Combating Knowledge Corruption in Agent Systems: A Byzantine-Tolerant Secure Collaborative RAG Framework

While retrieval-augmented generation systems partially address the hallucination issues in large language models, it also introduces new vulnerabilities to knowledge corruption attacks. Adversaries exploit these vulnerabilities by poisoning documents provided by RAG system to manipulate LLM...

DiagChain: A Diagnostic Benchmark for Evaluating LLM Agents on Evidence-Grounded Attack Chain Reconstruction

Large Language Model LLM agents offer a promising approach to attack chain reconstruction by retrieving and interpreting heterogeneous telemetry to infer ordered attacker actions. However, existing benchmarks mainly evaluate final outputs or aggregate accuracy, providing limited insight into how...

Post-Hoc Trajectory-Risk Certification for Modular LLM-Based Security Agents

Autonomous security agents operate as staged pipelines, such as classifying network traffic and then attributing attacks to a specific technique. Split conformal prediction gives each stage finite-sample coverage, but deployment requires a trajectory-level guarantee across the full chain. These...

Empirical Analysis of Evasion and Poisoning against Malware Data Drift Detection

As concept drift due to malware evolution presents challenges for malware classification, machine learning-based data drift detection tools are developed to mitigate this problem. These data drift detector tools are designed for a different purpose and built with different techniques compared to...

Paged Out! Magazine Issue 7

Paged Out! magazine issue 7 includes sections related to art, artificial intelligence, cryptography, demo scene, file formats, hardware, history, networks, OS internals, programming, retro stuff, reverse engineering, security / hacking, and system administration...

Delay Attacks on the German Smart Metering Infrastructure: A Security Analysis of CLS Channel Timing Constraints

This work analyzes the feasibility of delay attacks on control signals transmitted via the Controllable Local System CLS channel of the German Smart Metering Infrastructure SMI. It combines theoretical analysis with experimental validation under a threat model aligned to the Common Criteria...

Paged Out! Magazine Issue 2

Paged Out! magazine issue 2 includes sections related to algorithms, assembly, electronics, game development, OS internals, operating systems, programming, reverse engineering, security / hacking, writing articles, and system administration...

Behavioral Skill Reconstruction: Reconstructing Hidden Functionality from LLM Agent Skills

Closed source agent skills may encode proprietary instructions, scripts, constants, and data. Providers may offer their capabilities as services while keeping the underlying packages hidden. Prior work focuses on prompt injection attacks that directly disclose these artifacts, and existing defens...

AirKey: Multimodal Acoustic-Assisted WiFi Sensing for Zero-Training Robust PIN Inference

Contactless keystroke inference via WiFi sensing highlights severe privacy threats, yet its real-world feasibility is hindered by two fundamental physical and deployment bottlenecks: the strict requirement for network privileges to acquire stable sensing streams, and the inherent "waveform fusion...

Invisible Ink Threats: Adversarial Goals behind Legitimate Tasks in Computer-Use Agents

Computer-use agents CUAs, which empower large language models to autonomously operate operating systems and the web, are increasingly vulnerable to indirect prompt injection attacks. A widely adopted defense is the human-in-the-loop paradigm, in which the agent pauses for explicit user confirmati...

AMD SEV-SNP: A Confidential Computing Primer

This paper is a technical primer on AMD Secure Encrypted Virtualization with Secure Nested Paging SEV-SNP, a hardware confidential computing implementation that provides Trusted Execution Environments TEEs for virtual machines. SEV-SNP treats the hypervisor as adversarial. It encrypts guest memor...

LifeOS 7.28.3

LifeOS is a Life Operating System. It knows your goals, the people who matter to you, and where you are right now, and it works to move you toward where you want to be. The engine underneath is a verifiable loop: turn any request into testable criteria, then climb until they pass. This is the fir...

SparSEEty: Extracting Tokens from Sparsity-Exploiting LLM Serving Systems Via Deterministic Side Channels

Modern large language models LLMs exhibit activation sparsity, wherein only a subset of their neurons is activated for given input tokens. Researchers have leveraged this property to optimize LLM serving systems by omitting weight accesses and computations pertaining to inactive neurons...

Measuring Post-Quantum TLS Deployment across UK Internet Sectors

Post-quantum cryptography PQC is becoming an important component of long-term trust in Internet-facing infrastructure. Publicly observable PQC support provides evidence of externally visible deployment, but does not necessarily reflect the overall progress of an organisation's post-quantum...

AI Security Leaderboard: Methodology, Results and Minimal Standard

Frontier AI model developers increasingly rely on layered safeguards to prevent catastrophic misuse, but little public evidence exists on how much protection these safeguards provide, or how consistently across developers. We introduce the FAR.AI Minimal Standard for Safeguards, Version 1.0: a...

Rhabdomancer Vulnerability Research Assistant

Rhabdomancer is a blazing fast IDA headless plugin that locates calls to potentially insecure API functions in a binary file. Auditors can backtrace from these candidate points to find pathways allowing access to untrusted input...

A Multi-Objective AutoML-Based Efficient Intrusion Detection System for EV Charging Networks

Electric Vehicle Charging Systems EVCSs are increasingly connected with Internet of Things IoT devices, which improves charging intelligence but also expands their exposure to cyber-attacks. Intrusion Detection Systems IDSs are essential for securing EV charging networks; however, conventional...

Specter 2.2 NFC Reader / Skimmer Bug-Sweep FlipperZero FlipperZero

Specter turns your Flipper Zero into a pocket counter-surveillance bug-sweep for active 13.56 MHz NFC readers - a hidden card skimmer slipped into a payment terminal, a covert reader behind a door panel, a rogue logger taped under a desk. It passively senses the RF carrier that any powered-on...

Pseudo-Noise Superposition for Finite-Alphabet Physical Layer Security

Physical-layer security based on pseudo-noise PN superposition is a promising approach for mitigating eavesdropping in future wireless systems. However, under Shannon's capacity formulation with Gaussian signaling, achieving secrecy typically requires allocating substantial transmit power to PN,...

Antares: Foundation Models for Agentic Vulnerability Localization

Vulnerability localization is a fundamental step in software security, requiring models to reason over large codebases and iteratively identify vulnerable implementations. We present Antares, a family of compact language models 350M, 1B, and 3B parameters for agentic vulnerability localization...

WireGuardTCP

WireguardTCP adds an opt-in TCP path beneath the existing WireGuard encryption layer. Handshakes, keepalives, and encrypted data are framed inside a long-lived per-peer stream. UDP remains untouched and remains the default...

RFE Standards

Minimum Viable Standard MVS & Request for Evidence RFE Framework - Decompose bloated, legacy RFCs X.509/ASN.1 and RFC 3986 URIs into usage-driven, empirical standards. Coverage is dictated by observable real-world usage data plus an explicit Criticality Override Registry - not design-by-committee...

MutMem: Cryptographically Authorized Mutation in Persistent Agent Memory

Persistent agent memory must adapt as later outcomes change earlier evidence, yet mutable retrieval weights create an attribution problem: reviewers must distinguish authorized adaptation from database tampering. We present MutMem, an authorized-mutation protocol in HOM-AIMOS, a persistent...

TrainShield: Targeted Awareness for Cybersecurity Training

In recent years, cybersecurity threats have increasingly exploited human behaviour rather than purely technical vulnerabilities, exposing the limits of traditional awareness programmes delivered outside real-world contexts. To bridge this gap, we introduce TrainShield, an interaction paradigm for...

HashiCorp Consul Template 0.42.0 Path Redirection File Overwrite / Information Disclosure

This repository holds details relating to a HashiCorp Consul Template version 0.42.0 path redirection file overwrite vulnerability. HashiCorp Consul Template versions 0.42.0 and earlier contain a path resolution flaw in the writeToFile template helper where operator-supplied output paths are open...

EntailLLM: Verifying LLM-Generated Vulnerability Discovery Paths with Domain Knowledge Via Logic Programming

Large language models are increasingly used to reason about software vulnerabilities, but their outputs can silently violate domain knowledge, limiting their reliability in safety-critical settings such as medical devices. Prior work either treats that output as a prediction to be scored or...

Joern 4.0.594

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...

Agentic Incident Response through Digital Twin-Enhanced Multiscale Planning

Incident response is currently managed by security operators using predefined playbooks, resulting in slow, labor-intensive security decision-making processes. Consequently, there is a growing need for automated incident response planning. Decision-theoretic approaches based on control,...

OSSEC HIDS 4.2.0

OSSEC is a full platform to monitor and control your systems. It mixes together all the aspects of HIDS host-based intrusion detection, log monitoring and SIM/SIEM together in a simple, powerful and open source solution. This is the source code release...

HashiCorp Consul Template 0.41.4 Sandbox Path Bypass / Information Disclosure

This repository includes details for a HashiCorp Consul Template version 0.41.4 sandbox path bypass information disclosure vulnerability. HashiCorp Consul Template versions 0.41.4 and earlier contain a time-of-check to time-of-use flaw in the file template helper where symlink validation is...

Vulnerability Detection in AArch64 Machine Code Using a Digital Twin

This paper proposes an explainable digital twin for vulnerability detection in AArch64 machine code without access to source code. The digital twin reproduces the concrete execution of a program and preserves the state of registers, processor flags, memory, and live allocated blocks. Each...

Evading Chain-Of-Thought Monitoring through Model Poisoning

Chain-of-thought CoT monitoring is an increasingly important component of AI safety stacks but relies on the assumption that a model's reasoning trace is informative about its actions. This work studies the limits of CoT monitoring through the lens of model poisoning. We demonstrate that backdoor...

Why Formal Monitors Fail: Attack Distribution Entropy As a Coverage Bound for LTL-Based LLM Agent Safety

Runtime safety monitors based on Linear Temporal Logic LTL and finite automata FSA are increasingly deployed to intercept unsafe tool-call sequences in LLM agents. Yet the same monitor achieves 68-75% attack coverage on some model architectures and near-zero on others, with no explanation from...

On the Performance of Malware Detection Classifiers Using Hardware Performance Counters

Malware detection using Hardware Performance Counters HPC has emerged as a promising solution to improve the security of computing systems as a complement to antivirus software. Hardware-based malware detectors HMD use Machine Learning ML classifiers to detect malicious application patterns. The...

A Multimodal Automatic Redteaming Evaluation Based on Atomic Jailbreak Strategy Decoupling and Combination

Multimodal Large Language Models MLLMs have achieved impressive progress in image-text comprehension and generation, yet they remain susceptible to jailbreak attacks that can trigger harmful outputs and pose serious safety concerns. Existing multimodal jailbreak attacks have shown the feasibility...

AdaptoNet: Modular Foundation-Adaptive Neural Networks for Cyber-Physical Attack Detection in Power Grids

Cyber attacks on the power grid combine physical disruptions with compromised data to destabilize cyber-physical systems. We demonstrate that data denial attacks, where adversaries block measurements in a targeted region while triggering a line outage, reduce detection performance by more than...

Permission Denied: Policy-Graded Evaluation of Coding Agents in Hardened Environments

Coding agents increasingly run inside organizations whose security controls scoped credentials, restricted egress, read-only filesystems, non-root execution constrain them like any other software. Existing benchmarks, however, evaluate agents almost exclusively in permissive sandboxes, so it is...

Performance Analysis of Machine Learning Algorithms for Predicting Malware

Malware poses a persistent and evolving threat to modern computing systems, making accurate and timely detection a critical cybersecurity challenge. Traditional signature-based antivirus solutions often fail to identify newly emerging malware, leaving systems vulnerable until updated signatures...

How Benchmarks and Evaluation Protocols Shape Conclusions in Provenance-Based Intrusion Detection

Provenance-based intrusion detection systems PIDS frequently report strong performance, but the conclusions drawn from these results can be highly sensitive to benchmarking choices and evaluation protocols. We investigate this dependency by re-evaluating representative PIDS on public datasets tha...

Security in Low-Altitude ISAC with Coupled Communication and Sensing Information Leakage

Secure information transmission in integrated sensing and communication ISAC systems deployed in low-altitude wireless networks LAWN is particularly challenging due to the open airspace and the broadcast nature of wireless signals reused for both communication and sensing, which give rise to more...

Vulnerabilities, Secrets and Misconfiguration in the Highest-Exposure Docker Hub Images

Docker Hub is the registry underneath most container deployments, and a flaw in a widely reused base image is inherited by every image built on it. Prior ecosystem-scale measurements each rely on a single detector, leaving the tool-dependence of their counts unquantified, while the studies that d...

Decoy Images Amplify Caption-Mediated Defenses against Encoded Jailbreaks

We report a counter-intuitive interaction between image inputs and existing black-box defenses on Vision--Language Models VLMs: pairing an encoded jailbreak prompt with an unrelated decoy image can sharply lower attack success rate ASR. The operative change is in the defense pipeline, not in the...

Security-First Evaluation of Text-To-Terraform: Benchmarking LLMs and SLMs for Secure IaC Generation

Cloud misconfiguration remains a leading cause of security incidents, yet whether LLMs and SLMs can generate security-compliant Infrastructure-as-Code is an open question. We benchmark seven models, three closed LLMs Claude Opus 4, GPT-5.4, Gemini 2.5 Pro and four open SLMs Qwen2.5-Coder-14B,...

Multi-LLM Consensus Framework for Evaluating Banking-Sector NIDS Dataset Coverage of MITRE ATT&CK Techniques

The systemic criticality of global banking networks has ren-dered them high-priority targets for advanced persistent threats, neces-sitating Network Intrusion Detection Systems NIDS whose operational effectiveness must extend beyond statistical accuracy. However, a signif-icant validation gap...

From Chasing Ghosts to Missed Attacks: Perspectives and Perceptions of SOC Practitioners on LLM Integration, Risks, and Readiness

Security Operations Centers SOCs process large volumes of security events, requiring analysts to accurately detect and assess ongoing cyberattacks under time pressure. Recent advances in Large Language Models LLMs suggest potential benefits for security operations, yet their practical suitability...

Supporting Cybersecurity Risk Management for Medical Devices Via the SECUMAN Ontology and Shapes

We propose the SECUMAN ontology and shapes for representing and analysing cybersecurity risk-management documentation for medical devices. Cybersecurity risks are increasingly relevant for connected medical devices and may have direct consequences for patient safety. Current risk-management files...

A Decade of Healthcare Cyber Threats: Empirical Analysis, Evidence-Based Prioritisation, and AI Threat Model

Healthcare systems face persistent and evolving cyber threats, yet how adversarial tactics and techniques have shifted over time has not been systematically characterised using empirical, multi-source data. This paper analyses 1,214 threat records drawn from three authoritative sources: the MITRE...

When Prompts Control Robots: Prompt Injection Attacks in Multi-Agent Robotic Systems

Large language models are increasingly integrated into autonomous robotic systems for task planning and control, but this integration exposes them to prompt injection attacks that can lead to unsafe decisions and physical harm. Multi-agent settings increase the risks through cross-agent...

Adversarial Attacks in Multi-Agent LLM Pipelines: Unveiling Structural Vulnerabilities in Agentic AI Architectures

Multi-agent LLM pipelines orchestrate multiple specialized language model agents into structured workflows where intermediate outputs are passed across agents to solve complex tasks. This design introduces a security gap absent in single-agent settings: once an agent accepts adversarial content, ...

An AI Approach to Verified Production Cryptographic Libraries

Cryptographic code is critical infrastructure that must be correct, yet formally verifying production libraries remains difficult. Existing language-model proof systems solve isolated obligations with specifications and premises already given, leaving production-library verification unresolved. W...