Converging Zero Trust and IoT Security: A Multivocal Literature Review

The convergence of Internet of Things IoT security and Zero Trust ZT principles is a trending topic, demanding a comprehensive, multi-perspective analysis. We present the first multivocal literature review MLR on this topic, combining 68 academic and 36 industrial studies. This comprehensive revi...

From Spoofing to Trust: Emergency Alerts Spoofing Testbed and Cross-Cell Verification

Public warning systems PWS in cellular networks enable authorities to broadcast emergency alerts to all mobile phones in a geographic region in the event of threats such as earthquakes or severe weather. If an attacker can imitate these alerts and transmit a forged warning containing fake news or...

RowHammer Vulnerability Counter (RVC): Redefining RowHammer Detection with Victim-Centric Tracking

The Rowhammer vulnerability poses an increasing challenge with newer generations of DRAM and aggressive technology scaling. Existing mitigation techniques, such as Graphene, Twice, and Hydra, primarily rely on tracking activation counts for each row and issuing refreshes when a row reaches a...

Symbolic Execution Meets Multi-LLM Orchestration: Detecting Memory Vulnerabilities in Incomplete Rust CVE Snippets

This paper presents a system combining symbolic execution KLEE with a 4-agent multi-LLM architecture for detecting memory vulnerabilities in Rust unsafe code. A central challenge we address is the incomplete-code problem: CVE database entries provide only isolated code snippets that lack struct...

Machine-Checked Cardinality Bounds for Masked Barrett Reduction: A 1-Bit Side-Channel Leakage Barrier in Post-Quantum Cryptographic Hardware

Barrett reduction is the nonlinear core of every practical NTT-based post-quantum cryptography implementation. Existing composition frameworks ISW, t-SNI, PINI, DOM address Boolean masking over GF2; none provides a machine-checked characterization of Barrett's leakage under first-order arithmetic...

MAS-SZZ: Multi-Agentic SZZ Algorithm for Vulnerability-Inducing Commit Identification

Accurate vulnerability-inducing commit identification serves as a foundation for a series of software security tasks, such as vulnerability detection and affected version analysis. A straightforward solution is the SZZ algorithm, which traces back through the code history to identify the earliest...

python-ecdsa DER Parser Security Test Suite

This Python script is a security test and validation suite for the python-ecdsa library, focused on detecting potential DER Distinguished Encoding Rules parsing anomalies that may relate to CVE-2026-33936...

AgentVisor: Defending LLM Agents against Prompt Injection Via Semantic Virtualization

Large Language Model LLM agents are increasingly used to automate complex workflows, but integrating untrusted external data with privileged execution exposes them to severe security risks, particularly direct and indirect prompt injection. Existing defenses face significant challenges in balanci...

DETOUR: A Practical Backdoor Attack against Object Detection

Object detection OD is critical to real-world vision systems, yet existing backdoor attacks on detection transformers DETRs for OD tasks rely on patch-wise triggers optimized at fixed locations with minimal perturbations. Such attacks overlook that backdoor triggers in the real world may appear a...

Structured Security Auditing and Robustness Enhancement for Untrusted Agent Skills

Agent Skills package SKILL.md files, scripts, reference documents, and repository context into reusable capability units, turning pre-load auditing from single-prompt filtering into cross-file security review. Existing guardrails often flag risk but recover malicious intent inconsistently under...

The Vehicle May Be Sick: Denial of Diagnostic Services by Exploiting the CAN Transport Protocol

Vehicle diagnostics has become essential for detecting in-vehicle errors and ensuring safety. While the Unified Diagnostic Services UDS protocol is widely adopted for diagnostic operations, it relies on the ISO 15765-2 standard as the transport protocol over the Controller Area Network CAN, which...

Evaluation of Prompt Injection Defenses in Large Language Models

LLM-powered applications routinely embed secrets in system prompts, yet models can be tricked into revealing them. We built an adaptive attacker that evolves its strategies over hundreds of rounds and tested it against nine defense configurations across more than 20,000 attacks. Every defense tha...

Analysis of Personal Data Exposure in Thailand

In the digital era, personal data, particularly sensitive identifiers such as the Social Security Number and National Identification Number, have become a highly valuable asset, raising significant concerns regarding privacy and security. This study examines the risks associated with the online...

Safeguarding Skies: Airport Cybersecurity in the Digital Age

The aviation industry faces significant vulnerabilities from both physical and cybersecurity threats, highlighting the urgent need for enhanced cybersecurity measures amid increasingly sophisticated attacks. This paper systematically reviews emerging threats at airports, analyzing real-world...

SMSI: System Model Security Inference: Automated Threat Modeling for Cyber-Physical Systems

Threat modeling for cyber-physical systems CPS remains a largely manual exercise. This project presents SMSI System Model Security Inference, a hybrid neuro-symbolic pipeline that starts from a SysML architecture model and produces a prioritized list of NIST 800-53 security controls. The prototyp...

Constraint-Guided Multi-Agent Decompilation for Executable Binary Recovery

Decompilation -- recovering source code from compiled binaries -- is essential for security analysis, malware reverse engineering, and legacy software maintenance. However, existing decompilers produce code that often fails to compile or execute correctly, limiting their practical utility. We...

SeqShield: A Behavioral Analysis Approach to Uncover Rootkits

Rootkits are among the most elusive types of malware, capable of bypassing traditional static analysis methods due to their metamorphic behavior. Signature-based detection techniques struggle against these threats, necessitating a shift toward dynamic analysis approaches. We propose SeqShield, a...

Semantic Denial of Service in LLM-Controlled Robots

Safety-oriented instruction-following is supposed to keep LLM-controlled robots safe. We show it also creates an availability attack surface. By injecting short safety-plausible phrases 1-5 tokens into a robots audio channel, an adversary can trigger the models safety reasoning to halt or disrupt...

From Stateless Queries to Autonomous Actions: A Layered Security Framework for Agentic AI Systems

Agentic AI systems face security challenges that stateless large language models do not. They plan across extended horizons, maintain persistent memory, invoke external tools, and coordinate with peer agents. Existing security analyses organize threats by attack type prompt injection, jailbreakin...

Architecture Matters for Multi-Agent Security

Multi-agent systems MAS, composed of networks of two or more autonomous AI agents, have become increasingly popular in production deployments, yet introduce security risks that do not arise in single-agent settings. Even if individual agents exhibit robust security, architectural decisions...

ARIstoteles -- Dissecting Apple's Baseband Interface

Wireless chips and interfaces expose a substantial remote attack surface. As of today, most cellular baseband security research is performed on the Android ecosystem, leaving a huge gap on Apple devices. With iOS jailbreaks, last-generation wireless chips become fairly accessible for performance...

Ghost in the Agent: Redefining Information Flow Tracking for LLM Agents

Autonomous Large Language Model LLM agents are increasingly deployed to conduct complex tasks by interacting with external tools, APIs, and memory stores. However, processing untrusted external data exposes these agents to severe security threats, such as indirect prompt injection and unauthorize...

AsmRAG: LLM-Driven Malware Detection by Retrieving Functionally Similar Assembly Code

Deep learning malware detectors achieve high classification accuracy but suffer from severe interpretability limitations, typically returning probabilistic verdicts that lack forensic context. We introduce AsmRAG, a framework performing malware analysis through Assembly-Level Retrieval-Augmented...

Operationalising Information Security Management: A Procedural Framework Analysis of ISO/IEC 27001:2022 Implementation in a Financial-Technology Organisation

Organisations operating within information-intensive environments face intensifying pressure to formalise the governance of information security. The ISO/IEC 27001:2022 standard provides a globally recognised framework for establishing, implementing, maintaining, and continually improving an...

UNSEEN: A Cross-Stack LLM Unlearning Defense against AR-LLM Social Engineering Attacks

Emerging AR-LLM-based Social Engineering attack e.g., SEAR is at the edge of posing great threats to real-world social life. In such AR-LLM-SE attack, the attacker can leverage AR Augmented Reality glass to capture the image and vocal information of the target, using the LLM to identify the targe...

Evaluating Jailbreaking Vulnerabilities in LLMs Deployed As Assistants for Smart Grid Operations: A Benchmark against NERC Standards

The deployment of Large Language Models LLMs as assistants in electric grid operations promises to streamline compliance and decision-making but exposes new vulnerabilities to prompt-based adversarial attacks. This paper evaluates the risk of jailbreaking LLMs, i.e., circumventing safety alignmen...

Scalable and Verifiable Federated Learning for Cross-Institution Financial Fraud Detection

The global financial ecosystem confronts a critical asymmetry: while fraud syndicates operate as borderless, distributed networks, banking institutions remain constrained by regulatory data silos, limiting visibility into cross-institutional threat patterns under strict privacy laws such as GDPR...

Joern 4.0.527

Joern is the bug hunter's workbench. With this tool, you can uncover attack surface, sloppy coding practices, and variants of known vulnerabilities using an interactive code analysis shell. Joern supports C, C++, LLVM bitcode, x86 binaries via Ghidra, JVM bytecode via Soot, and Javascript...

Adversarial Co-Evolution of Malware and Detection Models: A Bilevel Optimization Perspective

Machine learning-based malware detectors are increasingly vulnerable to adversarial examples. Traditional defenses, such as one-shot adversarial training, often fail against adaptive attackers who use reinforcement learning to bypass detection. This paper proposes a robust defense framework based...

listmonk Admin Authentication / Password Flow Security Assessment Module

This Metasploit auxiliary module is a web application security testing tool designed to evaluate authentication and password management logic in a Listmonk admin panel deployment...

Apple Silicon Vulnerability Research — A18 Pro (MacBook Neo)

This is systematic security research targeting Apple's A18 Pro chip MacBook Neo / Mac17,5, the first A-series SoC shipped in a Mac laptop. The MacBook Neo is used as an authorized Apple Security Research Device SRD and doubles as a high-visibility proxy for iPhone 16 Pro research, since A18 Pro i...

Detecting Concept Drift in Evolving Malware Families Using Rule-Based Classifier Representations

This work proposes a structural approach to concept drift detection in malware classification using decision tree rulesets. Classifiers are trained across temporal windows on the EMBER2024 dataset, and drift is quantified by comparing extracted rule representations using feature importance,...

The Security Cost of Intelligence: AI Capability, Cyber Risk, and Deployment Paradox

Firms are deploying more capable AI systems, but organizational controls often have not kept pace. These systems can generate greater productivity gains, but high-value uses require broader authority exposure -- data access, workflow integration, and delegated authority -- when governance control...

GNU Privacy Guard 2.5.19

GnuPG the GNU Privacy Guard or GPG is GNU's tool for secure communication and data storage. It can be used to encrypt data and to create digital signatures. It includes an advanced key management facility and is compliant with the proposed OpenPGP Internet standard as described in RFC2440. As suc...

NLTK Simple Random Input Fuzzer for Function Testing

This script is a basic fuzzing tool that generates random inputs strings containing letters, numbers, and special characters and feeds them into a target function to test its stability. It runs multiple iterations, monitors for exceptions or crashes, and counts how many errors occur during...

MetInfo CMS 8.1 WeChat Module Vulnerability Detection Scanner

This Metasploit auxiliary module is a non-exploit vulnerability detection scanner designed to assess potential security weaknesses in the MetInfo CMS WeChat module, specifically related to weixinreply.class.php handling logic...

Automation-Exploit: A Multi-Agent LLM Framework for Adaptive Offensive Security with Digital Twin-Based Risk-Mitigated Exploitation

The offensive security landscape is highly fragmented: enterprise platforms avoid memory-corruption vulnerabilities due to Denial of Service DoS risks, Automatic Exploit Generation AEG systems suffer from semantic blindness, and Large Language Model LLM agents face safety alignment filters and...

Libgcrypt 1.12.2

Libgcrypt is a general-purpose cryptographic library based on the code from GnuPG. It provides functions for all cryptographic building blocks: symmetric ciphers AES, DES, Blowfish, CAST5, Twofish, and Arcfour, hash algorithms MD4, MD5, RIPE-MD160, SHA-1, and TIGER-192, MACs HMAC for all hash...

Rosemary 1.0.4

Rosemary is a cross-platform transparent tunneling platform designed for network pivoting. Unlike traditional tools that rely on TUN/TAP interfaces or require per-application proxy configuration like proxychains, Rosemary intercepts traffic at the kernel level...

Self-Supervised Learning for Android Malware Detection on a Time-Stamped Dataset

Android malware detectors built with machine learning often suffer from temporal bias: models are trained and evaluated without respecting apps' actual release times, inflating accuracy and weakening real-world robustness. We address this by constructing a time-stamped dataset of benign and...

Training a General Purpose Automated Red Teaming Model

Automated methods for red teaming LLMs are an important tool to identify LLM vulnerabilities that may not be covered in static benchmarks, allowing for more thorough probing. They can also adapt to each specific LLM to discover weaknesses unique to it. Most current automated red teaming methods a...

Grav CMS Authenticated Scanner

This Python script is a safe, read-only scanner designed to detect whether a target running Grav CMS with its Admin plugin may be vulnerable to CVE-2025-50286, based purely on version analysis...

A-THENA: Early Intrusion Detection for IoT with Time-Aware Hybrid Encoding and Network-Specific Augmentation

The proliferation of Internet of Things IoT devices has significantly expanded attack surfaces, making IoT ecosystems particularly susceptible to sophisticated cyber threats. To address this challenge, this work introduces A-THENA, a lightweight early intrusion detection system EIDS that...

Strategic Heterogeneous Multi-Agent Architecture for Cost-Effective Code Vulnerability Detection

Automated code vulnerability detection is critical for software security, yet existing approaches face a fundamental trade-off between detection accuracy and computational cost. We propose a heterogeneous multi-agent architecture inspired by game-theoretic principles, combining cloud-based LLM...

ID-Eraser: Proactive Defense against Face Swapping Via Identity Perturbation

Deepfake technologies have rapidly advanced with modern generative AI, and face swapping in particular poses serious threats to privacy and digital security. Existing proactive defenses mostly rely on pixel-level perturbations, which are ineffective against contemporary swapping models that extra...

Keras 3.13.0 Safe Parallel ML Stress Test Generator

This script is a safe and lightweight stress-testing utility designed to simulate machine learning model generation workloads without actually allocating large memory or creating real heavy files. It was designed to test Keras 3.13.0...

MCP Pitfall Lab: Exposing Developer Pitfalls in MCP Tool Server Security under Multi-Vector Attacks

Model Context Protocol MCP is increasingly adopted for tool-integrated LLM agents, but its multi-layer design and third-party server ecosystem expand risks across tool metadata, untrusted outputs, cross-tool flows, multimodal inputs, and supply-chain vectors. Existing MCP benchmarks largely measu...

Keras 3.13.0 HDF5 Shape Fuzzing for Robustness Testing

This script performs fuzz testing against Keras version 3.13.0 on randomly generated tensor shapes using NumPy and HDF5 to evaluate stability and error handling in file creation workflows...

Joern 4.0.526

Joern is the bug hunter's workbench. With this tool, you can uncover attack surface, sloppy coding practices, and variants of known vulnerabilities using an interactive code analysis shell. Joern supports C, C++, LLVM bitcode, x86 binaries via Ghidra, JVM bytecode via Soot, and Javascript...

A Sociotechnical, Practitioner-Centered Approach to Technology Adoption in Cybersecurity Operations: An LLM Case

Technology for security operations centers SOCs has a storied history of slow adoption due to concerns about trust and reliability. These concerns are amplified with artificial intelligence, particularly large language models LLMs, which exhibit issues such as hallucinations and inconsistent...