Academic papers, new techniques, benchmarks, and theoretical findings in AI/LLM security.
FlexDPI is a system for deep packet inspection (DPI, where network traffic is examined in detail to monitor what data is being sent) that aims to protect user privacy while still allowing network monitoring. The research presents a method that lets users choose which security rules apply to their traffic, while using verification techniques to ensure the system works correctly without exposing sensitive information.
This academic paper proposes a new authentication system that combines blockchain (a distributed ledger technology that records data across many computers) with privacy protection methods for military surveillance applications in 6G (the next generation of wireless networks). The framework is designed to allow secure identification and verification of users while keeping their personal information hidden from unauthorized access.
BEdX25519 is a lightweight authenticated key exchange protocol (a method for two devices to securely agree on encryption keys) designed for IoT (Internet of Things) devices to communicate directly with each other using blockchain (a distributed ledger technology) and elliptic curve cryptography (a type of mathematical encryption based on curves). The protocol aims to make secure device-to-device communication more efficient for resource-constrained IoT systems.
This academic paper, published in September 2026, describes a method for securely accessing encrypted data using hardware tokens (physical devices that store security credentials). The research presents a scheme designed to protect data while allowing authorized users to access it through these specialized hardware devices.
This academic paper describes a method for protecting videos using watermarking (a technique that embeds hidden information into media to prove ownership or detect tampering) by applying multiple mathematical transformations to make the watermark resistant to attacks. The research, published in November 2026, proposes using orthogonal transformations (mathematical operations that preserve certain properties) in combination to create a hybrid approach that is harder for attackers to remove or corrupt.
This academic paper proposes an improved authentication scheme for IoV (Internet of Vehicles, where connected cars communicate with each other and infrastructure) based on an enhanced BLS signature algorithm (a cryptographic method for verifying that a message came from a legitimate source). The research focuses on making vehicle authentication more efficient while maintaining security for connected vehicle systems.
This is a research paper about a new method for protecting images by combining compression (making files smaller) and encryption (scrambling data so only authorized people can read it) using a 2D coupled chaotic map (a mathematical technique that creates unpredictable patterns). The paper proposes an algorithm that allows the encrypted images to be traced or verified, adding an extra security layer beyond standard image protection.
This academic paper describes a new cryptographic method called revocable predicate encryption for inner products (a mathematical operation that combines two vectors), built using dual pairing vector space (a mathematical structure for encryption). The research presents a theoretical approach to encryption that allows certain access rights to be revoked, or taken away, after they've been granted, while maintaining security properties.
This research paper presents a framework that combines reversible data hiding (a technique to hide information within data while being able to completely restore the original data later) with homomorphic encryption (encryption that allows computations to be performed on encrypted data without decrypting it first). The approach is designed to work with dispersed data (information spread across multiple locations or systems) and offers a general method that could be applied to various scenarios.
N/A -- This is a research publication about image watermarking (hiding data inside images) using statistical modeling techniques, not an AI/LLM security issue, vulnerability, or incident.
Researchers have developed a new authentication and key agreement protocol (a method for securely verifying users and establishing encrypted connections) that combines PUF (physical unclonable functions, unique hardware fingerprints that cannot be copied) and biometrics (biological traits like fingerprints) to allow users to maintain secure sessions while moving between different systems or networks. The protocol is designed to preserve anonymity while enabling seamless handover across domains (separate security zones or organizations).
This research paper proposes a watermarking-based intrusion detection system for CAN bus (Controller Area Network, a communication system used in vehicles and industrial equipment) that uses dynamic wavelet analysis to detect malicious messages and resist attacks on the detection model itself. The system aims to protect CAN bus communications from unauthorized access and manipulation while remaining robust against adversarial attacks (attempts to fool the security system).
PriSat is a research paper about directed greybox fuzzing (a testing technique that automatically finds bugs by generating random inputs while using code structure information to guide the search). The work focuses on improving how fuzzing tools prioritize which program paths to explore, specifically by ensuring critical conditions are satisfied first. This approach aims to make automated bug-finding more efficient by helping testing tools discover vulnerabilities faster.
Researchers developed a predictive model to identify which people are most vulnerable to online scams by analyzing personality traits and other characteristics. The study, published in November 2026, used cross-validation (a technique where a model is tested on different sets of data to ensure it works reliably) to build a model that can help predict susceptibility to scams before they happen. This research could help protect people by identifying who might need extra education or awareness about scam tactics.
This research paper introduces HFAMA (Heuristics Framework for Authenticating Mobile Applications), a method designed to improve security in mobile apps by using pattern-based rules to verify that applications are legitimate and trustworthy. The framework aims to create a more resilient cybersecurity environment by helping protect mobile devices from fraudulent or malicious applications.
This academic paper presents a new model for IT audit risk assessment that combines bow-tie analysis (a visual diagram showing how failures can happen and their consequences) with fuzzy Bayesian networks (a statistical method that handles uncertain or imprecise information to calculate probabilities). The model aims to help organizations better identify and evaluate security risks during IT audits by combining these two analytical approaches.
This academic paper discusses extending ATT&CK (a framework that catalogs adversary tactics and techniques used in real attacks) coverage within logical attack graphs (visual models showing how attackers could chain multiple steps together to compromise a system). The research, published in November 2026, appears to focus on improving how security professionals can map and understand attack paths using this framework.
This academic paper describes a method for protecting closed-source drivers (software that controls hardware devices) by using a multidimensional domain switch (a technique that isolates code execution across different security contexts). The research was published in November 2026 in the journal Computers & Security and proposes a protective approach for drivers that manufacturers keep proprietary.
SAFARI is a framework designed to investigate ransomware (malicious software that encrypts files and demands payment) in an air-gapped environment (a computer system isolated from networks for security). The framework automates the process of analyzing how ransomware behaves and spreads, making it easier to study these threats safely without risking network infection.
Researchers discovered that STUN (Session Traversal Utilities for NAT, a protocol that helps devices communicate through network firewalls) can be misused as a covert channel by hiding secret data in optional message attributes that receivers can ignore. The study describes how this attack works, shows a working proof-of-concept implementation, and presents methods to detect when STUN is being used this way.