Are Frontier LLMs Ready for Cybersecurity? Evidence for Vertical Foundation Models from Dual-Mode Vulnerability Benchmarks

We evaluate whether frontier LLMs are ready for cybersecurity through a dual-mode benchmark: white-box function-level vulnerability detection VulnLLM-R, across C/Java/Python and black-box web application security testing five production-style applications with 118 ground-truth vulnerabilities...

Security, Privacy, and Ethical Risks in OpenClaw

This paper systematically investigates the security, privacy, and ethical risks, as well as the traceability challenges of OpenClaw, a locally executable AI agent system for natural language interaction and real-world task completion. While OpenClaw shows strong potential for personal assistance,...

Adversarial Vulnerability under Temporal Concept Drift: A Longitudinal Study of Android Malware Detection

We present a longitudinal, drift-aware evaluation of adversarial robustness across more than a decade of Android applications using static and dynamic feature representations extracted from emulator and real-device executions. The dataset is organized into yearly slices and evaluated under three...

Joern 4.0.546

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...

Innovations in Cardless Artificial Intelligence Banking: A Comprehensive Framework for Cyber Secure and Fraud Mitigation Using Machine Learning Algorithms

The advent of cardless artificial intelligence AI banking heralds a paradigm shift in the financial landscape, offering users unprecedented security and convenience. This paper outlines a comprehensive framework designed to enhance cybersecurity, introduce auto-generated virtual cards, and mitiga...

UNAD+: An Explainable Hybrid Framework for Unknown Network Attack Detection

The detection of previously unseen network attacks remains a major challenge for intrusion detection systems. Although supervised learning methods often perform well on known attack classes, they are limited when new attack types are not represented in the training data. Unsupervised methods are...

UFONet 2.0

UFONet abuses OSI Layer 7-HTTP to create/manage 'zombies' and to conduct different attacks using GET/POST, multi-threading, proxies, origin spoofing methods, cache evasion techniques, etc...

From Preventive to Reactive: How AI Coding Assistants Transform Developers' Security Awareness

AI coding assistants are now central to professional software development, yet their impact on how developers think about and practice security remains poorly understood. While prior work has documented vulnerability rates in AI-generated code, a more fundamental question persists: how do these...

Parser-Free Querying of Security Logs

Security analysts routinely query system logs to detect threats and investigate incidents, but each log source uses its own semi-structured format: logs are cheap to produce, but expensive to use. The standard approach, building per-source parsers to normalize logs into structured schemas, is...

Beyond Zero: Enterprise Security for the AI Era

The rise of autonomous AI agents and the accelerating velocity of corporate data access are stretching the application-centric model of zero trust security to its breaking point. This paper introduces Beyond Zero, a new security paradigm designed for the AI era. The Beyond Zero architecture...

Market-Analysis-Driven Methodology for Assessing Charging Station Cybersecurity

Modern charging communication standards for electric vehicles include optional security controls such as TLS-based authentication and encryption. However, with tens of thousands of fast charging points deployed in any given country, individually testing each one for security control support is...

Security of LLM-Generated Code: A Comparative Analysis

The majority of software developers use or are planning to use Artificial Intelligence AI tools in their development processes. Their top reasons include improving productivity and faster learning. In fact, Large Language Model LLM-generated code is currently in production, including in major tec...

Blind Spots in the Guard: How Domain-Camouflaged Injection Attacks Evade Detection in Multi-Agent LLM Systems

Injection detectors deployed to protect LLM agents are calibrated on static, template-based payloads that announce themselves as override directives. We identify a systematic blind spot: when payloads are generated to mimic the domain vocabulary and authority structures of the target document, wh...

Human Vulnerability Assessment in Cybersecurity: A Systematic Literature Review of Methods, Models, and Instruments

In cybersecurity, vulnerability assessment has typically focused on identifying and measuring vulnerabilities within digital assets and technical infrastructures. However, there is growing recognition that this approach alone is inadequate without a structured examination of the human factor, whi...

A First Measurement Study on Authentication Security in Real-World Remote MCP Servers

The Model Context Protocol MCP is emerging as a common interface connecting large language models LLMs with external services. Remote deployments are becoming increasingly important as agents connect to user-linked online services, such as social, productivity, and financial services. In such...

BYOT-CPS: A Hybrid Cyber-Physical Systems Testbed for IoT Security Assessment and Platform Evaluation

Internet of Things IoT security research continues to face a methodological gap between scalable virtual experimentation and realistic device behaviour. While pure simulation and emulation platforms provide control, repeatability, and scale, they do not fully reproduce firmware-specific behaviour...

Prompt Overflow: What the Guardrail Inspects Is Not What the Model Infers

Guardrail models a.k.a. safety checkers are widely deployed to screen user inputs before they reach large language models LLMs, serving as a primary defense against prompt injection attacks. Due to strict context constraints, these models handle overlength prompts through truncation or...

TriSweep: A Four-Drone Swarm Framework for Electromagnetic Side-Channel Analysis

Electromagnetic EM side-channel analysis traditionally assumes a stationary, close-proximity probe - a threat model that underestimates aerial adversaries. TriSweep is a simulation framework that designs and evaluates a four-drone swarm architecture for autonomous standoff EM-SCA of embedded...

Measuring Security without Fooling Ourselves: Why Benchmarking Agents Is Hard

The benchmarks used to evaluate AI agents in security-critical roles suffer from crucial weaknesses. Building on recent empirical evidence, we characterize three core challenges that undermine security evaluations: benchmark vulnerabilities, temporal staleness, and runtime uncertainty. We then...

Encrypted Neural Networks without Overflows

Fully homomorphic encryption FHE enables private inference by evaluating neural networks on encrypted data. In this way, we can delegate the computation to a third party server without ever revealing the user's data. Currently, the CKKS scheme is the backbone of most efficient FHE implementations...

Stabilising Explainability Fragility in Cybersecurity AI: The Impact and Mitigation of Multicollinearity in Public Benchmark Datasets

This paper investigates a unexplored yet impactful vulnerability in AI explainability used in intrusion detection IDS: multicollinearity-induced instability. Despite extensive reliance on post-hoc explainability tools such as SHAP or LIME, the impact of correlated features on explanation robustne...

Practical Countermeasure against Attacks Exploiting Detection Efficiency Mismatch in Quantum Key Distribution

We demonstrate a practical countermeasure against a well-known class of attacks on quantum key distribution QKD systems that exploit detection efficiency mismatch, where the receiver's detectors do not exhibit identical responses to incoming photons across all degrees of freedom. This class of...

Botnet Detection on CTU-13 Using Lightweight Machine Learning Models

Botnets are among the most persistent cyber threats, enabling large-scale attacks such as spam, credential theft, and distributed denial-of-service DDoS. While deep learning approaches have recently been applied to botnet detection, they are computationally intensive and often lack...

Pretraining Data Exposure in Large Language Models: A Survey of Membership Inference, Data Contamination, and Security Implications

Large Language Models LLMs have become the predominant paradigm in NLP, advancing both research and industry. As model sizes and pretraining data grow, concerns about Pretraining Data Exposure PDE increase due to the scale and opacity of training datasets. PDE refers to determining whether specif...

Wireshark Analyzer 4.6.6

Wireshark is a GTK+-based network protocol analyzer that lets you capture and interactively browse the contents of network frames. The goal of the project is to create a commercial-quality analyzer for Unix and Win32 and to give Wireshark features that are missing from closed-source sniffers. Thi...

Quality and Security Signals in AI-Generated Python Refactoring Pull Requests

As AI agents increasingly contribute to code development and maintenance, there is still limited empirical evidence on the quality and risk characteristics of their changes in real-world projects, particularly for refactoring-oriented contributions. It remains unclear how agent-authored refactori...

FreeBSD Security Advisory - FreeBSD-SA-26:19.file

FreeBSD Security Advisory - A file descriptor can be closed while a thread is blocked in a poll2 or select2 call waiting for that descriptor. Because the blocked thread does not hold a reference to the underlying object, this closure may result in the object being freed while the thread remains...

Backchaining Loss of Control Mitigations from Mission-Specific Benchmarks in National Security

Affordances and permissions are promising and timely safety levers for mitigating Loss of Control LoC threats in high-stakes deployment contexts, such as national security. Deployers in defense and intelligence could rely on several approaches to identify which affordances and permissions should ...

IronCurtain 0.11.0

IronCurtain is an early-stage research project exploring how to make AI agents safe enough to be genuinely useful. It is a runtime for autonomous AI agents, where security policy is derived from a human-readable constitution. APIs, configuration formats, and architecture may change...

Profiling User Vulnerability to Phishing through Psychological and Behavioral Factors

Phishing remains one of the most pervasive cybersecurity threats, shifting the focus from technological vulnerabilities to human cognitive and psychological factors. In coherence with the trend of studies on phishing to increasingly focus on human aspects and vulnerable users profiling, this stud...

VIPER-MCP: Detecting and Exploiting Taint-Style Vulnerabilities in Model Context Protocol Servers

Model Context Protocol MCP has emerged as a standard interface for connecting LLM agents to external tools. Because MCP servers expose privileged operations such as shell execution, network access, and file-system manipulation to agent-driven invocation, implementation flaws in tool handlers can...

Auditing Apple'S DifferentialPrivacy.Framework: Implementation Bugs, Misconfigurations, and Practical Risks

Since 2016, Apple has claimed that device analytics collected to improve user experience are protected by differential privacy DP. Apple's DifferentialPrivacy.framework is deployed across its operating systems and handles sensitive signals such as Safari domains, keyboard events, photo attributes...

HIDBench: Benchmarking Large Language Models for Host-Based Intrusion Detection

Recent benchmark efforts have advanced the evaluation of large language models LLMs in cybersecurity, including tasks such as penetration testing and vulnerability identification. However, a critical cybersecurity task, namely intrusion detection from system logs, remains unexplored. In this work...

FreeBSD Security Advisory - FreeBSD-SA-26:18.setcred

FreeBSD Security Advisory - The setcred2 system call is only available to privileged users. However, before the privilege level of the caller is checked, the user-supplied list of supplementary groups is copied into a fixed-size kernel stack buffer without first validating its length. If the...

FreeBSD Security Advisory - FreeBSD-SA-26:21.ptrace

FreeBSD Security Advisory - ptracePTSCREMOTE failed to properly validate parameters for the syscall2 and syscall2 meta-system calls. As a result, a user with the ability to debug a process may trigger arbitrary code execution in the kernel, even if the target process has no special privileges...

FreeBSD Security Advisory - FreeBSD-SA-26:24.cap_net

FreeBSD Security Advisory - In the case of the capnet service, when a key present in the old limit was omitted from the new limit, the missing key was treated as "allow any" instead of being rejected...

FreeBSD Security Advisory - FreeBSD-SA-26:20.fusefs

FreeBSD Security Advisory - When a fusefs file system implements extended attributes, the kernel may send a FUSELISTXATTR message to the userspace daemon to retrieve the list of extended attributes for a given file. The FUSE protocol requires the daemon to return a packed list of NUL-terminated...

FreeBSD Security Advisory - FreeBSD-SA-26:22.libcasper

FreeBSD Security Advisory - libcasper3 communicates with helper processes via UNIX domain sockets, and uses the select2 system call to wait for data to become available. However, it does not verify that its socket descriptor fits within select2's descriptor set size limit of FDSETSIZE 1024...

Domijn: The Security of Domain Registrars and the Risk of a Domain Name Takeover

Domain names are key assets for organisation. They anchor an organisation's online presence and reputation, and serve as linking pin for web services and, e.g., email. Consequently, a malicious takeover of a domain can lead to significant damages. Organisations register domain names through...

angr 9.2.216

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...

Detecting Offensive Cyber Agents: A Detection-In-Depth Approach

Artificial Intelligence AI agents can now orchestrate cyberattacks. This development is already increasing the speed and scale of cyber attacks, decreasing attack costs, and improving the operational autonomy of cyber capabilities. To defend against these emerging threats, actors must first devel...

FuzzingBrain V2: A Multi-Agent LLM System for Automated Vulnerability Discovery and Reproduction

Software vulnerabilities pose critical security threats, with nearly 50,000 CVEs reported in 2025. While Large Language Models LLMs show promise for automated vulnerability detection, three key challenges remain. First, LLM-generated vulnerability reports suffer from high false positive rates and...

FreeBSD Security Advisory - FreeBSD-SA-26:23.bsdinstall

FreeBSD Security Advisory - When bsdinstall or bsdconfig are prompted to scan for nearby Wi-Fi networks, they build up a list of network names and use bsddialog1 to prompt the user to select a network. This is implemented using a shell script, and the code which handled network names was not...

Detecting Trojaned DNNs Via Spectral Regression Analysis

Modern DNNs are repeatedly fine-tuned to incorporate new data and functionality. This evolutionary workflow introduces a security risk when updated data cannot be fully trusted, as adversaries may implant Trojans during fine-tuning. We present MIST, a Trojan detection approach that analyzes how a...

GenAI-Driven Threat Detection with Microsoft Security Copilot

Defending against today's increasingly sophisticated cyberattacks requires security analysts to continuously translate evolving attacker tradecraft into detection logic. This places defenders in a reactive posture, requiring constantly updated expertise across an increasingly fragmented security...

A Large Language Model Approach to Generating Bypass Rules for Malware Evasion in Analysis Sandbox

Sandbox evasion remains a critical challenge for automated malware analysis, as modern malware employs environment checks to detect analysis platforms and suppress malicious behavior. Existing approaches rely on manually crafted bypass rules that require deep reverse engineering of each evasion...

Awakening the Hydra: Stabilizing Multi-Concept Backdoor Injection in Text-To-Image Diffusion Models

Text-to-image diffusion models are increasingly developed through open-source reuse and repeated downstream fine-tuning, where reused checkpoints are difficult to verify and thus more susceptible to hidden backdoor behaviors. In such ecosystems, a single pretrained model may be sequentially adapt...

Refusal Evaluation in Coding LLMs and Code Agents: A Systematic Review of Thirteen Malicious-Code Prompt Corpora (2023-2025)

The evaluation of large language model refusal on malicious-coding tasks now spans at least thirteen publicly released prompt corpora AdvBench, the CyberSecEval family, RMCBench, RedCode, MCGMark, JailbreakBench, CySecBench, MalwareBench, CIRCLE, MOCHA, ASTRA, Scam2Prompt / Innoc2Scam-bench, and...

Hunting Vulnerability Variants in AI Infra: Measurement and Reference-Driven Detection

AI infra has become a shared execution layer for model training, deployment, and agent orchestration. Because many projects reimplement similar model-centric workflows, a vulnerability disclosed in one repository can recur as a variant in another repository with a related design. Yet the prevalen...

Detecting Data Exfiltration through I2P Anonymity Networks: A Two-Phase Machine Learning Approach

The Invisible Internet Project I2P provides strong anonymity through garlic routing and distributed network architecture, making it attractive for legitimate privacy needs. Nevertheless, the same properties can be exploited by malicious actors to steal sensitive information from corporate network...