Broken by Default: A Formal Verification Study of Security Vulnerabilities in AI-Generated Code

AI coding assistants are now used to generate production code in security-sensitive domains, yet the exploitability of their outputs remains unquantified. We address this gap with Broken by Default: a formal verification study of 3,500 code artifacts generated by seven frontier LLMs across 500...

Digital Privacy in IoT: Exploring Challenges, Approaches and Open Issues

Privacy has always been a critical issue in the digital era, particularly with the increasing use of Internet of Things IoT devices. As the IoT continues to transform industries such as healthcare, smart cities, and home automation, it has also introduced serious challenges regarding the security...

Evaluating Future Air Traffic Management Security

The L-Band Digital Aviation Communication System LDACS aims to modernize communications between the aircraft and the tower. Besides digitizing this type of communication, the contributors also focus on protecting them against cyberattacks. There are several proposals regarding LDACS security, and...

NetSecBed: A Container-Native Testbed for Reproducible Cybersecurity Experimentation

Cybersecurity research increasingly depends on reproducible evidence, such as traffic traces, logs, and labeled datasets, yet most public datasets remain static and offer limited support for controlled re-execution and traceability, especially in heterogeneous multi-protocol environments. This...

Invisible Adversaries: A Systematic Study of Session Manipulation Attacks on VPNs

Virtual Private Networks VPNs are widely used for censorship evasion and traffic protection. VPN users expect to be provided with adequate security protection, and at the same time not be affected by other users connected to the same VPN server, which can be illustrated as the non-interference...

Merkle Tree Certificate Post-Quantum PKI for Kubernetes and Cloud-Native 5G/B5G Core

Post-quantum signature schemes such as ML-DSA-65 produce signatures of 3,309 bytes and public keys of 1,952 bytes over 50 times larger than classical Ed25519. In TLS-authenticated environments like Kubernetes control planes and 5G Core networks, where every inter-component connection is mutually...

Towards Unveiling Vulnerabilities of Large Reasoning Models in Machine Unlearning

Large language models LLMs possess strong semantic understanding, driving significant progress in data mining applications. This is further enhanced by large reasoning models LRMs, which provide explicit multi-step reasoning traces. On the other hand, the growing need for the right to be forgotte...

CoopGuard: Stateful Cooperative Agents Safeguarding LLMs against Evolving Multi-Round Attacks

As Large Language Models LLMs are increasingly deployed in complex applications, their vulnerability to adversarial attacks raises urgent safety concerns, especially those evolving over multi-round interactions. Existing defenses are largely reactive and struggle to adapt as adversaries refine...

Semantics over Syntax: Uncovering Pre-Authentication 5G Baseband Vulnerabilities

Modern 5G user equipment UE processes Radio Resource Control RRC configuration messages during early control-plane exchanges, before authentication and integrity protection are established. Prior work for testing 5G UEs has largely focused on constructing syntactically invalid inputs. In contrast...

LLM-Enabled Open-Source Systems in the Wild: An Empirical Study of Vulnerabilities in GitHub Security Advisories

Large language models LLMs are increasingly embedded in open-source software OSS ecosystems, creating complex interactions among natural language prompts, probabilistic model outputs, and execution-capable components. However, it remains unclear whether traditional vulnerability disclosure...

Triggering and Detecting Exploitable Library Vulnerability from the Client by Directed Greybox Fuzzing

Developers utilize third-party libraries to improve productivity, which also introduces potential security risks. Existing approaches generate tests for public functions to trigger library vulnerabilities from client programs, yet they depend on proof-of-concepts PoCs, which are often unavailable...

Beamforming Feedback As a Novel Attack Surface for Wi-Fi Physical-Layer Security

With the rapid evolution of wireless technologies, Wi-Fi has expanded beyond its original role in data transmission to support various emerging applications, particularly in physical-layer security, including device authentication, user authentication, and secret key generation. Despite extensive...

SkillAttack: Automated Red Teaming of Agent Skills through Attack Path Refinement

LLM-based agent systems increasingly rely on agent skills sourced from open registries to extend their capabilities, yet the openness of such ecosystems makes skills difficult to thoroughly vet. Existing attacks rely on injecting malicious instructions into skills, making them easily detectable b...

Defending Buffer Overflows in WebAssembly: A Transpiler Approach

WebAssembly is quickly becoming a popular compilation target for a variety of code. However, vulnerabilities in the source languages translate to vulnerabilities in the WebAssembly binaries. This work proposes a methodology and a WebAssembly transpiler to prevent buffer overflows in the unmanaged...

Perceptual Gaps: ASCII Art and Overlapping Audio As CAPTCHA

As multimodal large language models LLMs advance, traditional CAPTCHAs have become obsolete at distinguishing humans from bots. To address this shift, this paper aims to investigate the possibility of using tasks for which humans have evolved highly specialised neural processing. We introduce two...

Explainability-Guided Adversarial Attacks on Transformer-Based Malware Detectors Using Control Flow Graphs

Transformer-based malware detection systems operating on graph modalities such as control flow graphs CFGs achieve strong performance by modeling structural relationships in program behavior. However, their robustness to adversarial evasion attacks remains underexplored. This paper examines the...

Improving ML Attacks on LWE with Data Repetition and Stepwise Regression

The Learning with Errors LWE problem is a hard math problem in lattice-based cryptography. In the simplest case of binary secrets, it is the subset sum problem, with error. Effective ML attacks on LWE were demonstrated in the case of binary, ternary, and small secrets, succeeding on fairly sparse...

Towards Predicting Multi-Vulnerability Attack Chains in Software Supply Chains from Software Bill of Materials Graphs

Software supply chain security compromises often stem from cascaded interactions of vulnerabilities, for example, between multiple vulnerable components. Yet, Software Bill of Materials SBOM-based pipelines for security analysis typically treat scanner findings as independent per-CVE Common...

AttackEval: A Systematic Empirical Study of Prompt Injection Attack Effectiveness against Large Language Models

Prompt injection has emerged as a critical vulnerability in large language model LLM deployments, yet existing research is heavily weighted toward defenses. The attack side -- specifically, which injection strategies are most effective and why -- remains insufficiently studied.We address this gap...

SecPI: Secure Code Generation with Reasoning Models Via Security Reasoning Internalization

Reasoning language models RLMs are increasingly used in programming. Yet, even state-of-the-art RLMs frequently introduce critical security vulnerabilities in generated code. Prior training-based approaches for secure code generation face a critical limitation that prevents their direct applicati...

Your Agent Is More Brittle Than You Think: Uncovering Indirect Injection Vulnerabilities in Agentic LLMs

The rapid deployment of open-source frameworks has significantly advanced the development of modern multi-agent systems. However, expanded action spaces, including uncontrolled privilege exposure and hidden inter-system interactions, pose severe security challenges. Specifically, Indirect Prompt...

Measuring the Permission Gate: A Stress-Test Evaluation of Claude Code's Auto Mode

Claude Code's auto mode is the first deployed permission system for AI coding agents, using a two-stage transcript classifier to gate dangerous tool calls. Anthropic reports a 0.4% false positive rate and 17% false negative rate on production traffic. We present the first independent evaluation o...

Explainable PQC: A Layered Interpretive Framework for Post-Quantum Cryptographic Security Assumptions

This paper studies how post-quantum cryptographic PQC security assumptions can be represented and communicated through a structured, layered framework that is useful for technical interpretation but does not replace formal cryptographic proofs. We propose "Explainable PQC,'' an interdisciplinary...

Automating Cloud Security and Forensics through a Secure-By-Design Generative AI Framework

As cloud environments become increasingly complex, cybersecurity and forensic investigations must evolve to meet emerging threats. Large Language Models LLMs have shown promise in automating log analysis and reasoning tasks, yet they remain vulnerable to prompt injection attacks and lack forensic...

ContractShield: Bridging Semantic-Structural Gaps Via Hierarchical Cross-Modal Fusion for Multi-Label Vulnerability Detection in Obfuscated Smart Contracts

Smart contracts are increasingly targeted by adversaries employing obfuscation techniques such as bogus code injection and control flow manipulation to evade vulnerability detection. Existing multimodal methods often process semantic, temporal, and structural features in isolation and fuse them...

Vienna Assistant 1.2.542 Local Privilege Escalation

Vienna Assistant MacOS version 1.2.542 suffers from a missing validation vulnerability that allows for privilege escalation...

Towards Secure Agent Skills: Architecture, Threat Taxonomy, and Security Analysis

Agent Skills is an emerging open standard that defines a modular, filesystem-based packaging format enabling LLM-based agents to acquire domain-specific expertise on demand. Despite rapid adoption across multiple agentic platforms and the emergence of large community marketplaces, the security...

A Tsetlin Machine-Driven Intrusion Detection System for Next-Generation IoMT Security

The rapid adoption of the Internet of Medical Things IoMT is transforming healthcare by enabling seamless connectivity among medical devices, systems, and services. However, it also introduces serious cybersecurity and patient safety concerns as attackers increasingly exploit new methods and...

Credential Leakage in LLM Agent Skills: A Large-Scale Empirical Study

Third-party skills extend LLM agents with powerful capabilities but often handle sensitive credentials in privileged environments, making leakage risks poorly understood. We present the first large-scale empirical study of this problem, analyzing 17,022 skills sampled from 170,226 on SkillsMP usi...

Apple Live Caller ID Privacy Concerns

Apple's oblivious HTTP relay for Live Caller ID Lookup iOS 18+ routes traffic through 14 third-party endpoints across six countries. These include an anonymous Delaware LLC sharing data with OpenAI, a Russian endpoint Yandex, and a Swiss GmbH whose privacy policy names "The Legal Entity to be...

A Systematic Security Evaluation of OpenClaw and Its Variants

Tool-augmented AI agents substantially extend the practical capabilities of large language models, but they also introduce security risks that cannot be identified through model-only evaluation. In this paper, we present a systematic security assessment of six representative OpenClaw-series agent...

OWASP CRS Arbitrary File Upload

A vulnerability was identified in OWASP CRS where whitespace padding in filenames can bypass file upload extension checks, allowing uploads of dangerous files such as .php, .phar, .jsp, and .jspx. This has been addressed in versions 3.3.9, 4.25.x LTS, and 4.8.x...

Supply-Chain Poisoning Attacks against LLM Coding Agent Skill Ecosystems

LLM-based coding agents extend their capabilities via third-party agent skills distributed through open marketplaces without mandatory security review. Unlike traditional packages, these skills are executed as operational directives with system-level privileges, so a single malicious skill can...

ML Defender (ARGus NDR): An Open-Source Embedded ML NIDS for Botnet and Anomalous Traffic Detection in Resource-Constrained Organizations

Ransomware and DDoS attacks disproportionately impact hospitals, schools, and small organizations that cannot afford enterprise security solutions. We present ML Defender aRGus NDR, an open-source network intrusion detection system built in C++20, deployable on commodity hardware at approximately...

RuleForge: Automated Generation and Validation for Web Vulnerability Detection at Scale

Security teams face a challenge: the volume of newly disclosed Common Vulnerabilities and Exposures CVEs far exceeds the capacity to manually develop detection mechanisms. In 2025, the National Vulnerability Database published over 48,000 new vulnerabilities, motivating the need for automation. W...

Poison Once, Exploit Forever: Environment-Injected Memory Poisoning Attacks on Web Agents

Memory makes LLM-based web agents personalized, powerful, yet exploitable. By storing past interactions to personalize future tasks, agents inadvertently create a persistent attack surface that spans websites and sessions. While existing security research on memory assumes attackers can directly...

Windows Persistence Via UserInitMprLogonScript

This Metasploit module establishes persistence by setting the UserInitMprLogonScript value in HKCU\Environment. During user logon, userinit.exe checks this value and executes the specified command or binary. The module writes a payload executable to disk and points UserInitMprLogonScript to that...

Seclens: Role-Specific Evaluation of LLM'S for Security Vulnerablity Detection

Existing benchmarks for LLM-based vulnerability detection compress model performance into a single metric, which fails to reflect the distinct priorities of different stakeholders. For example, a CISO may emphasize high recall of critical vulnerabilities, an engineering leader may prioritize...

Architectural Implications of the UK Cyber Security and Resilience Bill

The UK Cyber Security and Resilience CS&R Bill represents the most significant reform of UK cyber legislation since the Network and Information Systems NIS Regulations 2018. While existing analysis has addressed the Bill's regulatory requirements, there is a critical gap in guidance on the...

python-ecdsa Denial of Service

python-ecdsa suffers from a denial of service vulnerability...

AgentWatcher: A Rule-Based Prompt Injection Monitor

Large language models LLMs and their applications, such as agents, are highly vulnerable to prompt injection attacks. State-of-the-art prompt injection detection methods have the following limitations: 1 their effectiveness degrades significantly as context length increases, and 2 they lack...

Automated Malware Family Classification Using Weighted Hierarchical Ensembles of Large Language Models

Malware family classification remains a challenging task in automated malware analysis, particularly in real-world settings characterized by obfuscation, packing, and rapidly evolving threats. Existing machine learning and deep learning approaches typically depend on labeled datasets, handcrafted...

Design and Implementation of an Open-Source Security Framework for Cloud Infrastructure

Misconfiguration, excessive privilege, and tool fragmentation remain the main reasons why enterprise cloud environments are breached. Recent reports on cloud-native application protection note that most incidents can be traced back to configuration or identity errors rather than platform flaws, a...

From Component Manipulation to System Compromise: Understanding and Detecting Malicious MCP Servers

The model context protocol MCP standardizes how LLMs connect to external tools and data sources, enabling faster integration but introducing new attack vectors. Despite the growing adoption of MCP, existing MCP security studies classify attacks by their observable effects, obscuring how attacks...

AEGIS: Adversarial Entropy-Guided Immune System -- Thermodynamic State Space Models for Zero-Day Network Evasion Detection

As TLS 1.3 encryption limits traditional Deep Packet Inspection DPI, the security community has pivoted to Euclidean Transformer-based classifiers e.g., ET-BERT for encrypted traffic analysis. However, these models remain vulnerable to byte-level adversarial morphing -- recent pre-padding attacks...

WPProbe Plugin Enumeration Tool 0.11.4

A fast WordPress plugin and theme scanner that detects installed plugins via REST API enumeration and themes from HTML discovery, then maps them to known vulnerabilities. Over 5,000 plugins detectable without brute-force, thousands more with it...

Combating Data Laundering in LLM Training

Data rights owners can detect unauthorized data use in large language model LLM training by querying with proprietary samples. Often, superior performance e.g., higher confidence or lower loss on a sample relative to the untrained data implies it was part of the training corpus, as LLMs tend to...

The Quantum-Cryptographic Co-Evolution

As quantum computing matures toward the realization of Cryptographically Relevant Quantum Computers CRQC, global cryptographic infrastructure faces an existential threat. This paper introduces a two-dimensional coordinate system to map the co-evolution of cryptographic resilience x-axis and...

WhatWeb Scanner 0.6.4

WhatWeb is a next-generation web scanner. WhatWeb recognizes web technologies including content management systems CMS, blogging platforms, statistic/analytics packages, JavaScript libraries, web servers, and embedded devices. WhatWeb has over 1800 plugins, each to recognize something different...

Street-Legal Physical-World Adversarial Rim for License Plates

Automatic license plate reader ALPR systems are widely deployed to identify and track vehicles. While prior work has demonstrated vulnerabilities in ALPR systems, far less attention has been paid to their legality and physical-world practicality. We investigate whether low-resourced threat actors...