StealthRL: Reinforcement Learning Paraphrase Attacks for Multi-Detector Evasion of AI-Text Detectors

AI-text detectors face a critical robustness challenge: adversarial paraphrasing attacks that preserve semantics while evading detection. We introduce StealthRL, a reinforcement learning framework that stress-tests detector robustness under realistic adversarial conditions. StealthRL trains a...

SoK: The Pitfalls of Deep Reinforcement Learning for Cybersecurity

Deep Reinforcement Learning DRL has achieved remarkable success in domains requiring sequential decision-making, motivating its application to cybersecurity problems. However, transitioning DRL from laboratory simulations to bespoke cyber environments can introduce numerous issues. This is furthe...

Empirical Evaluation of SMOTE in Android Malware Detection with Machine Learning: Challenges and Performance in CICMalDroid 2020

Malware, malicious software designed to damage computer systems and perpetrate scams, is proliferating at an alarming rate, with thousands of new threats emerging daily. Android devices, prevalent in smartphones, smartwatches, tablets, and IoTs, represent a vast attack surface, making malware...

DyMA-Fuzz: Dynamic Direct Memory Access Abstraction for Re-Hosted Monolithic Firmware Fuzzing

The rise of smart devices in critical domains--including automotive, medical, industrial--demands robust firmware testing. Fuzzing firmware in re-hosted environments is a promising method for automated testing at scale, but remains difficult due to the tight coupling of code with a...

European Commission Cyber-Attack Response

On 30 January, the European Commission's central infrastructure managing mobile devices identified traces of a cyber-attack, which may have resulted in access to staff names and mobile numbers of some of its staff members. The Commission's swift response ensured the incident was contained and the...

MUZZLE: Adaptive Agentic Red-Teaming of Web Agents against Indirect Prompt Injection Attacks

Large language model LLM based web agents are increasingly deployed to automate complex online tasks by directly interacting with web sites and performing actions on users' behalf. While these agents offer powerful capabilities, their design exposes them to indirect prompt injection attacks...

One RNG to Rule Them All: How Randomness Becomes an Attack Vector in Machine Learning

Machine learning relies on randomness as a fundamental component in various steps such as data sampling, data augmentation, weight initialization, and optimization. Most machine learning frameworks use pseudorandom number generators as the source of randomness. However, variations in design choic...

Next-Gen CAPTCHAs: Leveraging the Cognitive Gap for Scalable and Diverse GUI-Agent Defense

The rapid evolution of GUI-enabled agents has rendered traditional CAPTCHAs obsolete. While previous benchmarks like OpenCaptchaWorld established a baseline for evaluating multimodal agents, recent advancements in reasoning-heavy models, such as Gemini3-Pro-High and GPT-5.2-Xhigh have effectively...

XMap: Fast Internet-Wide IPv4 and IPv6 Network Scanner

XMap is an open-source network scanner designed for performing fast Internet-wide IPv4 and IPv6 network research scanning. XMap was initially developed as the research artifact of a paper published at 2021 IEEE/IFIP International Conference on Dependable Systems and Networks DSN '21 and then made...

Framework for Integrating Zero Trust in Cloud-Based Endpoint Security for Critical Infrastructure

Cyber threats have become highly sophisticated, prompting a heightened concern for endpoint security, especially in critical infrastructure, to new heights. A security model, such as Zero Trust Architecture ZTA, is required to overcome this challenge. ZTA treats every access request as new and...

libssh 0.7.6 Advanced SSH Security Testing Tool

This is an advanced SSH security testing tool for libssh that provides robust session management, signal handling, safe memory management, and multiple operational modes while also checking banners to see if libssh is vulnerable to CVE-2018-10933...

Reverse Online Guessing Attacks on PAKE Protocols

Though not yet widely deployed, password-authenticated key exchange PAKE protocols have been the subject of several recent standardization efforts, partly because of their resistance against various guessing attacks, but also because they do not require a public-key infrastructure PKI, making the...

CIC-Trap4Phish: A Unified Multi-Format Dataset for Phishing and Quishing Attachment Detection

Phishing attacks represents one of the primary attack methods which is used by cyber attackers. In many cases, attackers use deceptive emails along with malicious attachments to trick users into giving away sensitive information or installing malware while compromising entire systems. The...

Exploring Semantic Labeling Strategies for Third-Party Cybersecurity Risk Assessment Questionnaires

Third-Party Risk Assessment TPRA is a core cybersecurity practice for evaluating suppliers against standards such as ISO/IEC 27001 and NIST. TPRA questionnaires are typically drawn from large repositories of security and compliance questions, yet tailoring assessments to organizational needs...

CyberExplorer: Benchmarking LLM Offensive Security Capabilities in a Real-World Attacking Simulation Environment

Real-world offensive security operations are inherently open-ended: attackers explore unknown attack surfaces, revise hypotheses under uncertainty, and operate without guaranteed success. Existing LLM-based offensive agent evaluations rely on closed-world settings with predefined goals and binary...

Evasion of IoT Malware Detection Via Dummy Code Injection

The Internet of Things IoT has revolutionized connectivity by linking billions of devices worldwide. However, this rapid expansion has also introduced severe security vulnerabilities, making IoT devices attractive targets for malware such as the Mirai botnet. Power side-channel analysis has...

Rethinking Latency Denial-Of-Service: Attacking the LLM Serving Framework, Not the Model

Large Language Models face an emerging and critical threat known as latency attacks. Because LLM inference is inherently expensive, even modest slowdowns can translate into substantial operating costs and severe availability risks. Recently, a growing body of research has focused on algorithmic...

RECUR: Resource Exhaustion Attack Via Recursive-Entropy Guided Counterfactual Utilization and Reflection

Large Reasoning Models LRMs employ reasoning to address complex tasks. Such explicit reasoning requires extended context lengths, resulting in substantially higher resource consumption. Prior work has shown that adversarially crafted inputs can trigger redundant reasoning processes, exposing LRMs...

MemPot: Defending against Memory Extraction Attack with Optimized Honeypots

Large Language Model LLM-based agents employ external and internal memory systems to handle complex, goal-oriented tasks, yet this exposes them to severe extraction attacks, and effective defenses remain lacking. In this paper, we propose MemPot, the first theoretically verified defense framework...

AirCatch: Effectively Tracing Advanced Tag-Based Trackers

Tag-based tracking ecosystems help users locate lost items, but can be leveraged for unwanted tracking and stalking. Existing protocol-driven defenses and prior academic solutions largely assume stable identifiers or predictable beaconing. However, identifier-based defenses fundamentally break do...

Aegis: Towards Governance, Integrity, and Security of AI Voice Agents

With the rapid advancement and adoption of Audio Large Language Models ALLMs, voice agents are now being deployed in high-stakes domains such as banking, customer service, and IT support. However, their vulnerabilities to adversarial misuse still remain unexplored. While prior work has examined...

SoK: DARPA'S AI Cyber Challenge (AIxCC): Competition Design, Architectures, and Lessons Learned

DARPA's AI Cyber Challenge AIxCC, 2023--2025 is the largest competition to date for building fully autonomous cyber reasoning systems CRSs that leverage recent advances in AI -- particularly large language models LLMs -- to discover and remediate vulnerabilities in real-world open-source software...

Empirical Analysis of Adversarial Robustness and Explainability Drift in Cybersecurity Classifiers

Machine learning ML models are increasingly deployed in cybersecurity applications such as phishing detection and network intrusion prevention. However, these models remain vulnerable to adversarial perturbations small, deliberate input modifications that can degrade detection accuracy and...

Jamming Attacks on the Random Access Channel in 5G and B5G Networks

Random Access Channel RACH jamming poses a critical security threat to 5G and beyond B5G networks. This paper presents an analytical model for predicting the impact of Msg1 jamming attacks on RACH performance. We use the OpenAirInterface OAI open-source user equipment UE to implement a Msg1 jammi...

Beyond Function-Level Analysis: Context-Aware Reasoning for Inter-Procedural Vulnerability Detection

Recent progress in ML and LLMs has improved vulnerability detection, and recent datasets have reduced label noise and unrelated code changes. However, most existing approaches still operate at the function level, where models are asked to predict whether a single function is vulnerable without...

Beyond Crash: Hijacking Your Autonomous Vehicle for Fun and Profit

Autonomous Vehicles AVs, especially vision-based AVs, are rapidly being deployed without human operators. As AVs operate in safety-critical environments, understanding their robustness in an adversarial environment is an important research problem. Prior physical adversarial attacks on vision-bas...

Zabbix Agent Binaries Path Abuse Scanner

This scanner performs automated static analysis of Zabbix Agent binaries to detect hardcoded OpenSSL configuration paths that may enable provider or engine abuse. It identifies embedded OPENSSLDIR, ENGINESDIR, and MODULESDIR values, extracts OpenSSL version information, and checks for dynamic...

KRONE: Hierarchical and Modular Log Anomaly Detection

Log anomaly detection is crucial for uncovering system failures and security risks. Although logs originate from nested component executions with clear boundaries, this structure is lost when they are stored as flat sequences. As a result, state-of-the-art methods risk missing true dependencies...

CISA: Reducing the Attack Surface for End-of-Support Edge Devices

The Cybersecurity and Infrastructure Security Agency CISA, the Federal Bureau of Investigation FBI, and the U.K.’s National Cyber Security Centre NCSC are releasing this fact sheet to urge defensive action against malicious cyber activity by nation-state threat actors. Nation-state threat actors...

Next-Generation Cyberattack Detection with Large Language Models: Anomaly Analysis across Heterogeneous Logs

This project explores large language models LLMs for anomaly detection across heterogeneous log sources. Traditional intrusion detection systems suffer from high false positive rates, semantic blindness, and data scarcity, as logs are inherently sensitive, making clean datasets rare. We address...

ACORN-IDS: Adaptive Continual Novelty Detection for Intrusion Detection Systems

Intrusion Detection Systems IDS must maintain reliable detection performance under rapidly evolving benign traffic patterns and the continual emergence of cyberattacks, including zero-day threats with no labeled data available. However, most machine learning-based IDS approaches either assume...

Hydra: Robust Hardware-Assisted Malware Detection

Malware detection using Hardware Performance Counters HPCs offers a promising, low-overhead approach for monitoring program behavior. However, a fundamental architectural constraint, that only a limited number of hardware events can be monitored concurrently, creates a significant bottleneck,...

ShallowJail: Steering Jailbreaks against Large Language Models

Large Language ModelsLLMs have been successful in numerous fields. Alignment has usually been applied to prevent them from harmful purposes. However, aligned LLMs remain vulnerable to jailbreak attacks that deliberately mislead them into producing harmful outputs. Existing jailbreaks are either...

YARA-X 1.13.0

YARA-X is a re-incarnation of YARA, a pattern matching tool designed with malware researchers in mind. This new incarnation intends to be faster, safer and more user-friendly than its predecessor. The ultimate goal of YARA-X is replacing YARA as the default pattern matching tool for malware...

AlertBERT: A Noise-Robust Alert Grouping Framework for Simultaneous Cyber Attacks

Automated detection of cyber attacks is a critical capability to counteract the growing volume and sophistication of cyber attacks. However, the high numbers of security alerts issued by intrusion detection systems lead to alert fatigue among analysts working in security operations centres SOC,...

Evaluating and Enhancing the Vulnerability Reasoning Capabilities of Large Language Models

Large Language Models LLMs have demonstrated remarkable proficiency in vulnerability detection. However, a critical reliability gap persists: models frequently yield correct detection verdicts based on hallucinated logic or superficial patterns that deviate from the actual root cause. This...

TrapSuffix: Proactive Defense against Adversarial Suffixes in Jailbreaking

Suffix-based jailbreak attacks append an adversarial suffix, i.e., a short token sequence, to steer aligned LLMs into unsafe outputs. Since suffixes are free-form text, they admit endlessly many surface forms, making jailbreak mitigation difficult. Most existing defenses depend on passive detecti...

Trojans in Artificial Intelligence (TrojAI) Final Report

The Intelligence Advanced Research Projects Activity IARPA launched the TrojAI program to confront an emerging vulnerability in modern artificial intelligence: the threat of AI Trojans. These AI trojans are malicious, hidden backdoors intentionally embedded within an AI model that can cause a...

Characterizing and Modeling the GitHub Security Advisories Review Pipeline

GitHub Security Advisories GHSA have become a central component of open-source vulnerability disclosure and are widely used by developers and security tools. A distinctive feature of GHSA is that only a fraction of advisories are reviewed by GitHub, while the mechanisms associated with this revie...

Deep Learning for Contextualized NetFlow-Based Network Intrusion Detection: Methods, Data, Evaluation and Deployment

Network Intrusion Detection Systems NIDS have progressively shifted from signature-based techniques toward machine learning and, more recently, deep learning methods. Meanwhile, the widespread adoption of encryption has reduced payload visibility, weakening inspection pipelines that depend on...

Semi-Device-Independent Quantum Random Number Generator Resistant to General Attacks

Quantum random number generators QRNGs produce true random numbers based on the inherent randomness of quantum theory, rendering them a foundational segment of quantum cryptography. Distinguished from trusted-device QRNGs whose security depends on characterized devices, semi-device-independent...

Clouding the Mirror: Stealthy Prompt Injection Attacks Targeting LLM-Based Phishing Detection

Phishing sites continue to grow in volume and sophistication. Recent work leverages large language models LLMs to analyze URLs, HTML, and rendered content to decide whether a website is a phishing site. While these approaches are promising, LLMs are inherently vulnerable to prompt injection PI...

Entropy Bounds Via Hypothesis Testing and Its Applications to Two-Way Key Distillation in Quantum Cryptography

Quantum key distribution QKD achieves information-theoretic security, without relying on computational assumptions, by distributing quantum states. To establish secret bits, two honest parties exploit key distillation protocols over measurement outcomes resulting after the the distribution of...

Microsoft Windows 10 DLL Hijacking Scanner

This PHP class provides a security assessment tool for detecting potential DLL hijacking vulnerabilities on Windows systems. It's designed for educational and defensive security purposes only. that can be exploited on many recent versions of Windows 10, Windows 11, Windows Server 2022...

Identifying Adversary Tactics and Techniques in Malware Binaries with an LLM Agent

Understanding TTPs Tactics, Techniques, and Procedures in malware binaries is essential for security analysis and threat intelligence, yet remains challenging in practice. Real-world malware binaries are typically stripped of symbols, contain large numbers of functions, and distribute malicious...

GNSS SpAmming: A Spoofing-Based GNSS Denial-Of-Service Attack

GNSSs are vulnerable to attacks of two kinds: jamming i.e. denying access to the signal and spoofing i.e. impersonating a legitimate satellite. These attacks have been extensively studied, and we have a myriad of countermeasures to mitigate them. In this paper we expose a new type of attack:...

Persistent Human Feedback, LLMs, and Static Analyzers for Secure Code Generation and Vulnerability Detection

Existing literature heavily relies on static analysis tools to evaluate LLMs for secure code generation and vulnerability detection. We reviewed 1,080 LLM-generated code samples, built a human-validated ground-truth, and compared the outputs of two widely used static security tools, CodeQL and...

Trojan Attacks on Neural Network Controllers for Robotic Systems

Neural network controllers are increasingly deployed in robotic systems for tasks such as trajectory tracking and pose stabilization. However, their reliance on potentially untrusted training pipelines or supply chains introduces significant security vulnerabilities. This paper investigates...

CVE-Factory: Scaling Expert-Level Agentic Tasks for Code Security Vulnerability

CVE-Factory is a Multi-Agent system for fully automated, end-to-end CVE reproduction. Given CVE records, the system automatically researches details, generates test cases, builds Docker environments, and validates that each vulnerability can be both exploited and patched. The pipeline transforms...

Bypassing AI Control Protocols Via Agent-As-A-Proxy Attacks

As AI agents automate critical workloads, they remain vulnerable to indirect prompt injection IPI attacks. Current defenses rely on monitoring protocols that jointly evaluate an agent's Chain-of-Thought CoT and tool-use actions to ensure alignment with user intent. We demonstrate that these...