aegis-audio-defense

AEGIS: Audio Endogenous Guarding via Internal Signals Against Large Audio-Language Model Jailbreaks Submitted to ICASSP 2027. AEGIS keeps the target audio-language model frozen and adds a mid-layer risk gate that conditionally drives late-layer safety adapters, with closed-loop scaling at...

redthread

RedThread Find the exploit. Judge it. Draft the fix. Prove what changed. RedThread is a CLI-first framework for testing LLM systems, validating failures, and turning confirmed vulnerabilities into evidence-backed defense candidates. It is built for teams who need more than a one-off jailbreak dem...

Security of Foundation-Model-Powered Embodied Agents: Attack Surfaces, Attacks, Defenses, and Evaluation

Foundation models are increasingly used for perception, reasoning, planning, and action generation in embodied agents, creating security risks that can propagate from digital inputs to physical behavior. Existing surveys often organize threats by mechanisms such as jailbreaks, prompt injection,...

PT-2026-36667

CVE-2026-30412 SentinelCloud, AI-Driven Autonomous DevOps Engineer One closed loop. Five agents. Seven scenarios. Zero hallucinated kubectl. Live demo https://t.co/ocEWNzLf9Z...

Jailbreaking the Matrix: Nullspace Steering for Controlled Model Subversion

Large language models remain vulnerable to jailbreak attacks -- inputs designed to bypass safety mechanisms and elicit harmful responses -- despite advances in alignment and instruction tuning. We propose Head-Masked Nullspace Steering HMNS, a circuit-level intervention that i identifies attentio...

The Rise of Managed Risk Operations: How the New Qualys mROC Portal Helps Partners Scale the Risk Operations Center

Key Takeaways The mROC Portal acts as a portfolio-wide command center, giving partners unified visibility into high-risk customer environments, active threats, and critical exposures to drive prioritized, portfolio-wide risk management. Partners can filter risk, drill into any customer, and take...

Meet Agent Val: Closing the Validation Gap in Exposure Management at Machine Speed with Agentic AI

Executive Summary The primary challenge in vulnerability management is proving what is actually exploitable. Many vulnerabilities are not exploited, but still drain resources. Traditional tools often fail to validate real risks. Agent Val, within Qualys Enterprise TruRisk Management, delivers thi...

Agent Grant: From Identity Signals to Measurable Risk Reduction

Executive Summary Identity is now the 1 attack surface. Agent Grant in Qualys ETM Identity uses agentic AI to measure and reduce identity risk across AD, Entra, Okta & other cloud IdPs/IDaaS. It operationalizes identity risk by turning messy Active Directory & identity-risk signals into validated...

A Demonstration of Self-Adaptive Jamming Attack Detection in AI/ML Integrated O-RAN

The open radio access network O-RAN enables modular, intelligent, and programmable 5G network architectures through the adoption of software-defined networking, network function virtualization, and implementation of standardized open interfaces. However, one of the security concerns for O-RAN,...

SoK: Measuring What Matters for Closed-Loop Security Agents

Cybersecurity is a relentless arms race, with AI driven offensive systems evolving faster than traditional defenses can adapt. Research and tooling remain fragmented across isolated defensive functions, creating blind spots that adversaries exploit. Autonomous agents capable of integrating, explo...

CyFence: Securing Cyber-Physical Controllers Via Trusted Execution Environment

In the last decades, Cyber-physical Systems CPSs have experienced a significant technological evolution and increased connectivity, at the cost of greater exposure to cyber-attacks. Since many CPS are used in safety-critical systems, such attacks entail high risks and potential safety harms...

CVE-2024-40125

An arbitrary file upload vulnerability in the Media Manager function of Closed-Loop Technology CLESS Server v4.5.2 allows attackers to execute arbitrary code via uploading a crafted PHP file to the upload endpoint...

SecurePay: Enabling Secure and Fast Payment Processing for Platform Economy

Recent years have witnessed a rapid development of platform economy, as it effectively addresses the trust dilemma between untrusted online buyers and merchants. However, malicious platforms can misuse users' funds and information, causing severe security concerns. Previous research efforts aimed...

CVE-2024-40125

An arbitrary file upload vulnerability in the Media Manager function of Closed-Loop Technology CLESS Server v4.5.2 allows attackers to execute arbitrary code via uploading a crafted PHP file to the upload endpoint...

CVE-2024-40125

An arbitrary file upload vulnerability in the Media Manager function of Closed-Loop Technology CLESS Server v4.5.2 allows attackers to execute arbitrary code via uploading a crafted PHP file to the upload endpoint...

My-CVEs

🔴 My-CVEs Vulnerability research, CVE advisories, and Proof...

CVE-2024-40125

An arbitrary file upload vulnerability in the Media Manager function of Closed-Loop Technology CLESS Server v4.5.2 allows attackers to execute arbitrary code via uploading a crafted PHP file to the upload endpoint...

PT-2024-28789

Name of the Vulnerable Software and Affected Versions Closed-Loop Technology CLESS Server version 4.5.2 Description An arbitrary file upload vulnerability in the Media Manager function allows attackers to execute arbitrary code via uploading a crafted PHP file to the upload endpoint...

CVE-2024-40125: Unrestricted Upload of File with Dangerous Type

An arbitrary file upload vulnerability in the Media Manager function of Closed-Loop Technology CLESS Server v4.5.2 allows attackers to execute arbitrary code via uploading a crafted PHP file to the upload endpoint...

CVE-2024-40125

An arbitrary file upload vulnerability in the Media Manager function of Closed-Loop Technology CLESS Server v4.5.2 allows attackers to execute arbitrary code via uploading a crafted PHP file to the upload endpoint...