greenbone AG Some text descriptions might be excerpted from a referenced sources, and are Copyright C by the respective right holders. SPDX-License-Identifier: GPL-2.0-only i...

Chatbots and Human Conversation

For most of history, communicating with a computer has not been like communicating with a person. In their earliest years, computers required carefully constructed instructions, delivered through punch cards; then came a command-line interface, followed by menus and options and text boxes. If you...

AI likely to boost ransomware, warns government body

The British National Cyber Security Centre NCSC says it expects Artificial Intelligence AI to heighten the global ransomware threat. In a report, the NCSC makes the assessment that AI will almost certainly increase the volume and heighten the impact of cyberattacks over the next two years. We’re...

Poisoning AI Models

New research into poisoning AI models: The researchers first trained the AI models using supervised learning and then used additional "safety training" methods, including more supervised learning, reinforcement learning, and adversarial training. After this, they checked if the AI still had hidde...

Side Channels Are Common

Really interesting research: "Lend Me Your Ear: Passive Remote Physical Side Channels on PCs." Abstract: We show that built-in sensors in commodity PCs, such as microphones, inadvertently capture electromagnetic side-channel leakage from ongoing computation. Moreover, this information is often...