Securing the Model Context Protocol: Defending LLMs against Tool Poisoning and Adversarial Attacks

The Model Context Protocol MCP enables Large Language Models to integrate external tools through structured descriptors, increasing autonomy in decision-making, task execution, and multi-agent workflows. However, this autonomy creates a largely overlooked security gap. Existing defenses focus on...

AgenticCyber: A GenAI-Powered Multi-Agent System for Multimodal Threat Detection and Adaptive Response in Cybersecurity

The increasing complexity of cyber threats in distributed environments demands advanced frameworks for real-time detection and response across multimodal data streams. This paper introduces AgenticCyber, a generative AI powered multi-agent system that orchestrates specialized agents to monitor...

BEACON: A Unified Behavioral-Tactical Framework for Explainable Cybercrime Analysis with Large Language Models

Cybercrime increasingly exploits human cognitive biases in addition to technical vulnerabilities, yet most existing analytical frameworks focus primarily on operational aspects and overlook psychological manipulation. This paper proposes BEACON, a unified dual-dimension framework that integrates...

Characterizing Large-Scale Adversarial Activities through Large-Scale Honey-Nets

The increasing sophistication of cyber threats demands novel approaches to characterize adversarial strategies, particularly those targeting critical infrastructure and IoT ecosystems. This paper presents a longitudinal analysis of attacker behavior using HoneyTrap, an adaptive honeypot framework...

LLM Causality Analysis Framework

A comprehensive framework for multi-level causality analysis in Large Language Models LLMs, enabling systematic investigation of safety mechanisms and misbehavior detection across token, neuron, layer, and representation levels. Includes the whitepaper 2512.04841.pdf titled SoK: A Comprehensive...

Sift or Get off the PoC: Applying Information Retrieval to Vulnerability Research with SiftRank

Security research is fundamentally a problem of resource constraint and consequent prioritization. There is simply too much attack surface and too little time and energy to spend analyzing it all. The most effective security researchers are often those who are most skilled at intuitively deciding...

Transmission Integer Overflow

2017 research from Google where Tavis found that transmission suffered from various integer overflows when parsing torrent files...

Adobe Acrobat Force-Installed Vulnerable Chrome Extension

Back in 2017, Adobe Acrobat force-installed a vulnerable chrome extension susceptible to cross site scripting...

Frequency-Matching Quantum Key Distribution

Quantum key distribution QKD enables information-theoretically secure communication against eavesdropping. However, phase instability remains a challenge across many QKD applications, particularly in schemes such as twin-field QKD and measurement-device-independent QKD. The most dominant source o...

MalwareBytes Missing Signing / Privilege Escalation

This is older research from 2016 when Google found that MalwareBytes failed to sign packages and download them over a secure channel as well as various other security issues...

The Road of Adaptive AI for Precision in Cybersecurity

Cybersecurity's evolving complexity presents unique challenges and opportunities for AI research and practice. This paper shares key lessons and insights from designing, building, and operating production-grade GenAI pipelines in cybersecurity, with a focus on the continual adaptation required to...

Nuclei 3.6.0

Nuclei is a modern, high-performance vulnerability scanner that leverages simple YAML-based templates. It empowers you to design custom vulnerability detection scenarios that mimic real-world conditions, leading to zero false positives...

TeleAI-Safety: A Comprehensive LLM Jailbreaking Benchmark Towards Attacks, Defenses, and Evaluations

While the deployment of large language models LLMs in high-value industries continues to expand, the systematic assessment of their safety against jailbreak and prompt-based attacks remains insufficient. Existing safety evaluation benchmarks and frameworks are often limited by an imbalanced...

Beyond Detection: A Comprehensive Benchmark and Study on Representation Learning for Fine-Grained Webshell Family Classification

Malicious WebShells pose a significant and evolving threat by compromising critical digital infrastructures and endangering public services in sectors such as healthcare and finance. While the research community has made significant progress in WebShell detection i.e., distinguishing malicious...

A Practical Honeypot-Based Threat Intelligence Framework for Cyber Defence in the Cloud

In cloud environments, conventional firewalls rely on predefined rules and manual configurations, limiting their ability to respond effectively to evolving or zero-day threats. As organizations increasingly adopt platforms such as Microsoft Azure, this static defense model exposes cloud assets to...

Hybrid Quantum-Classical Autoencoders for Unsupervised Network Intrusion Detection

Unsupervised anomaly-based intrusion detection requires models that can generalize to attack patterns not observed during training. This work presents the first large-scale evaluation of hybrid quantum-classical HQC autoencoders for this task. We construct a unified experimental framework that...

Safe2Harm: Semantic Isomorphism Attacks for Jailbreaking Large Language Models

Large Language Models LLMs have demonstrated exceptional performance across various tasks, but their security vulnerabilities can be exploited by attackers to generate harmful content, causing adverse impacts across various societal domains. Most existing jailbreak methods revolve around Prompt...

ASTRIDE: A Security Threat Modeling Platform for Agentic-AI Applications

AI agent-based systems are becoming increasingly integral to modern software architectures, enabling autonomous decision-making, dynamic task execution, and multimodal interactions through large language models LLMs. However, these systems introduce novel and evolving security challenges, includi...

A Novel Trust-Based DDoS Cyberattack Detection Model for Smart Business Environments

As the frequency and complexity of Distributed Denial-of-Service DDoS attacks continue to increase, the level of threats posed to Smart Internet of Things SIoT business environments have also increased. These environments generally have several interconnected SIoT systems and devices that are...

PBFuzz: Agentic Directed Fuzzing for PoV Generation

Proof-of-Vulnerability PoV input generation is a critical task in software security and supports downstream applications such as path generation and validation. Generating a PoV input requires solving two sets of constraints: 1 reachability constraints for reaching vulnerable code locations, and ...

BGPFuzz: Automated Configuration Fuzzing of the Border Gateway Protocol

Telecommunications networks rely on configurations to define routing behavior, especially in the Border Gateway Protocol BGP, where misconfigurations can lead to severe outages and security breaches, as demonstrated by the 2021 Facebook outage. Unlike existing approaches that rely on synthesis or...

CISA: Principles for the Secure Integration of Artificial Intelligence in Operational Technology

Artificial intelligence AI has the potential to increase efficiency and productivity, enhance decision-making, cut costs and improve customer experience, but introducing AI in operational technology OT environments can introduce risks that require careful management to support the safety, securit...

React 19.0 / 19.1.0 / 19.1.1 / 19.2.0 Remote Code Execution

On November 29th, Lachlan Davidson reported a security vulnerability in React that allows unauthenticated remote code execution by exploiting a flaw in how React decodes payloads sent to React Server Function endpoints. Even if your app does not implement any React Server Function endpoints it ma...

Wireshark Analyzer 4.6.2

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...

WildCode: An Empirical Analysis of Code Generated by ChatGPT

LLM models are increasingly used to generate code, but the quality and security of this code are often uncertain. Several recent studies have raised alarm bells, indicating that such AI-generated code may be particularly vulnerable to cyberattacks. However, most of these studies rely on code that...

A Comprehensive Study on the Impact of Vulnerable Dependencies on Open-Source Software

Open-source libraries are widely used by software developers to speed up the development of products, however, they can introduce security vulnerabilities, leading to incidents like Log4Shell. With the expanding usage of open-source libraries, it becomes even more imperative to comprehend and...

The Treasury Proof Ledger: A Cryptographic Framework for Accountable Bitcoin Treasuries

Public companies and institutional investors that hold Bitcoin face increasing pressure to show solvency, manage risk, and satisfy regulatory expectations without exposing internal wallet structures or trading strategies. This paper introduces the Treasury Proof Ledger TPL, a Bitcoin-anchored...

Primitive Vector Cipher(PVC): A Hybrid Encryption Scheme Based on the Vector Computational Diffie-Hellman (V-CDH) Problem

This work introduces the Primitive Vector Cipher PVC, a novel hybrid encryption scheme integrating matrix-based cryptography with advanced Diffie-Hellman key exchange. PVC's security is grounded on the established hardness of the Vector Computational Diffie- Hellman V-CDH problem. The two-layered...

ReFuzz: Reusing Tests for Processor Fuzzing with Contextual Bandits

Processor designs rely on iterative modifications and reuse well-established designs. However, this reuse of prior designs also leads to similar vulnerabilities across multiple processors. As processors grow increasingly complex with iterative modifications, efficiently detecting vulnerabilities...

Breaking Isolation: A New Perspective on Hypervisor Exploitation Via Cross-Domain Attacks

Hypervisors are under threat by critical memory safety vulnerabilities, with pointer corruption being one of the most prevalent and severe forms. Existing exploitation frameworks depend on identifying highly-constrained structures in the host machine and accurately determining their runtime...

Unfolding Challenges in Securing and Regulating Unmanned Air Vehicles

Unmanned Aerial Vehicles UAVs or drones are being introduced in a wide range of commercial applications. This has also made them prime targets of attackers who compromise their fundamental security properties, including confidentiality, integrity, and availability. As researchers discover novel...

A Descriptive Model for Modelling Attacker Decision-Making in Cyber-Deception

Cyber-deception is an increasingly important defensive strategy, shaping adversarial decision making through controlled misinformation, uncertainty, and misdirection. Although game-theoretic, Bayesian, Markov decision process, and reinforcement learning models offer insight into deceptive...

Periodic Directory Security Audit 1.0

This code enables persistence via the /etc/periodic directory similarly to recent metasploit modules that perform the same function. This is a variant written in PHP...

One Detector Fits All: Robust and Adaptive Detection of Malicious Packages from PyPI to Enterprises

The rise of supply chain attacks via malicious Python packages demands robust detection solutions. Current approaches, however, overlook two critical challenges: robustness against adversarial source code transformations and adaptability to the varying false positive rate FPR requirements of...

Adversarial Limits of Quantum Certification: When Eve Defeats Detection

Security of quantum key distribution QKD relies on certifying that observed correlations arise from genuine quantum entanglement rather than eavesdropper manipulation. Theoretical security proofs assume idealized conditions, practical certification must contend with adaptive adversaries who...

Learning the Wrong Lessons: Syntactic-Domain Spurious Correlations in Language Models

Whitepaper from researchers at MIT, Northeastern University, and Meta. For an LLM to correctly respond to an instruction it must understand both the semantics and the domain i.e., subject area of a given task-instruction pair. However, syntax can also convey implicit information Recent work shows...

A Wolf in Sheep's Clothing: Bypassing Commercial LLM Guardrails Via Harmless Prompt Weaving and Adaptive Tree Search

Large language models LLMs remain vulnerable to jailbreak attacks that bypass safety guardrails to elicit harmful outputs. Existing approaches overwhelmingly operate within the prompt-optimization paradigm: whether through traditional algorithmic search or recent agent-based workflows, the...

Decryption Thorough Polynomial Ambiguity: Noise-Enhanced High-Memory Convolutional Codes for Post-Quantum Cryptography

We present a novel approach to post-quantum cryptography that employs directed-graph decryption of noise-enhanced high-memory convolutional codes. The proposed construction generates random-like generator matrices that effectively conceal algebraic structure and resist known structural attacks...

Cybersecurity AI: The World's Top AI Agent for Security Capture-The-Flag (CTF)

Are Capture-the-Flag competitions obsolete? In 2025, Cybersecurity AI CAI systematically conquered some of the world's most prestigious hacking competitions, achieving Rank 1 at multiple events and consistently outperforming thousands of human teams. Across five major circuits-HTB's AI vs Humans,...

S3C2 SICP Summit 2025-06: Vulnerability Response Summit

Recent years have shown increased cyber attacks targeting less secure elements in the software supply chain and causing significant damage to businesses and organizations. The US and EU governments and industry are equally interested in enhancing software security, including supply chain and...

Equilibrium SAT Based PQC: New Aegis against Quantum Computing

Public-key cryptography algorithms have evolved towards increasing computational complexity to hide desired messages, which is accelerating with the development of the Internet and quantum computing. This paper introduces a novel public-key cryptography algorithm that generates ciphertexts by...

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...

Physical ID-Transfer Attacks against Multi-Object Tracking Via Adversarial Trajectory

Multi-Object Tracking MOT is a critical task in computer vision, with applications ranging from surveillance systems to autonomous driving. However, threats to MOT algorithms have yet been widely studied. In particular, incorrect association between the tracked objects and their assigned IDs can...

INFERMAL: Inferential Analysis of Maliciously Registered Domains

Cybercriminals have long depended on domain names for phishing, spam, malware distribution, and botnet operation. To facilitate the malicious activities, they continually register new domain names for exploitation. Previous work revealed an abnormally high concentration of malicious registrations...

BackportBench: A Multilingual Benchmark for Automated Backporting of Patches

Many modern software projects evolve rapidly to incorporate new features and security patches. It is important for users to update their dependencies to safer versions, but many still use older, vulnerable package versions because upgrading can be difficult and may break their existing codebase...

AI-Driven Cybersecurity Testbed for Nuclear Infrastructure: Comprehensive Evaluation Using METL Operational Data

Advanced nuclear reactor systems face increasing cybersecurity threats as sophisticated attackers exploit cyber-physical interfaces to manipulate control systems while evading traditional IT security measures. This research presents a comprehensive evaluation of artificial intelligence approaches...

COGNITION: From Evaluation to Defense against Multimodal LLM CAPTCHA Solvers

This paper studies how multimodal large language models MLLMs undermine the security guarantees of visual CAPTCHA. We identify the attack surface where an adversary can cheaply automate CAPTCHA solving using off-the-shelf models. We evaluate 7 leading commercial and open-source MLLMs across 18...

WhiteLie: A Robust System for Spoofing User Data in Android Platforms

Android employs a permission framework that empowers users to either accept or deny sharing their private data for example, location with an app. However, many apps tend to crash when they are denied permission, leaving users no choice but to allow access to their data in order to use the app. In...

LeechHijack: Covert Computational Resource Exploitation in Intelligent Agent Systems

Large Language Model LLM-based agents have demonstrated remarkable capabilities in reasoning, planning, and tool usage. The recently proposed Model Context Protocol MCP has emerged as a unifying framework for integrating external tools into agent systems, enabling a thriving open ecosystem of...

Beyond the Hype: A Large-Scale Empirical Analysis of On-Chain Transactions in NFT Scams

Non-fungible tokens NFTs serve as a representative form of digital asset ownership and have attracted numerous investors, creators, and tech enthusiasts in recent years. However, related fraud activities, especially phishing scams, have caused significant property losses. There are many graph...