Securing Retrieval-Augmented Generation: A Taxonomy of Attacks, Defenses, and Future Directions

Retrieval-augmented generation RAG significantly enhances large language models LLMs but introduces novel security risks through external knowledge access. While existing studies cover various RAG vulnerabilities, they often conflate inherent LLM risks with those specifically introduced by RAG. I...

OpenSCAP Libraries 1.4.4

The openscap project is a set of open source libraries that support the SCAP Security Content Automation Protocol set of standards from NIST. It supports CPE, CCE, CVE, CVSS, OVAL, and XCCDF...

SkillTrojan: Backdoor Attacks on Skill-Based Agent Systems

Skill-based agent systems tackle complex tasks by composing reusable skills, improving modularity and scalability while introducing a largely unexamined security attack surface. We propose SkillTrojan, a backdoor attack that targets skill implementations rather than model parameters or training...

Beyond Single Reports: Evaluating Automated ATT&CK Technique Extraction in Multi-Report Campaign Settings

Large-scale cyberattacks, referred to as campaigns, are documented across multiple CTI reports from diverse sources, with some providing a high-level overview of attack techniques and others providing technical details. Extracting attack techniques from reports is essential for organizations to...

OpenSSL Toolkit 3.6.2

OpenSSL is a robust, fully featured Open Source toolkit implementing the Secure Sockets Layer and Transport Layer Security protocols with full-strength cryptography world-wide. This is the 3.6 release...

OpenSSL Toolkit 3.3.7

OpenSSL is a robust, fully featured Open Source toolkit implementing the Secure Sockets Layer and Transport Layer Security protocols with full-strength cryptography world-wide. This is the 3.3 release...

OpenSSL Toolkit 3.0.20

OpenSSL is a robust, fully featured Open Source toolkit implementing the Secure Sockets Layer and Transport Layer Security protocols with full-strength cryptography world-wide. This is the 3.0 LTS release...

Hiding an Ear in Plain Sight: On the Practicality and Implications of Acoustic Eavesdropping with Telecom Fiber Optic Cable

Optical fibers are widely regarded as reliable communication channels due to their resistance to external interference and low signal loss. This paper demonstrates a critical side channel within telecommunication optical fiber that allows for acoustic eavesdropping. By exploiting the sensitivity ...

OpenSSL Toolkit 3.5.6

OpenSSL is a robust, fully featured Open Source toolkit implementing the Secure Sockets Layer and Transport Layer Security protocols with full-strength cryptography world-wide. This is the 3.5 LTS release...

MCP-DPT: A Defense-Placement Taxonomy and Coverage Analysis for Model Context Protocol Security

The Model Context Protocol MCP enables large language models LLMs to dynamically discover and invoke third-party tools, significantly expanding agent capabilities while introducing a distinct security landscape. Unlike prompt-only interactions, MCP exposes pre-execution artifacts, shared context,...

Vulnerability Abundance: A Formal Proof of Infinite Vulnerabilities in Code

We present a constructive proof that a single C program, the Vulnerability Factory, admits a countably infinite set of distinct, independently CVE-assignable software vulnerabilities. We formalise the argument using elementary set theory, verify it against MITRE's CVE Numbering Authority counting...

Aether Smart Contract Security Analysis Framework 5.0.2

Aether is a Python-based framework for analyzing Solidity smart contracts, generating vulnerability findings, producing Foundry-based proof-of-concept PoC tests, and validating exploits on mainnet forks. It combines Solidity AST parsing, taint analysis, control flow graph analysis, cross-contract...

VulGD: A LLM-Powered Dynamic Open-Access Vulnerability Graph Database

Software vulnerabilities continue to pose significant threats to modern information systems, requiring a timely and accurate risk assessment. Public repositories, such as the National Vulnerability Database and CVE details, are regularly updated, but predominantly utilize relational data models...

Hiding in the Tunnels: Unmasking the New Stealthy BPFDoor Variants

This is Rapid7's whitepaper discussing BPFDoor variants. Advanced persistent threats APTs are locked in a continuous arms race with network defenders. As static indicators of compromise IoCs for the notorious BPFDoor malware became widely deployed by security vendors, the threat actors went back ...

OpenSSL Toolkit 3.4.5

OpenSSL is a robust, fully featured Open Source toolkit implementing the Secure Sockets Layer and Transport Layer Security protocols with full-strength cryptography world-wide. This is the 3.4 release...

Aether Smart Contract Security Analysis Framework 6.0

Aether is a Python-based framework for analyzing Solidity smart contracts, generating vulnerability findings, producing Foundry-based proof-of-concept PoC tests, and validating exploits on mainnet forks. It combines Solidity AST parsing, taint analysis, control flow graph analysis, cross-contract...

ARuleCon: Agentic Security Rule Conversion

Security Information and Event Management SIEM systems make it possible for detecting intrusion anomalies in real-time manner by their applied security rules. However, the heterogeneity of vendor-specific rules e.g., Splunk SPL, Microsoft KQL, IBM AQL, Google YARA-L, and RSA ESA makes...

Anamorphic Encryption with CCA Security: A Standard Model Construction

Anamorphic encryption serves as a vital tool for covert communication, maintaining secrecy even during post-compromise scenarios. Particularly in the receiver-anamorphic setting, a user can shield hidden messages even when coerced into surrendering their secret keys. However, a major bottleneck i...

System Card: Claude Mythos Preview

This System Card describes Claude Mythos Preview, a large language model from Anthropic. Mythos Preview is their most capable frontier model to date, and shows a striking leap in scores on many evaluation benchmarks compared to their previous frontier model, Claude Opus 4.6. This System Card...

Broken Quantum: A Systematic Formal Verification Study of Security Vulnerabilities across the Open-Source Quantum Computing Simulator Ecosystem

Quantum computing simulators form the classical software foundation on which virtually all quantum algorithm research depends. We present Broken Quantum, the first comprehensive formal security audit of the open-source quantum computing simulator ecosystem. Applying COBALT QAI -- a four-module...

SentinelSphere: Integrating AI-Powered Real-Time Threat Detection with Cybersecurity Awareness Training

The field of cybersecurity is confronted with two interrelated challenges: a worldwide deficit of qualified practitioners and ongoing human-factor weaknesses that account for the bulk of security incidents. To tackle these issues, we present SentinelSphere, a platform driven by artificial...

Guiding Symbolic Execution with Static Analysis and LLMs for Vulnerability Discovery

Symbolic execution detects vulnerabilities with precision, but applying it to large codebases requires harnesses that set up symbolic state, model dependencies, and specify assertions. Writing these harnesses has traditionally been a manual process requiring expert knowledge, which significantly...

Windows Service for User (S4U) Scheduled Task Persistence Schedule Trigger

This Metasploit module creates a scheduled task that will run using service-for-user S4U. This allows the scheduled task to run even as an unprivileged user that is not logged into the device. This will result in lower security context, allowing access to local resources only. The module requires...

SkillSieve: A Hierarchical Triage Framework for Detecting Malicious AI Agent Skills

OpenClaw's ClawHub marketplace hosts over 13,000 community-contributed agent skills, and between 13% and 26% of them contain security vulnerabilities according to recent audits. Regex scanners miss obfuscated payloads; formal static analyzers cannot read the natural language instructions in...

Time-Domain Voice Identity Morphing (TD-VIM): A Signal-Level Approach to Morphing Attacks on Speaker Verification Systems

In biometric systems, it is a common practice to associate each sample or template with a specific individual. Nevertheless, recent studies have demonstrated the feasibility of generating "morphed" biometric samples capable of matching multiple identities. These morph attacks have been recognized...

Argus: Reorchestrating Static Analysis Via a Multi-Agent Ensemble for Full-Chain Security Vulnerability Detection

Recent advancements in Large Language Models LLMs have sparked interest in their application to Static Application Security Testing SAST, primarily due to their superior contextual reasoning capabilities compared to traditional symbolic or rule-based methods. However, existing LLM-based approache...

Signature Placement in Post-Quantum TLS Certificate Hierarchies: An Experimental Study of ML-DSA and SLH-DSA in TLS 1.3 Authentication

Post-quantum migration in TLS 1.3 should not be understood as a flat substitution problem in which one signature algorithm is replaced by another and deployment cost is inferred directly from primitive-level benchmarks. In certificate-based authentication, the practical effect of a signature fami...

From Incomplete Architecture to Quantified Risk: Multimodal LLM-Driven Security Assessment for Cyber-Physical Systems

Cyber-physical systems often contend with incomplete architectural documentation or outdated information resulting from legacy technologies, knowledge management gaps, and the complexity of integrating diverse subsystems over extended operational lifecycles. This architectural incompleteness...

Hybrid ResNet-1D-BiGRU with Multi-Head Attention for Cyberattack Detection in Industrial IoT Environments

This study introduces a hybrid deep learning model for intrusion detection in Industrial IoT IIoT systems, combining ResNet-1D, BiGRU, and Multi-Head Attention MHA for effective spatial-temporal feature extraction and attention-based feature weighting. To address class imbalance, SMOTE was applie...

CritBench: A Framework for Evaluating Cybersecurity Capabilities of Large Language Models in IEC 61850 Digital Substation Environments

The advancement of Large Language Models LLMs has raised concerns regarding their dual-use potential in cybersecurity. Existing evaluation frameworks overwhelmingly focus on Information Technology IT environments, failing to capture the constraints, and specialized protocols of Operational...

SoK: Understanding Anti-Forensics Concepts and Research Practices across Forensic Subdomains

Anti-forensics includes a growing set of techniques designed to obstruct forensic analysis. While cybercriminals increasingly rely on these methods, they also help researchers identify and remedy weaknesses in forensic tools, advancing the overall robustness of digital forensics. Despite repeated...

LLM4CodeRE: Generative AI for Code Decompilation Analysis and Reverse Engineering

Code decompilation analysis is a fundamental yet challenging task in malware reverse engineering, particularly due to the pervasive use of sophisticated obfuscation techniques. Although recent large language models LLMs have shown promise in translating low-level representations into high-level...

Towards the Development of an LLM-Based Methodology for Automated Security Profiling in Compliance with Ukrainian Cybersecurity Regulations

In recent years, the pace of development of information technology in various areas has increased drastically, forcing cybersecurity specialists to constantly review existing processes in order to prevent unauthorized access to confidential information. Using Ukraine as a primary case study, this...

Windows Service for User (S4U) Scheduled Task Persistence Event Trigger

This Metasploit module creates a scheduled task that will run using service-for-user S4U. This allows the scheduled task to run even as an unprivileged user that is not logged into the device. This will result in lower security context, allowing access to local resources only. The module requires...

LanG -- a Governance-Aware Agentic AI Platform for Unified Security Operations

Modern Security Operations Centers struggle with alert fatigue, fragmented tooling, and limited cross-source event correlation. Challenges that current Security Information Event Management and Extended Detection and Response systems only partially address through fragmented tools. This paper...

Auditable Agents

LLM agents call tools, query databases, delegate tasks, and trigger external side effects. Once an agent system can act in the world, the question is no longer only whether harmful actions can be prevented--it is whether those actions remain answerable after deployment. We distinguish...

Swiss-Bench 003: Evaluating LLM Reliability and Adversarial Security for Swiss Regulatory Contexts

The deployment of large language models LLMs in Swiss financial and regulatory contexts demands empirical evidence of both production reliability and adversarial security, dimensions not jointly operationalized in existing Swiss-focused evaluation frameworks. This paper introduces Swiss-Bench 003...

Can Drift-Adaptive Malware Detectors Be Made Robust? Attacks and Defenses under White-Box and Black-Box Threats

Concept drift and adversarial evasion are two major challenges for deploying machine learning-based malware detectors. While both have been studied separately, their combination, the adversarial robustness of drift-adaptive detectors, remains unexplored. We address this problem with AdvDA, a rece...

Foundations for Agentic AI Investigations from the Forensic Analysis of OpenClaw

Agentic Al systems are increasingly deployed as personal assistants and are likely to become a common object of digital investigations. However, little is known about how their internal state and actions can be reconstructed during forensic analysis. Despite growing popularity, systematic forensi...

Hackers or Hallucinators? A Comprehensive Analysis of LLM-Based Automated Penetration Testing

The rapid advancement of Large Language Models LLMs has created new opportunities for Automated Penetration Testing AutoPT, spawning numerous frameworks aimed at achieving end-to-end autonomous attacks. However, despite the proliferation of related studies, existing research generally lacks...

Aether - Adaptive Exploit and Threat Hunting Engine for EVM-based Repositories 5.0

Aether is a Python-based framework for analyzing Solidity smart contracts, generating vulnerability findings, producing Foundry-based proof-of-concept PoC tests, and validating exploits on mainnet forks. It combines Solidity AST parsing, taint analysis, control flow graph analysis, cross-contract...

Stop Fixating on Prompts: Reasoning Hijacking and Constraint Tightening for Red-Teaming LLM Agents

With the widespread application of LLM-based agents across various domains, their complexity has introduced new security threats. Existing red-team methods mostly rely on modifying user prompts, which lack adaptability to new data and may impact the agent's performance. To address the challenge,...

ClawLess: A Security Model of AI Agents

Autonomous AI agents powered by Large Language Models can reason, plan, and execute complex tasks, but their ability to autonomously retrieve information and run code introduces significant security risks. Existing approaches attempt to regulate agent behavior through training or prompting, which...

Windows Service for User (S4U) Scheduled Task Persistence Logon Trigger

This Metasploit module creates a scheduled task that will run using service-for-user S4U. This allows the scheduled task to run even as an unprivileged user that is not logged into the device. This will result in lower security context, allowing access to local resources only. The module requires...

Stealthy and Adjustable Text-Guided Backdoor Attacks on Multimodal Pretrained Models

Multimodal pretrained models are vulnerable to backdoor attacks, yet most existing methods rely on visual or multimodal triggers, which are impractical since visually embedded triggers rarely occur in real-world data. To overcome this limitation, we propose a novel Text-Guided Backdoor TGB attack...

OpenSSL Security Advisory 20260407

OpenSSL Security Advisory 20260407 - Applications using RSASVE key encapsulation to establish a secret encryption key can send contents of an uninitialized memory buffer to a malicious peer. Applications using AES-CFB128 encryption or decryption on systems with AVX-512 and VAES support can trigge...

Windows Service for User (S4U) Scheduled Task Persistence Logon Trigger

This Metasploit module creates a scheduled task that will run using service-for-user S4U. This allows the scheduled task to run even as an unprivileged user that is not logged into the device. This will result in lower security context, allowing access to local resources only. The module requires...

Your LLM Agent Can Leak Your Data: Data Exfiltration Via Backdoored Tool Use

Tool-use large language model LLM agents are increasingly deployed to support sensitive workflows, relying on tool calls for retrieval, external API access, and session memory management. While prior research has examined various threats, the risk of systematic data exfiltration by backdoored...

WebSP-Eval: Evaluating Web Agents on Website Security and Privacy Tasks

Web agents automate browser tasks, ranging from simple form completion to complex workflows like ordering groceries. While current benchmarks evaluate general-purpose performancee.g., WebArena or safety against malicious actionse.g., SafeArena, no existing framework assesses an agent's ability to...

PoC-Adapt: Semantic-Aware Automated Vulnerability Reproduction with LLM Multi-Agents and Reinforcement Learning-Driven Adaptive Policy

While recent approaches leverage large language models LLMs and multi-agent pipelines to automatically generate proof-of-concept PoC exploits from vulnerability reports, existing systems often suffer from two fundamental limitations: unreliable validation based on surface-level execution signals...