AI-Assisted Design of a Post-Quantum Cryptographic Accelerator: A Deployed-Silicon Case Study

Post-quantum migration is mandated on published timelines, and silicon that ships with a defect cannot be patched remotely. The standard acceptance gate cannot detect an entire class of ML-DSA defects. Signing resamples until a candidate meets its norm bounds, so the executed path varies with the...

An Emulation Anchored Digital Twin Testbed for Cyberattack and Defense Analysis in Hospital IT OT Environments

Modern hospitals increasingly rely on integrated Information Technology IT and Operational Technology OT infrastructures to support critical healthcare services. However, this convergence expands the cybersecurity attack surface and makes safe validation of defensive mechanisms difficult on live...

Description-Code Inconsistency in Real-World MCP Servers: Measurement, Detection, and Security Implications

The Model Context Protocol MCP has emerged as a critical standard empowering Large Language Models LLMs to utilize external tools. In this ecosystem, LLMs rely on natural language descriptions provided by MCP servers to select and execute functions. This interaction implicitly assumes that tool...

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...

Terminal Wrench: A Dataset of 331 Reward-Hackable Environments and 3,632 Exploit Trajectories

The authors of this paper release Terminal Wrench, a subset of 331 terminal-agent benchmark environments, copied from the popular open benchmarks that are demonstrably reward-hackable. The data set includes 3,632 hack trajectories and 2,352 legitimate baseline trajectories across three frontier...

Cybersecurity Skills in New Graduates: A Philippine Perspective

This study investigates the key skills and competencies needed by new cybersecurity graduates in the Philippines for entry-level positions. Using a descriptive cross-sectional research design, it combines analysis of job listings from Philippine online platforms with surveys of students, teachers...

HarmQ: Harmonic Backdoor Attacks against Quantum Neural Networks

Quantum Neural Networks QNNs have emerged as a promising paradigm for quantum machine learning in the Noisy Intermediate-Scale Quantum NISQ era, leveraging quantum phenomena such as superposition and entanglement to process information in exponentially large Hilbert spaces. However, QNNs inherit...

GNSS Spoofing Threat for V2X Communications

Global Navigation Satellite Systems GNSS constitute a core technology for delivering crucial positioning, navigation, and timing PNT services in the Vehicle-to-Everything V2X domain, where they are indispensable for generating Cooperative Awareness Messages CAM that uphold network reliability and...

PhantomSkill: Malicious Code Injection in Agent Skill Ecosystems

Agent skills allow LLM-based coding agents to acquire domain-specific capabilities from third-party packages, but they also introduce a new supply-chain attack surface. We present PhantomSkill, an attack framework that hides malicious behavior in a skill's auxiliary resources rather than in its...

Espanso 2.3.0 Configuration Security Auditor

This Python script implements a security auditing tool for Espanso configuration files. The EspansoSecurityAuditor class scans Espanso match configurations for potentially dangerous shell commands, insecure permissions, and suspicious execution patterns that could indicate malicious automation or...

Poking around in the Dark: Why a Shared Understanding of Components Matters

By listing the components included in an application, Software Bills of Materials SBOMs are intended to support the timely identification of vulnerable components and ensure the security of the software supply chain. However, we question the underlying assumption that there is agreement on the...

Persona Attack: Incremental Memory Injection Jailbreak Attack against Large Language Models

As Large Language Models evolve for user convenience, vulnerability to jailbreak attacks continues to be reported despite ongoing efforts in safety training. Traditional jailbreak techniques typically focus on a single prompt injection, neglecting the models' ability to remember the flow of...

Insights into Security-Related AI-Generated Pull Requests

Recent years have experienced growing contributions of AI coding agents that assist human developers in various software engineering tasks. However, this growing AI-assisted autonomy raises questions about security and trust. In this paper, we analyze more than 33,000 AI-generated pull requests P...

Automating Agent Hijacking Via Structural Template Injection

Agent hijacking, highlighted by OWASP as a critical threat to the Large Language Model LLM ecosystem, enables adversaries to manipulate execution by injecting malicious instructions into retrieved content. Most existing attacks rely on manually crafted, semantics-driven prompt manipulation, which...

Large Language Models Cannot Reliably Detect Vulnerabilities in JavaScript: The First Systematic Benchmark and Evaluation

Researchers have proposed numerous methods to detect vulnerabilities in JavaScript, especially those assisted by Large Language Models LLMs. However, the actual capability of LLMs in JavaScript vulnerability detection remains questionable, necessitating systematic evaluation and comprehensive...

Hiding in the AI Traffic: Abusing MCP for LLM-Powered Agentic Red Teaming

Generative AI is reshaping offensive cybersecurity by enabling autonomous red team agents that can plan, execute, and adapt during penetration tests. However, existing approaches face trade-offs between generality and specialization, and practical deployments reveal challenges such as...

SASER: Stego Attacks on Open-Source LLMs

Open-source large language models LLMs have demonstrated considerable dominance over proprietary LLMs in resolving neural processing tasks, thanks to the collaborative and sharing nature. Although full access to source codes, model parameters, and training data lays the groundwork for transparenc...

Mind the Gap: Robustness Risks in PII Detection Systems

Personally Identifiable Information PII detection is a foundational component of data protection infrastructure where missed entities constitute direct privacy and security risks. Although modern PII systems report strong performance on standard benchmarks, we show that these evaluations mask...

Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response

Cyber-capable AI agents combine language models with tools, memory, and execution en- vironments to perform multi-step offensive-security tasks. Existing work separately measures cyber capability and catalogs attacks against agent components, but provides less guidance on containing a capable age...

FROST: Fingerprinting Remotely Using OPFS-based SSD Timing

Prior work showed that variations in SSD access time can be used to leak information about user activity, e.g., the websites a user accesses, and for covert data transmission. To achieve this, SSD contention side channels require accurate high-resolution timing measurements of I/O operations, e.g...

APT-Agent: Automated Penetration Testing Using Large Language Models

Penetration testing is essential to securing modern web infrastructures, yet traditional manual methods struggle to keep pace with their scale and complexity. Large Language Models LLMs offer new opportunities for automating these tasks, but existing approaches face two persistent challenges:...

PickleFuzzer: A Case Study in Fuzzing for Discrepancies between Python Pickle Implementations

Python's native serialization protocol, pickle, is a powerful but insecure format for transferring untrusted data. It is frequently used, especially for saving machine learning models, despite known security challenges. While developers sometimes mitigate this risk by restricting imports during...

TGL-APT: Temporal Graph Learning with Graph Distillation for Efficient APT Investigation

Advanced Persistent Threat APT attacks pose a critical challenge to modern systems, as their stealthy, multi-stage nature renders conventional detection methods ineffective. While provenance graphs provide rich behavioral context for attack investigation, attack-relevant evidence is often sparse...

StealthBench: Measuring Operational Stealth in Autonomous Offensive-Security Agents

Stealth, the discipline of achieving an objective without revealing your presence, capabilities, or collected intelligence, is what separates sophisticated operators from detectable ones. Elite security researchers and advanced persistent threats achieve their objectives unnoticed; autonomous...

SecureForge: Finding and Preventing Vulnerabilities in LLM-Generated Code Via Prompt Optimization

LLM coding agents now generate code at an unprecedented scale, yet LLM-generated code introduces cybersecurity vulnerabilities into codebases without human involvement. Even when frontier models are explicitly asked to write secure production code with relevant weaknesses to avoid in context, we...

Kill-Chain Canaries: Stage-Level Tracking of Prompt Injection across Attack Surfaces and Model Safety Tiers

We present a stage-decomposed analysis of prompt injection attacks against five frontier LLM agents. Prior work measures task-level attack success rate ASR; we localize the pipeline stage at which each model's defense activates. We instrument every run with a cryptographic canary token...

AXE: An Agentic EXploit Engine for Confirming Zero-Day Vulnerability Reports

Vulnerability detection tools are widely adopted in software projects, yet they often overwhelm maintainers with false positives and non-actionable reports. Automated exploitation systems can help validate these reports; however, existing approaches typically operate in isolation from detection...

EchoLeak: the First Real-World Zero-Click Prompt Injection Exploit in a Production LLM System

Large language model LLM assistants are increasingly integrated into enterprise workflows, raising new security concerns as they bridge internal and external data sources. This paper presents an in-depth case study of EchoLeak CVE-2025-32711, a zero-click prompt injection vulnerability in Microso...

SHADE-Arena: Evaluating Sabotage and Monitoring in LLM Agents

As Large Language Models LLMs are increasingly deployed as autonomous agents in complex and long horizon settings, it is critical to evaluate their ability to sabotage users by pursuing hidden objectives. We study the ability of frontier LLMs to evade monitoring and achieve harmful hidden goals...

WeClawArena: An Auditable Sandbox and Benchmark for Cross-User Agents Collaboration and Security in Human-Centered Agent Networks

Recent advances in persistent personal-agent frameworks are making human-centered agent networks realistic deployment targets: each user can be served by an AI agent that acts on the user's behalf, maintains state, and communicates with other agents through social and task relations. In these...

Code-Augur: Agentic Vulnerability Detection Via Specification Inference

The advent of agentic vulnerability detection is already becoming a watershed moment for software security. Audits conducted entirely by autonomous LLM agents are uncovering critical vulnerabilities in fundamental software underpinning digital society. Many of these vulnerabilities remained maske...

Zero Knowledge (About) Encryption: A Comparative Security Analysis of Three Cloud-based Password Managers

Zero Knowledge Encryption is a term widely used by vendors of cloud-based password managers. Although it has no strict technical meaning, the term conveys the idea that the server, who stores encrypted password vaults on behalf of users, is unable to learn anything about the contents of those...

HogVul: Black-Box Adversarial Code Generation Framework against LM-Based Vulnerability Detectors

Recent advances in software vulnerability detection have been driven by Language Model LM-based approaches. However, these models remain vulnerable to adversarial attacks that exploit lexical and syntax perturbations, allowing critical flaws to evade detection. Existing black-box attacks on...

Breaking ECDSA with Electromagnetic Side-Channel Attacks: Challenges and Practicality on Modern Smartphones

Smartphones handle sensitive tasks such as messaging and payment and may soon support critical electronic identification through initiatives such as the European Digital Identity EUDI wallet, currently under development. Yet the susceptibility of modern smartphones to physical side-channel analys...

Experimental Protocol Fingerprinting in Quantum Networks Via Physical Layer Side Channel Analysis

Quantum communication is a key enabler of next-generation networks, leveraging quantum entanglement to enable a new class of information exchange. While prior work has focused on the theoretical analysis of communication protocols, their exposure to physical layer side channel analysis remains...

An Automated Framework for Extracting Reachable Attack Chains from Cyber Threat Intelligence Reports

Cyber Threat Intelligence CTI reports richly describe real-world attack processes, but their unstructured narratives cannot be directly used for automated attack-path reasoning. Existing CTI extraction methods focus on indicators, entities, or TTP labels without modeling the execution conditions...

Secret Stealing Attacks on Local LLM Fine-Tuning through Supply-Chain Model Code Backdoors

Local fine-tuning datasets routinely contain sensitive secrets such as API keys, personal identifiers, and financial records. Although ''local offline fine-tuning'' is often viewed as a privacy boundary, we reveal that compromised model code is sufficient to steal them. Current passive...

Security Considerations for Artificial Intelligence Agents

This article, a lightly adapted version of Perplexity's response to NIST/CAISI Request for Information 2025-0035, details our observations and recommendations concerning the security of frontier AI agents. These insights are informed by Perplexity's experience operating general-purpose agentic...

A Systematization of Security Vulnerabilities in Computer Use Agents

Computer Use Agents CUAs, autonomous systems that interact with software interfaces via browsers or virtual machines, are rapidly being deployed in consumer and enterprise environments. These agents introduce novel attack surfaces and trust boundaries that are not captured by traditional threat...

SAEFUZZ: Smart Contract Vulnerability Detection through Statically Guided Evolutionary Fuzzing

The effectiveness of smart contract fuzzing depends strongly on whether generated transactions reach deep, state-dependent execution paths. Existing fuzzers often generate highly random call sequences, wasting executions on semantically invalid or low-value states and leaving vulnerabilities that...

PTSan: A Practical Memory Safety Sanitizer for C/C++ with Pointer-Object Authority

Memory safety errors remain the dominant source of severe vulnerabilities in C and C++. Pointer-based sanitizers provide stronger guarantees than location-based tools such as LLVM's ASan, but their overhead and compatibility limitations have constrained production use. We present PTSan, an LLVM...

RAVEN: Agentic RAG for Automated Vulnerability Repair

Automated vulnerability repair has emerged as a promising direction to mitigate the growing number of software vulnerabilities. Recent advances in Large Language Models LLMs have further accelerated research in automated repair. However, existing frameworks remain largely restricted to...

Is Vibe Coding Safe? Benchmarking Vulnerability of Agent-Generated Code in Real-World Tasks

Vibe coding is a new programming paradigm in which human engineers instruct large language model LLM agents to complete complex coding tasks with little supervision. Although it is increasingly adopted, are vibe coding outputs really safe to deploy in production? To answer this question, we propo...

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...

(A)I Sees What You Don't: Exploiting New Attack Surfaces in Third-Party Mobile Agents

Third-party mobile agents powered by Vision-Language Models VLMs have emerged as a promising paradigm for automating smartphone interactions. These agents act as high-privilege decision-makers, perceiving device states through screenshots and executing actions via VLM reasoning, transforming how ...

AWE: Adaptive Agents for Dynamic Web Penetration Testing

Modern web applications are increasingly produced through AI-assisted development and rapid no-code deployment pipelines, widening the gap between accelerating software velocity and the limited adaptability of existing security tooling. Pattern-driven scanners fail to reason about novel contexts,...

APT-ClaritySet: A Large-Scale, High-Fidelity Labeled Dataset for APT Malware with Alias Normalization and Graph-Based Deduplication

Large-scale, standardized datasets for Advanced Persistent Threat APT research are scarce, and inconsistent actor aliases and redundant samples hinder reproducibility. This paper presents APT-ClaritySet and its construction pipeline that normalizes threat actor aliases reconciling approximately...

Jailbreak Mimicry: Automated Discovery of Narrative-Based Jailbreaks for Large Language Models

Large language models LLMs remain vulnerable to sophisticated prompt engineering attacks that exploit contextual framing to bypass safety mechanisms, posing significant risks in cybersecurity applications. We introduce Jailbreak Mimicry, a systematic methodology for training compact attacker mode...

The Art of Hide and Seek: Making Pickle-Based Model Supply Chain Poisoning Stealthy Again

Pickle deserialization vulnerabilities have persisted throughout Python's history, remaining widely recognized yet unresolved. Due to its ability to transparently save and restore complex objects into byte streams, many AI/ML frameworks continue to adopt pickle as the model serialization protocol...

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...