aisecwatch.com
DashboardVulnerabilitiesNewsResearchArchiveStatsDataset
aisecwatch.com

Real-time AI security monitoring. Tracking AI-related vulnerabilities, safety and security incidents, privacy risks, research developments, and policy changes.

Navigation

VulnerabilitiesNewsResearchDigest ArchiveNewsletter ArchiveSubscribeData SourcesStatisticsDatasetAPIIntegrationsWidgetRSS Feed

Maintained by

Truong (Jack) Luu

Information Systems Researcher

Browse All

All tracked items across vulnerabilities, news, research, incidents, and regulatory updates.

to
Export CSV
3286 items

CVE-2025-0649: Incorrect JSON input stringification in Google's Tensorflow serving versions up to 2.18.0 allows for potentially unbound

highvulnerability
security
May 6, 2025
CVE-2025-0649

CVE-2025-0649 is a bug in Google's TensorFlow Serving (a tool that runs machine learning models as a service) versions up to 2.18.0 where incorrect handling of JSON input can cause unbounded recursion (a program calling itself repeatedly without stopping), leading to server crashes. This vulnerability has a CVSS score (a 0-10 rating of how severe a vulnerability is) of 8.9, indicating high severity. The issue relates to out-of-bounds writes (writing data to unintended memory locations) and stack-based buffer overflow (overflowing a memory region meant for temporary data).

Fix: A patch is available at https://github.com/tensorflow/serving/commit/6cb013167d13f2ed3930aabb86dbc2c8c53f5adf (identified by Google Inc. as the official patch for this vulnerability).

NVD/CVE Database

CVE-2025-30165: vLLM is an inference and serving engine for large language models. In a multi-node vLLM deployment using the V0 engine,

highvulnerability
security
May 6, 2025
CVE-2025-30165

CVE-2025-30165 is a vulnerability in vLLM (a system for running large language models) that affects multi-node deployments using the V0 engine. The vulnerability exists because vLLM deserializes (converts from storage format back into usable data) incoming network messages using pickle, an unsafe method that allows attackers to execute arbitrary code on secondary hosts. This could let an attacker compromise an entire vLLM deployment if they control the primary host or use network-level attacks like ARP cache poisoning (redirecting network traffic to a malicious server).

CVE-2025-25014: A Prototype pollution vulnerability in Kibana leads to arbitrary code execution via crafted HTTP requests to machine lea

criticalvulnerability
security
May 6, 2025
CVE-2025-25014

CVE-2025-25014 is a prototype pollution vulnerability (a type of bug where an attacker modifies the basic template that objects are built from) in Kibana that allows attackers to execute arbitrary code (run commands they shouldn't be able to run) by sending specially crafted HTTP requests (malicious web requests) to machine learning and reporting endpoints. The vulnerability affects multiple versions of Kibana and was identified by Elastic.

CVE-2025-46735: Terraform WinDNS Provider allows users to manage their Windows DNS server resources through Terraform. A security issue

lowvulnerability
security
May 6, 2025
CVE-2025-46735

The Terraform WinDNS Provider (a tool for managing Windows DNS servers through Terraform, an infrastructure automation tool) had a security flaw before version 1.0.5 where the `windns_record` resource didn't properly validate user input, allowing authenticated command injection (an attack where malicious commands are sneaked into legitimate input to execute unauthorized code in the underlying PowerShell command prompt). This vulnerability only affects users who already have authentication access to the system.

CVE-2025-4287: A vulnerability was found in PyTorch 2.6.0+cu124. It has been rated as problematic. Affected by this issue is the functi

lowvulnerability
security
May 5, 2025
CVE-2025-4287

A vulnerability (CVE-2025-4287) was found in PyTorch 2.6.0+cu124 in a function that handles GPU communication, which can be exploited to cause a denial of service (making a system or service stop working) by someone with local access to the computer. The vulnerability has been publicly disclosed and rated as medium severity.

CVE-2025-43852: Retrieval-based-Voice-Conversion-WebUI is a voice changing framework based on VITS. Versions 2.2.231006 and prior are vu

criticalvulnerability
security
May 5, 2025
CVE-2025-43852

Retrieval-based-Voice-Conversion-WebUI (a framework for changing voices using AI) in version 2.2.231006 and earlier has a critical vulnerability where user input is passed unsafely to a function that loads model files using torch.load (a Python tool that can execute code from files). An attacker could exploit this by providing a malicious model file path, leading to RCE (remote code execution, where an attacker can run commands on the system).

CVE-2025-43851: Retrieval-based-Voice-Conversion-WebUI is a voice changing framework based on VITS. Versions 2.2.231006 and prior are vu

criticalvulnerability
security
May 5, 2025
CVE-2025-43851

Retrieval-based-Voice-Conversion-WebUI, a voice changing framework, has a vulnerability in versions 2.2.231006 and earlier where user input (like a file path) is passed directly to torch.load (a function that reads model files). This unsafe deserialization (loading untrusted data that could contain malicious code) allows attackers to execute arbitrary commands on the system running the software.

CVE-2025-43850: Retrieval-based-Voice-Conversion-WebUI is a voice changing framework based on VITS. Versions 2.2.231006 and prior are vu

criticalvulnerability
security
May 5, 2025
CVE-2025-43850

Retrieval-based-Voice-Conversion-WebUI is a voice changing tool that has a security flaw in versions 2.2.231006 and earlier. The vulnerability allows unsafe deserialization (loading untrusted data that could contain malicious code) when the program takes user input for a model file path and loads it using torch.load, which could let attackers run arbitrary code on the system.

CVE-2025-43849: Retrieval-based-Voice-Conversion-WebUI is a voice changing framework based on VITS. Versions 2.2.231006 and prior are vu

criticalvulnerability
security
May 5, 2025
CVE-2025-43849

Retrieval-based-Voice-Conversion-WebUI, a voice changing tool, has a vulnerability in versions 2.2.231006 and earlier where unsafe deserialization (loading data in a way that can execute malicious code) allows attackers to run code remotely. The problem occurs because the software takes user input for model file paths and loads them using torch.load without proper safety checks, enabling RCE (remote code execution, where attackers can run commands on the affected system).

CVE-2025-43848: Retrieval-based-Voice-Conversion-WebUI is a voice changing framework based on VITS. Versions 2.2.231006 and prior are vu

criticalvulnerability
security
May 5, 2025
CVE-2025-43848

Retrieval-based-Voice-Conversion-WebUI, a voice-changing tool, has a vulnerability in versions 2.2.231006 and earlier where user input for model file paths is passed unsafely to torch.load (a function that loads saved AI models). This unsafe deserialization (loading data from untrusted sources without checking it first) can allow attackers to run arbitrary code on the system.

CVE-2025-43847: Retrieval-based-Voice-Conversion-WebUI is a voice changing framework based on VITS. Versions 2.2.231006 and prior are vu

criticalvulnerability
security
May 5, 2025
CVE-2025-43847

Retrieval-based-Voice-Conversion-WebUI, a voice-changing framework, has a critical vulnerability in versions 2.2.231006 and earlier where unsafe deserialization (loading data from untrusted sources without checking it first) can occur. An attacker can exploit this by providing a malicious file path that gets loaded using torch.load, which can lead to RCE (remote code execution, where an attacker runs commands on a system they don't own).

CVE-2025-43846: Retrieval-based-Voice-Conversion-WebUI is a voice changing framework based on VITS. Versions 2.2.231006 and prior are vu

criticalvulnerability
security
May 5, 2025
CVE-2025-43846

Retrieval-based-Voice-Conversion-WebUI, a voice changing tool based on VITS (a voice synthesis model), has a vulnerability in versions 2.2.231006 and earlier where user-supplied file paths are loaded directly using torch.load (a function that can execute code when loading files), allowing attackers to run arbitrary code on the system. This happens because the ckpt_path1 variable accepts untrusted input and passes it unsafely to a model-loading function.

How ChatGPT Remembers You: A Deep Dive into Its Memory and Chat History Features

mediumnews
securityprivacy

CVE-2023-53123: In the Linux kernel, the following vulnerability has been resolved: PCI: s390: Fix use-after-free of PCI resources with

highvulnerability
security
May 2, 2025
CVE-2023-53123

A vulnerability in the Linux kernel on s390 systems caused a use-after-free bug (accessing memory after it has been freed) in PCI resources when individual functions on multi-function devices were hot-unplugged and then re-added. The bug occurred because the system kept stale references to freed memory resources, which could be incorrectly claimed when the device reappeared.

MCP: Untrusted Servers and Confused Clients, Plus a Sneaky Exploit

infonews
securityresearch

CVE-2023-53043: In the Linux kernel, the following vulnerability has been resolved: arm64: dts: qcom: sc7280: Mark PCIe controller as c

mediumvulnerability
security
May 2, 2025
CVE-2023-53043

CVE-2023-53043 is a bug in the Linux kernel where a PCIe controller (a hardware component that manages data transfer between a computer and devices connected via PCIe, a high-speed connection standard) was not marked as cache coherent (meaning the system wasn't told that data in the fast-access memory matches data in main memory). This could cause data corruption when the kernel tried to manage memory operations. The fix marks the PCIe node with the dma-coherent flag to tell the system that PCIe devices maintain cache coherency.

AI Regulatory Sandbox Approaches: EU Member State Overview

inforegulatory
policy
May 2, 2025

AI regulatory sandboxes are controlled testing environments where companies can develop and test AI systems with guidance from regulators before releasing them to the public, as required by the EU AI Act (EU's new rules for artificial intelligence). These sandboxes help companies understand what regulations they must follow, protect them from fines if they follow official guidance, and make it easier for small startups to enter the market. Each EU Member State must create at least one sandbox by August 2, 2026, though different countries are taking different approaches to organizing them.

CVE-2025-46567: LLama Factory enables fine-tuning of large language models. Prior to version 1.0.0, a critical vulnerability exists in t

mediumvulnerability
security
May 1, 2025
CVE-2025-46567

CVE-2025-46567 is a critical vulnerability in LLaMA-Factory (a tool for fine-tuning large language models) that exists before version 1.0.0. The vulnerability is in the `llamafy_baichuan2.py` script, which unsafely loads user-supplied files using `torch.load()` (a function that deserializes, or reconstructs, Python objects from saved data), allowing attackers to execute arbitrary commands by crafting a malicious file.

CVE-2025-23163: In the Linux kernel, the following vulnerability has been resolved: net: vlan: don't propagate flags on open With the

mediumvulnerability
security
May 1, 2025
CVE-2025-23163

A deadlock (a situation where the system gets stuck because two parts of code are waiting for each other) was discovered in the Linux kernel's VLAN (virtual LAN, a way to create multiple logical networks on one physical device) handling code. The problem occurred when virtual network devices tried to acquire the same lock twice during network interface initialization, causing the system to hang. The fix changes when certain network flags are propagated, moving them from the device open process to the flag change process instead.

CVE-2025-46560: vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Versions starting from 0.8.0 and p

mediumvulnerability
security
Apr 30, 2025
CVE-2025-46560

vLLM (a system for running large language models efficiently) versions 0.8.0 through 0.8.4 have a critical performance bug in how it processes multimodal input (text, images, audio). The bug uses an inefficient algorithm (quadratic time complexity, meaning it slows down exponentially as input size grows) when replacing placeholder tokens (special markers like <|audio_|> that get expanded into repeated tokens), which allows attackers to crash or freeze the system by sending specially crafted malicious inputs.

Previous98 / 165Next

Fix: The maintainers recommend that users ensure their environment is on a secure network. Additionally, the V0 engine has been off by default since v0.8.0, and the V1 engine is not affected by this issue.

NVD/CVE Database

Fix: A security update is available from Elastic for Kibana versions 8.17.6, 8.18.1, or 9.0.1, as referenced in the Elastic vendor advisory at https://discuss.elastic.co/t/kibana-8-17-6-8-18-1-or-9-0-1-security-update-esa-2025-07/377868.

NVD/CVE Database

Fix: Update to version 1.0.5, which contains a fix for the issue.

NVD/CVE Database

Fix: Apply the patch identified as commit 5827d2061dcb4acd05ac5f8e65d8693a481ba0f5, which is recommended to fix this issue.

NVD/CVE Database
NVD/CVE Database
NVD/CVE Database
NVD/CVE Database
NVD/CVE Database
NVD/CVE Database
NVD/CVE Database
NVD/CVE Database
May 5, 2025

ChatGPT has two memory features: saved memories (which users can manage) and chat history (a newer feature that builds a profile over time without user visibility or control). The chat history feature doesn't search past conversations but maintains recent chat history and learns user preferences, though the implementation details are not publicly documented, and users cannot inspect or modify what the system learns about them unless they use prompt hacking (manipulating the AI's instructions to reveal hidden information).

Embrace The Red

Fix: The fix introduces a new function called pci_bus_remove_resource() to remove individual resources from the PCI bus's resource list when a PCI function is hot-unplugged, while leaving other functions' resources untouched. Additionally, the MMIO resources (memory-mapped I/O addresses that allow software to communicate with hardware) are no longer added to the struct zpci_bus's resource list, and instead the zpci_bar_struct's resource pointer is used directly.

NVD/CVE Database
May 2, 2025

The Model Context Protocol (MCP) is a system that lets AI applications discover and use external tools from servers at runtime (while the program is running). However, MCP has a security weakness: because servers can send instructions through the tool descriptions, they can perform prompt injection (tricking an AI by hiding instructions in its input) to control the AI client, making servers more powerful than they should be.

Embrace The Red

Fix: Mark the PCIe node as dma-coherent in the device tree configuration. Patches are available at: https://git.kernel.org/stable/c/267b899375bf38944d915c9654d6eb434edad0ce, https://git.kernel.org/stable/c/8a63441e83724fee1ef3fd37b237d40d90780766, and https://git.kernel.org/stable/c/e43bba938e2c9104bb4f8bc417ac4d7bb29755e1

NVD/CVE Database
EU AI Act Updates

Fix: This issue has been patched in version 1.0.0. Users should upgrade to version 1.0.0 or later. A patch is available at: https://github.com/hiyouga/LLaMA-Factory/commit/2989d39239d2f46e584c1e1180ba46b9768afb2a

NVD/CVE Database

Fix: Propagate allmulti (receiving all multicast traffic) and promisc (promiscuous mode, receiving all traffic) flags on flags change, not on the open operation. This prevents the recursive locking issue by avoiding the need to re-acquire the same lock during device initialization.

NVD/CVE Database

Fix: This issue has been patched in version 0.8.5.

NVD/CVE Database