Comprehensive Vulnerability Analysis Is Necessary for Trustworthy LLM-MAS

This paper argues that a comprehensive vulnerability analysis is essential for building trustworthy Large Language Model-based Multi-Agent Systems LLM-MAS. These systems, which consist of multiple LLM-powered agents working collaboratively, are increasingly deployed in high-stakes applications bu...

Seven Security Challenges That Must Be Solved in Cross-Domain Multi-Agent LLM Systems

Large language models LLMs are rapidly evolving into autonomous agents that cooperate across organizational boundaries, enabling joint disaster response, supply-chain optimization, and other tasks that demand decentralized expertise without surrendering data ownership. Yet, cross-domain...

Deepfake Scams Are Distorting Reality Itself

The easy access that scammers have to sophisticated AI tools means everything from emails to video calls can’t be trusted...

Cisco Nexus Dashboard Fabric Controller 安全漏洞

The Cisco Nexus Dashboard Fabric Controller is a comprehensive network management platform from Cisco for managing Cisco NX-OS deployments for LAN, SAN, and IP Fabric for Media IPFM networks in data centers. A trust management issue vulnerability exists in Cisco Nexus Dashboard Fabric Controller...

⚡ Weekly Recap: APT Intrusions, AI Malware, Zero-Click Exploits, Browser Hijacks and More

If this had been a security drill, someone would've said it went too far. But it wasn't a drill—it was real. The access? Everything looked normal. The tools? Easy to find. The detection? Came too late. This is how attacks happen now—quiet, convincing, and fast. Defenders aren't just chasing hacke...

A Unified Framework for Human AI Collaboration in Security Operations Centers with Trusted Autonomy

This article presents a structured framework for Human-AI collaboration in Security Operations Centers SOCs, integrating AI autonomy, trust calibration, and Human-in-the-loop decision making. Existing frameworks in SOCs often focus narrowly on automation, lacking systematic structures to manage...

Trust Boundary Violation

Overview Affected versions of this package are vulnerable to Trust Boundary Violation due to the Browse method using URLs provided through API responses from authenticated GitHub hosts when users execute gh commands. An attacker in control of a malicious GitHub server can execute arbitrary comman...

Trust Boundary Violation

Overview Affected versions of this package are vulnerable to Trust Boundary Violation due to the Browse method using URLs provided through API responses from authenticated GitHub hosts when users execute gh commands. An attacker in control of a malicious GitHub server can execute arbitrary comman...

Project AI 信任管理问题漏洞

Project AI is a platform by Aryan Singh Personal Developer designed to simplify the creation of AI agents using Google AI Studio. Project AI has a trust management issue vulnerability that stems from the presence of hard-coded API keys in the code...

Consilium Safety CS5000 Fire Panel 信任管理问题漏洞

The Consilium Safety CS5000 Fire Panel is a fire alarm control panel from Consilium Safety of Sweden. A trust management issue vulnerability exists in the Consilium Safety CS5000 Fire Panel that stems from the presence of hard-coded passwords on the VNC server, which could lead to remote access t...

Chainless Apps: a Modular Framework for Building Apps with Web2 Capability and Web3 Trust

Modern blockchain applications are often constrained by a trade-off between user experience and trust. Chainless Apps present a new paradigm of application architecture that separates execution, trust, bridging, and settlement into distinct compostable layers. This enables app-specific sequencing...

Intel Xeon 6 Processor Elevation of Privilege Vulnerability

The Intel Xeon 6 Processor is a new generation of server processors from Intel aimed at data centers, artificial intelligence AI and high performance computing HPC. The Intel Xeon 6 Processor suffers from an elevation of privilege vulnerability that stems from insufficient control flow management...

Dell PowerStore 信任管理问题漏洞

Dell PowerStore is a scalable all-flash array storage from Dell USA. A trust management issue vulnerability exists in Dell PowerStore version 4.0.0.0, which stems from the use of hard-coded credentials and can be exploited by an attacker to cause unauthorized access...

IBM Security ReaQta EDR Trust Management Issues Vulnerability

IBM Security ReaQta EDR is an Endpoint Detection and Response EDR solution from International Business Machines IBM that detects, investigates and responds to endpoint threats in real time through behavioral analytics and AI technology, providing automated threat hunting and incident response...

A Novel Zero-Trust Identity Framework for Agentic AI: Decentralized Authentication and Fine-Grained Access Control

Traditional Identity and Access Management IAM systems, primarily designed for human users or static machine identities via protocols such as OAuth, OpenID Connect OIDC, and SAML, prove fundamentally inadequate for the dynamic, interdependent, and often ephemeral nature of AI agents operating at...

Security Benefits and Side Effects of Labeling AI-Generated Images

Generative artificial intelligence is developing rapidly, impacting humans' interaction with information and digital media. It is increasingly used to create deceptively realistic misinformation, so lawmakers have imposed regulations requiring the disclosure of AI-generated content. However, only...

Chinese-Owned VPNs

One one my biggest worries about VPNs is the amount of trust users need to place in them, and how opaque most of them are about who owns them and what sorts of data they retain. A new study found that many commercials VPNS are often surreptitiously owned by Chinese companies. It would be hard for...

ADA: Automated Moving Target Defense for AI Workloads Via Ephemeral Infrastructure-Native Rotation in Kubernetes

This paper introduces the Adaptive Defense Agent ADA, an innovative Automated Moving Target Defense AMTD system designed to fundamentally enhance the security posture of AI workloads. ADA operates by continuously and automatically rotating these workloads at the infrastructure level, leveraging t...

Zero-Trust Foundation Models: a New Paradigm for Secure and Collaborative Artificial Intelligence for Internet of Things

This paper focuses on Zero-Trust Foundation Models ZTFMs, a novel paradigm that embeds zero-trust security principles into the lifecycle of foundation models FMs for Internet of Things IoT systems. By integrating core tenets, such as continuous verification, least privilege access LPA, data...

The vulnerabilities of Software Guard eXtensions (SGX) and Trust Domain Extensions (TDX) in microsoftware for Intel Xeon 6 processor with E-cores allow attackers to enhance their privileges.

The vulnerability of Software Guard eXtensions SGX and Trust Domain Extensions TDX in microsoftware for Intel Xeon 6 processor with E-cores is related to improper restrictions on software interfaces by hardware functions. Exploiting this vulnerability can allow attackers to enhance their privileg...