(A)ISpy: Parasitic Trojans for Machine Learning Infrastructure

Modern machine learning ML pipelines depend heavily on third party libraries for graph compilation and hardware acceleration. While current practices audit data and model artifacts or rely on file integrity checks, the execution environment remains implicitly trusted. This blind spot enables acti...

RRAM-DP: Device-Calibrated Differential Privacy for In-Memory Edge Learning

Edge Artificial Intelligence of Things AIoT systems often collect sensitive data in situ, raising serious privacy concerns. Resistive-switching random-access memory RRAM is an attractive substrate for efficient AIoT thanks to its multi-bit storage and compute-in-memory CiM capabilities, while its...

Residual Observability and Attack Detectability in Encrypted OPC UA Traffic

OPC Unified Architecture OPC UA encryption conceals application-layer semantics and restricts intrusion detection to residual communication structure. Although machine learning-based intrusion detection systems IDSs can detect attacks in encrypted OPC UA traffic, the relationship between residual...

Salience Induction against Multi-Hop RAG Agents: Threat and Defense

Agentic retrieval-augmented generation RAG systems increasingly retrieve external evidence and orchestrate tools for knowledge-intensive applications. In Multi-Hop question answering, agents chain facts across documents. Existing defenses focus on content poisoning, which injects false facts, and...

Insecure Coding Preferences in Long-Term Memory: Security Risks for LLM-Based Code Generation

LLM-based systems increasingly incorporate long-term memory to improve cross-session continuity. However, once insecure coding preferences are stored, they may silently influence security-critical decisions in subsequent generations. In this study, we conduct the first systematic empirical study ...

Trusted Credentials, Untrusted Behavior: Benchmarking LLM-Agent Security in High-Performance Computing

Large language model LLM agents are starting to take on routine work in high-performance computing HPC, including monitoring Slurm jobs, diagnosing failed builds, inspecting simulation output, and coordinating scientific workflows. To do this work, an agent commonly acts under its user's...

Measuring and Evaluating the Performance of Generative AI Models for Scam Detection

Online scams continue to cause substantial financial and personal harm. As a result, detection systems based on Large Language Models LLMs have been integrated into security products ranging from email gateways and browser extensions to fraud-monitoring dashboards. As this adoption accelerates, a...

How Jailbreak Attacks Inform Safety Alignment: A Defender-Centric, Shapley-Based Evaluation of Jailbreak Contributions

Jailbreak attacks on large language models are usually evaluated by attacker-centric metrics such as attack success rate ASR, yet an attack that breaks a model is not necessarily useful for improving its safety. We propose a defender-centric view of jailbreak evaluation, where attacks are evaluat...

The Finite Key Effect of Side-Channel-Secure Quantum Key Distribution beyond Post-Selection Technique

By applying the framework of entropic uncertainty relation EUR and the Quantum Leftover Hash Lemma QLHL, we introduce a security-proof method for variable-length side-channel-secure SCS quantum key distribution QKD against coherent attacks. This method reframes composable security as a statistica...

Between Safe Boundaries: Exploiting Temporal Consistency for Jailbreaking Text-To-Video Generation Models

Recently, text-to-video T2V models have been widely deployed, sparking growing concerns over their robustness against jailbreak attacks. Existing jailbreak methods, mostly adapted from text-to-image attacks, suffer notable drawbacks when applied to T2V systems. They fail to fully leverage tempora...

Shared Vulnerabilities in Robustness-Optimized Defenses: One Breach Exposes the Family

Adversarial robustness optimization aims to preserve correct prediction under adversarial perturbations, and has produced substantial robustness gains through methods such as adversarial training and adversarial purification. However, we identify a new security risk: these gains can create shared...

A Multi-Model Hybrid Defense Approach against White-Box Adversarial Attacks in Computer Network Traffic

It is crucial to safeguard computer networks from evolving network security threats and unknown cyberattacks. An essential tool for protecting computer networks against unknown cyber threats is Network Intrusion Detection System NIDS. However, NIDS faces a major security concern due to its...

DSA Nonce Vulnerabilities: An Interactive Analysis

Digital signatures are fundamental to identity authentication and data integrity in cybersecurity, and the NIST-standardized Digital Signature Algorithm DSA frequently appears in the cryptography track of CTF competitions. However, DSA relies on number theory, modular arithmetic, and large-intege...

Isolation Failure from Shared Storage: Characterizing and Exploiting Page-Cache SCA Leakage across Containers and VMs

Modern cloud platforms increasingly combine strong software isolation mechanisms with shared hardware resources to improve performance and resource efficiency. Conventional containers do this by sharing the host kernel directly, whereas sandboxed runtimes e.g., gVisor and VM-based runtimes e.g.,...

ShadowPickle: Evading Machine Learning Model Scanners Via Stealthy Pickle Deserialization Attacks

Model hosting hubs e.g., Hugging Face are vulnerable to supply chain attacks that enable remote code execution on trusted user environments. Attackers often distribute malicious Pre-trained ML models PTMs via model hubs. In this paper, we present novel attacks against PTMs and model hubs called...

Federated Lightweight Intrusion Detection in Drone Swarms with Knowledge Distillation

Drone swarms are increasingly deployed in critical applications such as surveillance, disaster response, and infrastructure monitoring. However, their reliance on open communication channels and their limited computational resources make them vulnerable to a wide range of cyber-threats. There is ...

A Non-Intrusive Traffic Analysis Framework for Authorization Risk Detection and Coordinated Response in Web Applications

Authorization violations under valid Web sessions are difficult to identify and handle in real time from traffic because they depend strongly on business semantics and exhibit few distinctive protocol-level features. This paper proposes a non-intrusive traffic analysis framework for authorization...

How Do You Choose Your AI Component? an Interview Study of Secure AI Integration in Practice

The increasing adoption of Large Language Models LLMs as AI components in modern software systems introduces distinct security risks to the software supply chain. While many considerations and safety mechanisms are in place for components of the traditional software supply chain, the recent rapid...

Adaptive Incident Prioritization for Security Operations at Scale

Large security operations centers SOCs often face hundreds of active incidents per day, creating substantial cognitive and operational demands for analysts. Analysts must quickly decide which incidents deserve attention within long, constantly changing queues, yet incidents are commonly ordered b...

Federated Learning and LLM-Driven Threat Intelligence for Zero Trust IoT Architecture

While the Internet of Things IoT has become essential, they introduced serious security and privacy challenges, especially for mission-critical environments. Legacy devices are vulnerable to viruses, data breaches, and unauthorized access, and updating these devices would be infeasibly costly. As...

Reliable Remediation Impact Prediction for Black-Box Security Ratings

Security rating platforms summarize externally observable cyber exposure and are expected to help organizations prioritize remediation. A platform may want to tell an organization how a candidate remediation action would affect its score, but repeatedly exposing exact score responses can reveal...

Nimux 1.0.1

Nimux is a native command surface for authorized security assessments. It combines network enumeration, credential validation, Active Directory operations, Kerberos workflows, remote execution, file movement, secrets collection, DCSync, GPO operations, database clients, and SOCKS routing into one...

Evaluating Open-Weight LLMs for Generating Structured Threat Information for Autonomous Vehicle Vulnerabilities

Connected and Autonomous Vehicles CAVs rely on interconnected software and hardware components, including sensors, Electronic Control Units, in-vehicle infotainment systems, and telematics units, where vulnerabilities can compromise assets, users, and vehicle operations. These vulnerabilities are...

AI Watermark Evidence Fails Forensic Readiness: An Empirical Evaluation

Governments are increasingly mandating that LLM-generated content carry watermarks. The EU AI Act calls for markings that are "sufficiently reliable and robust." California's SB 942 requires disclosure that is "permanent or extraordinarily difficult to remove." Both mandates rest on an untested...

TaintRadar: Semantic-Aware Taint-Style Vulnerability Detection Via Augmented Code Property Graphs

Despite significant advances, static vulnerability analysis suffers from three critical limitations: coarse sanitization modeling, which treats validation as a binary barrier; database blindness, which breaks taint tracking across persistence layers; and shallow object-oriented analysis, which...

The Language of Security: How Prompt Syntax Shapes Secure Code Generation in Open LLMs

Large Language Models LLMs are increasingly used for source code generation despite their outputs often exhibiting security vulnerabilities. Prior work shows that prompt engineering can mitigate such risks, yet 1 they focused on high-level prompting strategies, neglecting recent evidence that...

A Control-Driven Framework for Secure SaaS Onboarding in Regulated Enterprises

As enterprises increasingly adopt Software-as-a-Service SaaS platforms for mission-critical functions, onboarding these services has emerged as a complex challenge extending well beyond procurement and basic security review. In regulated environments, SaaS onboarding must address multiple...

Enhanced Multi-Class DDoS Attack Identification Using a Meta-Learning Ensemble

Distributed Denial of Service DDoS attacks continue to pose significant threats to network availability and security. While many detection systems focus on binary classification attack vs. benign, effective mitigation often requires identifying the specific type of DDoS attack. This paper...

Revisiting Data-Driven Dynamic Security Assessment with a Tabular Foundation Model

Data-driven pre-fault dynamic security assessment DSA rapidly evaluates the dynamic risk of credible contingencies on a power system using machine learning. Existing approaches face two limitations. First, they require a large labelled database for training, with a separate model trained, tuned,...

Code-Poisoning Property Inference Attacks

The flourishing code hosting platforms and coding agents enable even beginners with private data to build tailored Machine Learning ML models using available code quickly. The training data for ML models, often regarded as private property e.g., clinical records, transaction information, is at...

SQUIRO: A Framework for Security-Aware Quantum-Classical Scheduling on Kubernetes

Distributed infrastructure schedulers traditionally optimise capacity, locality, and cost, but provide limited support for security posture and emerging quantum-classical workloads. As hybrid quantum-classical computing becomes increasingly practical and post-quantum security requirements begin t...

DoSQ: A Cross-Layer Denial of Service Quality Attack by Exploiting Side Channels in 5G NR

The 3rd Generation Partnership Project 3GPP's Fifth Generation New Radio 5G NR is critical to supporting mission-critical services. However, 5G systems are vulnerable to smart jamming attacks that can propagate to applications running on top of these networks i.e., cross-layer. The 5G gNB...

DICOMHawk: A Cyber Deception Framework for Medical Imaging Infrastructure

Cyber-attacks against exposed healthcare infrastructure threaten sensitive patient data and clinical operations, yet existing defensive tools for DICOM-based medical imaging systems provide limited interaction and are easily fingerprinted. We introduce DICOMHawk, a cyber-deception framework that...

Natural Backdoor Attacks on Speech Recognition Models

With the rapid development of deep learning, its vulnerability has gradually emerged in recent years. This work focuses on backdoor attacks on speech recognition systems. We adopt sounds that are ordinary in nature or in our daily life as triggers for natural backdoor attacks. We conduct...

Fuzz'EMup: Leveraging EM Side-Channel Emanation to Guide Black-Box Embedded Firmware Fuzzing

As IoT and embedded devices proliferate across various domains, securing their firmware has become critical. Fuzzing offers a systematic approach to uncovering vulnerabilities in firmware, and coverage feedback can improve its effectiveness by guiding exploration. However, many devices make...

Towards Secure and Trustworthy DAOs for Cross-Chain Governance

Cross-chain DAOs face unique security challenges that go beyond traditional single-chain vulnerabilities. This paper identifies and categorizes four critical attack vectors in cross-chain DAO governance: bribery attacks, token control exploits, human-computer interaction deceptions, and protocol...

Signal-Based Model Access Risk Analysis for AI System Operations Security

Artificial intelligence AI systems are now ubiquitous across domains such as security, finance, healthcare, consumer technology, and large-scale cloud services, where they process massive volumes of data and make consequential decisions daily. This widespread adoption has created a broad attack...

Converging Safety and Security: IO-Link Wireless and OPC UA over 5G under PrEN 50742

The integration of wireless communication technologies in industrial automation offers greater flexibility, but also exposes safety systems to a broader threat vector. Emerging regulations, such as the draft standard prEN 50742, mandate the convergence of functional safety and cybersecurity by...

Vogls: A Fast Interactive Full-Timing Simulator for Pre-Silicon Power Side-Channel Analysis

Designing hardware circuits resistant to side-channel attacks increasingly relies on simulation to predict device leakage before fabrication. Current functional verification simulators are designed for extended correctness-checking runs and are ill-suited for producing large numbers of short trac...

Routing Ceilings Are Domain-Independent: Structural Prior Injection in Code Security Vulnerability Detection

Large language models LLMs exhibit a well-documented gap between latent capability and consistent activation: the router hypothesis posits that models possess the knowledge to solve a task but lack reliable internal routing to activate it. Prior work in formal mathematical reasoning SAIR, C�zares...

Bad Memory: Evaluating Prompt Injection Risks from Memory in Agentic Systems

A growing class of agentic systems maintain persistent state across sessions through memory files, behavioral preferences, and knowledge bases. While this makes agents more useful and self-improving, it also creates a new attack surface for prompt injections in which malicious instructions can be...

Specter 1.0 NFC Reader / Skimmer Bug-Sweep

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...

Setup Complete, Now You Are Compromised: Weaponizing Setup Instructions against AI Coding Agents

AI coding agents set up projects by reading documentation and installing the dependencies it lists, without verifying their names, sources, or known vulnerabilities. By editing only a README, requirements file, or Makefile, an attacker can redirect the agent to an untrusted registry, a...

Joern 4.0.582

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...

MemPoison: Uncovering Persistent Memory Threats and Structural Blind Spots in LLM Agents

Persistent external memory enhances agent continuity but introduces persistent security vulnerabilities: adversarial content can be injected via standard interaction channels, retained across turns, and later distort downstream behavior. To address this challenge, we propose MemPoison, a...

FlowGuard: From Signals to Evidence for MCP Security Detection

The Model Context Protocol MCP enables LLM agents to interact with external tools through metadata exchange, tool invocation, and response consumption. Existing MCP security scanners primarily reason about suspicious semantic signals rather than real execution behaviors, which can lead to...

Xalgorix Autonomous AI Pentesting Agent 4.5.62

Most scanners detect. Xalgorix proves. An autonomous LLM agent works a full pentest methodology, then an independent verifier re-exploits every finding before it's reported - so you get proof, not a pile of maybes to triage. Self-hosted, private, and bring-your-own-LLM. Built in Go + TypeScript...

SonicWall SMA1000 Series SSRF Detection Tool

A safe detection tool for identifying CVE-2026-15409 affecting SonicWall SMA1000 Series appliances. The Python utility performs non-destructive checks by issuing requests to common application endpoints using an external test URL and reports indicators of possible server-side request forgery...

RedAmon 6.0.2

An autonomous AI framework that chains reconnaissance, exploitation, and post-exploitation into a single pipeline, then goes further by triaging every finding, implementing code fixes, and opening pull requests on your repository. From first packet to merged patch, with human oversight at every...

Beyond Success Rate: Cost-Aware Evaluation of Offensive and Defensive Security Agents

Security-agent evaluations commonly measure peak offensive capability under generous inference budgets, emphasizing vulnerability discovery, exploit development, penetration testing, and CTF completion. Such measurements are useful but incomplete: in operational security, every reasoning step, to...