Why LLMs Fail: A Failure Analysis and Partial Success Measurement for Automated Security Patch Generation

Large Language Models LLMs show promise for Automated Program Repair APR, yet their effectiveness on security vulnerabilities remains poorly characterized. This study analyzes 319 LLM-generated security patchesacross 64 Java vulnerabilities from the Vul4J benchmark. Using tri-axis evaluation...

Security Considerations for Multi-Agent Systems

Multi-agent artificial intelligence systems or MAS are systems of autonomous agents that exercise delegated tool authority, share persistent memory, and coordinate via inter-agent communication. MAS introduces qualitatively distinct security vulnerabilities from those documented for singular AI...

A Comparative Study of Recent Advances in Internet of Intrusion Detection Things

The Internet of Things IoT has revolutionized the way devices communicate and interact with each other, but it has also created new challenges in terms of security. In this context, intrusion detection has become a crucial mechanism to ensure the safety of IoT systems. To address this issue, a...

CVE-2026-29091

Locutus brings stdlibs of other programming languages to JavaScript for educational purposes. Prior to version 3.0.0, a remote code execution RCE flaw was discovered in the locutus project, specifically within the calluserfuncarray function implementation. The vulnerability allows an attacker to...

CVE-2026-29091 Locutus: Remote Code Execution (RCE) in locutus call_user_func_array due to Code Injection

Locutus brings stdlibs of other programming languages to JavaScript for educational purposes. Prior to version 3.0.0, a remote code execution RCE flaw was discovered in the locutus project, specifically within the calluserfuncarray function implementation. The vulnerability allows an attacker to...

SemFuzz: A Semantics-Aware Fuzzing Framework for Network Protocol Implementations

Network protocols are the foundation of modern communication, yet their implementations often contain semantic vulnerabilities stemming from inadequate understanding of specification semantics. Existing gray-box and black-box testing approaches lack semantic modeling of protocols, making it...

Supporting Artifact Evaluation with LLMs: A Study with Published Security Research Papers

Artifact Evaluation AE is essential for ensuring the transparency and reliability of research, closing the gap between exploratory work and real-world deployment is particularly important in cybersecurity, particularly in IoT and CPSs, where large-scale, heterogeneous, and privacy-sensitive data...

PQC-LEO: An Evaluation Framework for Post-Quantum Cryptographic Algorithms

Advances in quantum computing threaten digital communication security by undermining the foundations of current public-key cryptography through Shor's quantum algorithm. This has driven the development of Post-Quantum Cryptography PQC, a new set of algorithms resistant to quantum attacks. While...

SecureRAG-RTL: A Retrieval-Augmented, Multi-Agent, Zero-Shot LLM-Driven Framework for Hardware Vulnerability Detection

Large language models LLMs have shown remarkable capabilities in natural language processing tasks, yet their application in hardware security verification remains limited due to scarcity of publicly available hardware description language HDL datasets. This knowledge gap constrains LLM performan...

EVMbench: Evaluating AI Agents on Smart Contract Security

Smart contracts on public blockchains now manage large amounts of value, and vulnerabilities in these systems can lead to substantial losses. As AI agents become more capable at reading, writing, and running code, it is natural to ask how well they can already navigate this landscape, both in way...

New RFP Template for AI Usage Control and AI Governance 

As AI becomes the central engine for enterprise productivity, security leaders are finally getting the green light — and the budget — to secure it. But there’s a quiet crisis unfolding in the boardroom: many organizations know they need "AI Governance," but they have no idea what they are actuall...

Impact of 5G SA Logical Vulnerabilities on UAV Communications: Threat Models and Testbed Evaluation

This paper examines how logical vulnerabilities in 5G Standalone networks affect UAV command and control communication. The study looks at three attacker positions in the architecture: a malicious user equipment UE connected to the same logical network as the UAV, an attacker with access to the 5...

Astra Linux – Vulnerability in libxml2

Uncontrolled recursion occurs during XPath evaluation in libxml2, including in versions up to and including 2.9.14. This allows a local attacker to cause a stack overflow through crafted expressions. The XPath processing functions xmlXPathRunEval, xmlXPathCtxtCompile, and xmlXPathEvalExpr reset t...

Portwell Engineering Toolkits

RISK EVALUATION Successful exploitation of this vulnerability could allow a local attacker to escalate privileges or cause a denial-of-service condition. 2. RECOMMENDED PRACTICES CISA recommends users take defensive measures to minimize the risk of exploitation of this vulnerability, such as:...

Gravity Falls: A Comparative Analysis of Domain-Generation Algorithm (DGA) Detection Methods for Mobile Device Spearphishing

Mobile devices are frequent targets of eCrime threat actors through SMS spearphishing smishing links that leverage Domain Generation Algorithms DGA to rotate hostile infrastructure. Despite this, DGA research and evaluation largely emphasize malware C2 and email phishing datasets, leaving limited...

MajorDoMo Console Eval Unauthenticated RCE

This module exploits an unauthenticated remote code execution vulnerability in MajorDoMo, an open-source home automation platform. The admin panel's PHP console is accessible without authentication due to a missing exit after redirect in modules/panel.class.php. The redirect"/" call intended to...

Can LLMs Hack Enterprise Networks? -- Replicated Computational Results (RCR) Report

This is the Replicated Computational Results RCR Report for the paper "Can LLMs Hack Enterprise Networks?" The paper empirically investigates the efficacy and effectiveness of different LLMs for penetration-testing enterprise networks, i.e., Microsoft Active Directory Assumed-Breach Simulations...

OpenClaw Access Control Error Vulnerability (CNVD-2026-13408)

OpenClaw is an intelligent artificial assistant open-sourced by OpenClaw. OpenClaw suffers from an access control error vulnerability. The vulnerability stems from a mismatch between rawCommand and command in the node host system.run handler, which can be exploited by an attacker to cause the...

Exploit for CVE-2026-3395

CVE‑2026‑3395 — MaxSite CMS Unauthenticated Remote Code Execut...

CVE-2026-3395

A flaw has been found in MaxSite CMS up to 109.1. This impacts the function eval of the file application/maxsite/admin/plugins/editormarkitup/preview-ajax.php of the component MarkItUp Preview AJAX Endpoint. Executing a manipulation can lead to code injection. It is possible to launch the attack...