Empowering IoT Security: On-Device Intrusion Detection in Resource Constrained Devices

IoT devices particularly microcontrollers are challenged by their inherent limitations in processing capabilities, memory capacity, and energy conservation. Securing communication within IoT networks is further complicated by the heterogeneity of devices and the myriad of potential security...

Security-Aware Planning and Control of Multi-Agent Systems with LTL Tasks

This paper presents a secure-by-construction planning and control framework for multi-agent systems subject to linear temporal logic LTL specifications. The framework protects sensitive information from a passive intruder with partial observations of the agents' motion. Security in multi-agent...

Identifying AI Web Scrapers Using Canary Tokens

From pre-training to query-time augmentation, web-scraped data helps to improve the quality and contextual relevancy of content generated by large language models LLMs. However, large-scale web scraping to feed LLMs can affect site stability and raise legal, privacy, or ethics concerns. If websit...

Characterizing AI-Assisted Bot Traffic in Darknet Data: Implications for ICS and IIoT Security

The rise of automated scanning tools and AI assisted reconnaissance agents has significantly altered internet background traffic patterns, threatening the baseline assumptions underlying intrusion detection systems IDS deployed in critical infrastructure networks. This paper characterizes the...

Context-Aware Web Attack Detection in Open-Source SIEM Systems Via MITRE ATT&CK-Enriched Behavioral Profiling

Security Information and Event Management SIEM systems aggregate log data from heterogeneous sources to detect coordinated attacks. Traditional rule-based correlation engines struggle to classify multi-step web application attacks because they examine each event without reference to the behaviour...

Backdoor Channels Hidden in Latent Space: Cryptographic Undetectability in Modern Neural Networks

Recent cryptographic results establish that neural networks can be backdoored such that no efficient algorithm can distinguish them from a clean model. These guarantees, however, have been confined to stylised architectures of limited practical relevance, leaving open whether comparable...

Red-Teaming Agent Execution Contexts: Open-World Security Evaluation on OpenClaw

Agentic language-model systems increasingly rely on mutable execution contexts, including files, memory, tools, skills, and auxiliary artifacts, creating security risks beyond explicit user prompts. This paper presents DeepTrap, an automated framework for discovering contextual vulnerabilities in...

ExploitBench: A Capability Ladder Benchmark for LLM Cybersecurity Agents

Exploitation is not a binary event. It is a ladder of acquiring progressive capabilities, from executing a single buggy line of code to taking full control of the target. However, existing LLM security benchmarks treat a crash as exploitation success. That single binary outcome collapses the hard...

Memory Forensics Techniques for Automated Detection and Analysis of Go Malware

The Go programming language has become increasingly popular among malware developers due to its ability to produce statically linked, cross-platform executables that challenge traditional analysis techniques. These binaries embed a substantial runtime and compiler-generated metadata and are...

DCVD: Dual-Channel Cross-Modal Fusion for Joint Vulnerability Detection and Localization

Software vulnerability detection plays a critical role in ensuring system security, where real-world auditing requires not only determining whether a function is vulnerable but also pinpointing the specific lines responsible. However, existing approaches either rely on a single information source...

GNU Privacy Guard 2.5.20

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...

Joern 4.0.538

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...

angr 9.2.215

angr is an open-source binary analysis platform for Python. It combines both static and dynamic symbolic "concolic" analysis, providing tools to solve a variety of tasks...

Security Incentivization: An Empirical Study of How Micropayments Impact Code Security

Security often receives insufficient developer attention because it does not directly generate visible value, leading to underinvestment in practice. We evaluate a countermeasure by team-level incentives tied to measurable security improvements over time. Our semi-automated mechanism aggregates...

Numerical Security Analysis for Practical Quantum Key Distribution

Quantum key distribution QKD promises information-theoretic security based on quantum mechanics and idealized device models. Practical implementations, however, deviate from these models due to unavoidable device imperfections, and existing security proofs fall short of capturing the complexity o...

Backdoor Threats in Variational Quantum Circuits: Taxonomy, Attacks, and Defenses

Variational quantum algorithms VQAs are a central paradigm for noisy intermediate-scale NISQ quantum computing, yet their reliance on predesigned and pretrained variational quantum circuits VQCs introduces critical security vulnerabilities, particularly backdoor attacks. These attacks embed hidde...

Insecure Despite Proven Updated: Extracting the Root VCEK Seed on EPYC Milan Via a Software-Only Attack

In the official whitepaper of Secure Encrypted Virtualization with Secure Nested Paging SEV-SNP, AMD explicitly emphasizes the capability to prevent Trusted Computing Base TCB rollback attacks. Cryptographically, this is realized by signing attestation reports with the Versioned Chip Endorsement...

Proteus: A Self-Evolving Red Team for Agent Skill Ecosystems

Agent skills extend LLM agents with reusable instructions, tool interfaces, and executable code, and users increasingly install third-party skills from marketplaces, repositories, and community channels. Because a skill exposes both executable behavior and context-setting documentation, its...

From Controlled to the Wild: Evaluation of Pentesting Agents for the Real-World

AI pentesting agents are increasingly credible as offensive security systems, but current benchmarks still provide limited guidance on which will perform best in real-world targets. Existing evaluation protocols assess and optimize for predefined goals such as capture-the-flag, remote code...

Joern 4.0.537

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...

Do Androids Dream of Breaking the Game? Systematically Auditing AI Agent Benchmarks with BenchJack

Agent benchmarks have become the de facto measure of frontier AI competence, guiding model selection, investment, and deployment. However, reward hacking, where agents maximize a score without performing the intended task, emerges spontaneously in frontier models without overfitting. We argue tha...

Iterative Audit Convergence in LLM-Managed Multi-Agent Systems: A Case Study in Prompt Engineering Quality Assurance

Prompt specifications for multi-agent large language model LLM systems carry data contracts and integration logic across many interdependent files but are rarely subjected to structured-inspection rigor. This paper reports a single-system empirical case study of iterative, agent-driven auditing...

Do Skill Descriptions Tell the Truth? Detecting Undisclosed Security Behaviors in Code-Backed LLM Skills

Programmatic skills in LLM ecosystems consist of a natural-language description and executable implementation files. Users and LLMs rely on the description to understand the skill's scope. However, the implementation may perform security-relevant operations, such as credential access, network...

Convolutional-Neural-Networks for Deanonymisation of I2P Traffic

This study investigates the potential for deanonymizing services within the Invisible Internet Project I2P network through passive traffic analysis and machine learning techniques. The primary objective is to identify distinctive patterns in I2P traffic despite the encryption of its payload. To...

Reconstruction of Personally Identifiable Information from Supervised Finetuned Models

Supervised Finetuning SFT has become one of the primary methods for adapting a large language model LLM with extensive pre-trained knowledge to domain-specific, instruction-following tasks. SFT datasets, composed of instruction-response pairs, often include user-provided information that may...

SkillSafetyBench: Evaluating Agent Safety under Skill-Facing Attack Surfaces

Reusable skills are becoming a common interface for extending large language model agents, packaging procedural guidance with access to files, tools, memory, and execution environments. However, this modularity introduces attack surfaces that are largely missed by existing safety evaluations: eve...

Secure (Multiple) Key-Cast over Networks: Multiple Eavesdropping Nodes

We study the secure multiple key-cast problem over noiseless networks under node-based eavesdroppers, where one or more source nodes participate in the generation of distinct secret keys to be shared among designated terminal subsets, while an eavesdropper observing up to $\ell$ nodes, including...

VulTriage: Triple-Path Context Augmentation for LLM-Based Vulnerability Detection

Automated vulnerability detection is a fundamental task in software security, yet existing learning-based methods still struggle to capture the structural dependencies, domain-specific vulnerability knowledge, and complex program semantics required for accurate detection. Recent Large Language...

Behavioral Integrity Verification for AI Agent Skills

Agent skills extend LLM agents with privileged third-party capabilities such as filesystem access, credentials, network calls, and shell execution. Existing safety work catches malicious prompts and risky runtime actions, but the skill artifact itself goes unverified. We formalize this as the...

CTFusion: A CTF-Based Benchmark for LLM Agent Evaluation

Recent advances in Large Language Models LLMs have enabled agentic systems for complex, multi-step tasks; cybersecurity is emerging as a prominent application. To evaluate such agents, researchers widely adopt Capture The Flag CTF benchmarks. However, current CTF benchmarks reuse existing...

Five Attacks on X402 Agentic Payment Protocol

The x402 protocol revives the HTTP 402 Payment Required status code to enable web-native micropayments across APIs, content, and agents. It combines synchronous HTTP authorization with asynchronous blockchain settlement and introduces a cross-layer attack surface absent from conventional web and...

FreeMOCA: Memory-Free Continual Learning for Malicious Code Analysis

As over 200 million new malware samples are identified each year, antivirus systems must continuously adapt to the evolving threat landscape. However, retraining solely on new samples leads to catastrophic forgetting and exploitable blind spots, while retraining on the entire dataset incurs...

IPI-Proxy: An Intercepting Proxy for Red-Teaming Web-Browsing AI Agents against Indirect Prompt Injection

Web-browsing AI agents are increasingly deployed in enterprise settings under strict whitelists of approved domains, yet adversaries can still influence them by embedding hidden instructions in the HTML pages those domains serve. Existing red-teaming resources fall short of this scenario:...

Still Camouflage, Moving Illusion: View-Induced Trajectory Manipulation in Autonomous Driving

Existing physical adversarial attacks on vision-based autonomous driving induce time-evolving perception errors, including biased object tracking or trajectory prediction, through i sophisticated physical patch inducing detection box drift when entering the view distance, or ii dynamically changi...

Attacks and Mitigations for Distributed Governance of Agentic AI under Byzantine Adversaries

Agentic AI governance is a critical component of agentic AI infrastructure ensuring that agents follow their owner's communication and interaction policies, and providing protection against attacks from malicious agents. The state-of-the-art solution, SAGA, assumes a logically centralized point o...

When LLMs Team Up: A Coordinated Attack Framework for Automated Cyber Intrusions

Automated intrusion-style workflows require LLM agents to reason over partial observations, tool outputs, and executable artifacts under bounded budgets. A single LLM instance often compresses evidence extraction, planning, execution, and validation into one context, which increases the risk of...

Security of Decoy-State Quantum Key Distribution with Correlated Bit-And-Basis Encoders

Practical quantum key distribution QKD modulators inevitably introduce correlations, causing the state emitted in a given round to depend on the setting choices made in previous rounds. These correlations break the round-by-round independence structure on which many widely used security proof...

Windows/x86 (XP SP3) (English) calc.exe Shellcode

15 bytes small Windows/x86 XP SP3 English calc.exe shellcode...

Can a Single Message Paralyze the AI Infrastructure? the Rise of AbO-DDoS Attacks through Targeted Mobius Injection

Large Language Model LLM agents have emerged as key intermediaries, orchestrating complex interactions between human users and a wide range of digital services and LLM infrastructures. While prior research has extensively examined the security of LLMs and agents in isolation, the systemic risk of...

Under the Hood of SKILL.Md: Semantic Supply-Chain Attacks on AI Agent Skill Registry

Autonomous AI agents increasingly extend their capabilities through Agent Skills: modular filesystem packages whose SKILL.md files describe when and how agents should use them. While this design enables scalable, on-demand capability expansion, it also introduces a semantic supply-chain risk in...

Comment and Control: Hijacking Agentic Workflows Via Context-Grounded Evolution

Automation platforms such as GitHub Actions and n8n are increasingly adopting so-called agentic workflows, which integrate Large Language Model LLM agents for tasks such as code review and data synchronization. While bringing convenience for developers, this integration exposes a new risk: An...

Cybercrime and Prevention: Colonel Blotto in Social Engineering

Cybercriminals increasingly target the human factor rather than continuously advancing technological defense mechanisms. Consequently, institutions that allocate substantial resources to strengthening their cybersecurity infrastructure may remain vulnerable if a deceived employee voluntarily...

Context-Aware Spear Phishing: Generative AI-Enabled Attacks against Individuals Via Public Social Media Data

We demonstrate how publicly available social-media data and generative AI GenAI can be misused to automate and scale highly personalized, context-aware spear-phishing campaigns. With minimal attacker effort, a small amount of public activity per target is sufficient for GenAI models to extract...

GhostLock: SMB Deny-Share Handles As a Zero-Privilege Availability Weapon

GhostLock demonstrates that a low-privileged Windows domain user with standard read access to an SMB share can produce ransomware-equivalent organizational availability impact with zero writes, zero encryption, and zero signals in every behavioral defense the modern enterprise security stack...

A Systematic Security Testing Approach for InterUSS-Based Environments

Unmanned Traffic Management UTM federated ecosystems, such as InterUSS, enable secure coordination among UAS Service Suppliers USSs. However, they bring up some security challenges at the infrastructure level that haven't been fully explored. This paper presents a security testing approach for...

xpath 1.0.0

xpath is a multi-technique XPath injection scanner written entirely in Nim with no external dependencies. It's a single static binary that handles error-based, boolean blind, time-based blind, union injection, and authentication bypass detection, plus data extraction once injection is confirmed. ...

OSK ATBroker Registry Security Scanner

This program is a defensive Windows security scanner designed to inspect registry locations related to On-Screen Keyboard osk.exe and Accessibility/ATBroker configuration, which are sometimes abused in privilege escalation or persistence attacks...

Windows Registry Privilege Escalation Scanner / Audit Tool

This PowerShell script is a defensive security auditing tool designed to inspect Windows registry areas commonly associated with privilege escalation EoP techniques and system misconfigurations...

Can You Keep a Secret? Involuntary Information Leakage in Language Model Writing

Language models are deployed in settings that require compartmentalization: system prompts should not be disclosed, chain-of-thought reasoning is hidden from users, and sensitive data passes through shared contexts. We test whether models can keep prompted information out of their writing. We giv...

LLMs for Secure Hardware Design and Related Problems: Opportunities and Challenges

The integration of Large Language Models LLMs into Electronic Design Automation EDA and hardware security is rapidly reshaping the semiconductor industry. While LLMs offer unprecedented capabilities in generating Register Transfer Level RTL code, automating testbenches, and bridging the semantic...