Adversarial Suffix Filtering: a Defense Pipeline for LLMs

Large Language Models LLMs are increasingly embedded in autonomous systems and public-facing environments, yet they remain susceptible to jailbreak vulnerabilities that may undermine their security and trustworthiness. Adversarial suffixes are considered to be the current state-of-the-art...

CVE-2025-22892

Uncontrolled resource consumption for some OpenVINO™ model server software maintained by IntelR before version 2024.4 may allow an unauthenticated user to potentially enable denial of service via adjacent access...

CVE-2025-22892

Summary of CVE-2025-22892 : Uncontrolled resource consumption in Intel OpenVINO Model Server software (pre-2024.4) could allow an unauthenticated, adjacent attacker to trigger a denial of service. The issue stems from resource management weaknesses that permit excessive resource use. Affected pro...

php: libxml streams use wrong content-type header when requesting a redirected resource

A flaw was found in PHP's DOM and SimpleXML extensions. This vulnerability allows incorrect parsing of a redirected HTTP resource via improper content-type header handling...

Intel OpenVINO Model Server Software Advisory - Lenovo Support US

No description provided...

Defining a new methodology for modeling and tracking compartmentalized threats

In the evolving cyberthreat landscape, Cisco Talos is witnessing a significant shift towards compartmentalized attack kill chains, where distinct stages -- such as initial compromise and subsequent exploitation -- are executed by multiple threat actors. This trend complicates traditional threat...

kernel: xdp: fix invalid wait context of page_pool_destroy()

In the Linux kernel, the following vulnerability has been resolved: xdp: fix invalid wait context of pagepooldestroy If the driver uses a page pool, it creates a page pool with pagepoolcreate. The reference count of page pool is 1 as default. A page pool will be destroyed only when a reference...

VMware Aria Automation 安全漏洞

VMware Aria Automation is a modern workflow automation platform from VMware that simplifies and automates complex data center infrastructure tasks to improve scalability and agility. A security vulnerability exists in VMware Aria Automation that originates from DOM-type cross-site scripting and...

On the Interplay of Explainability, Privacy and Predictive Performance with Explanation-Assisted Model Extraction

Machine Learning as a Service MLaaS has gained important attraction as a means for deploying powerful predictive models, offering ease of use that enables organizations to leverage advanced analytics without substantial investments in specialized infrastructure or expertise. However, MLaaS...

Moderate: rpm-ostree security update

The rpm-ostree tool binds together the RPM packaging model with the OSTree model of bootable file system trees. It provides commands that can be used both on client systems and on server-side composes. The rpm-ostree-client package provides commands for client systems to perform upgrades and...

Intel Server M50FCP和Intel Server D50DNP 输入验证错误漏洞

Intel Server M50FCP and Intel Server D50DNP are both servers from Intel Corporation USA. An input validation error vulnerability exists in Intel Server M50FCP and Intel Server D50DNP, which stems from improper input validation in the UEFI firmware DXE module, which could lead to elevation of...

Removing Watermarks with Partial Regeneration Using Semantic Information

As AI-generated imagery becomes ubiquitous, invisible watermarks have emerged as a primary line of defense for copyright and provenance. The newest watermarking schemes embed semantic signals - content-aware patterns that are designed to survive common image manipulations - yet their true...

PT-2025-21114 · Intel · Openvino Model Server

Name of the Vulnerable Software and Affected Versions: OpenVINO model server software versions prior to 2024.4 Description: The issue allows an unauthenticated user to potentially enable denial of service via adjacent access due to uncontrolled resource consumption. Recommendations: For versions...

Intel OpenVINO model server 资源管理错误漏洞

Intel OpenVINO model server is a high-performance AI model servitization platform based on the Intel OpenVINO tool suite from Intel Corporation USA. A resource management error vulnerability exists in Intel OpenVINO model server versions prior to 2024.4, which stems from insufficient control over...

Red Teaming the Mind of the Machine: a Systematic Evaluation of Prompt Injection and Jailbreak Vulnerabilities in LLMs

Large Language Models LLMs are increasingly integrated into consumer and enterprise applications. Despite their capabilities, they remain susceptible to adversarial attacks such as prompt injection and jailbreaks that override alignment safeguards. This paper provides a systematic investigation o...

OpenVINO™ Model Server Software Advisory

Summary: A potential security vulnerability in the OpenVINO™ model server software maintained by Intel® may allow denial of service. Intel is releasing software updates to mitigate this potential vulnerability. Vulnerability Details: CVEID: CVE-2025-22892 Description: Uncontrolled resource...

Optimized Couplings for Watermarking Large Language Models

Large-language models LLMs are now able to produce text that is, in many cases, seemingly indistinguishable from human-generated content. This has fueled the development of watermarks that imprint a signal'' in LLM-generated text with minimal perturbation of an LLM's output. This paper provides a...

Improved Algorithms for Differentially Private Language Model Alignment

Language model alignment is crucial for ensuring that large language models LLMs align with human preferences, yet it often involves sensitive user data, raising significant privacy concerns. While prior work has integrated differential privacy DP with alignment techniques, their performance...

Intel Server M50FCP和Intel Server D50DNP 输入验证错误漏洞

Intel Server M50FCP and Intel Server D50DNP are both servers from Intel Corporation USA. An input validation error vulnerability exists in Intel Server M50FCP and Intel Server D50DNP, which stems from mishandling of UEFI firmware errors that could lead to elevation of privilege...

CVE-2025-47274

ToolHive is a utility designed to simplify the deployment and management of Model Context Protocol MCP servers. Due to the ordering of code used to start an MCP server container, versions of ToolHive prior to 0.0.33 inadvertently store secrets in the run config files which are used to restart...