Research

TrustSearch is a system that performs reverse image search (finding similar images in a database) on encrypted data stored in the cloud while protecting user privacy. It uses Intel SGX (a trusted execution environment, which is a secure area on a processor where sensitive operations can run protected from outside access) to search images without decrypting them, but had to optimize its design because SGX has limited memory and processing resources.

This research proposes a new encryption method called registered attribute-based encryption (RABE, a cryptographic technique that controls who can access data based on their attributes rather than fixed keys) to protect electronic health records (medical data stored in the cloud) from privacy and security risks. The proposed system addresses key problems with existing RABE approaches by allowing permission changes without constantly re-encrypting data and by reducing the computational work required on users' devices to decrypt information.

This article examines how business leaders manage cybersecurity governance (the policies and processes that control how organizations handle security) by interviewing 31 financial sector executives. It identifies three main challenges: unclear responsibility and decision-making authority, misalignment between overall strategy and day-to-day security operations, and confusion about roles and expectations. The authors propose a CROA framework (cybersecurity responsibility, ownership and accountability) along with seven recommendations and a self-assessment tool to help executives strengthen organizational resilience (an organization's ability to withstand and recover from security incidents).

Researchers have developed a technique called Model X-Ray that can detect hidden malware embedded in AI model weights (the numerical parameters that make up a trained AI system) using few-shot learning (training a detector with only a small number of examples). This work addresses a security risk where attackers could hide malicious code inside AI models that might go undetected during normal use.

Researchers developed a new AI model called a Multi-Frequency Temporal Spatio-Transformer that can detect when attackers try to break into Internet of Things devices (IoT, everyday connected devices like smart home sensors). The model is designed to remain accurate even when attackers deliberately try to fool it using adversarial attacks (techniques that manipulate input data to trick AI systems into making wrong predictions). This research addresses the challenge of keeping IoT network security systems reliable against sophisticated attacks.

This is an academic survey article that reviews methods for making traditional machine learning models more explainable and interpretable across different fields. The survey covers techniques that help users understand how machine learning models make decisions, rather than treating them as "black boxes" where the reasoning is hidden. It was published in a peer-reviewed computer science journal in September 2026.

ATLAS v2026.05 introduces a major structural overhaul that separates versioning for content updates from format changes, moving to a new YAML format (v6.0.0) with improved consistency and relationship handling. The update adds support for multiple AI platforms (Predictive, Generative, Agentic, and Enterprise) to techniques and introduces new tooling including Pydantic schemas (strict data validation), SQLAlchemy ORM models (database storage), and a FastAPI REST API (web service for managing the data). Historical ATLAS releases have been migrated and preserved in the new structure.

N/A -- This content is a navigation menu and feature listing for GitHub v6.0.0, not a security issue or AI/LLM problem. It describes GitHub's product offerings (Copilot for code generation, Actions for automation, security tools) but contains no specific technical concern to analyze.

Researchers have developed PacketPatch, a method for creating adversarial packets (malicious network data designed to fool AI systems) that can deceive byte-feature-based encrypted traffic classification systems (AI models that identify what type of network traffic is flowing through encrypted connections by analyzing raw data patterns). The work demonstrates how attackers could potentially manipulate encrypted network communications to evade detection by these AI-powered security systems.

This academic paper explores using graph neural networks (machine learning models that analyze connected data structures) and adaptive partial disconnection (selectively cutting off connections in a network) as methods to stop malware from spreading through systems. The research, published in July 2026, presents these techniques as defensive strategies for protecting networks against malware propagation.

This is a research paper proposing a new multi-factor authentication (MFA, a security method requiring multiple forms of proof to verify a user's identity) system that adapts based on context. The paper, published in July 2026, suggests that authentication security can be improved by adjusting verification requirements based on factors like user location, device, and behavior patterns rather than using the same rigid security checks for everyone.

Researchers found security weaknesses in DIZY, an ultra-lightweight stream cipher (an encryption method designed for devices with limited computing power) designed to protect resource-constrained devices like RFID tags. The attacks show that DIZY-80 and DIZY-128 provide weaker security (65/86-bit levels) than claimed (80/112-bit levels) by exploiting how the cipher initializes. The researchers proposed an improved version called DIZYa that resists these attacks while maintaining the original design's advantages.

Facial manipulation techniques like face-swapping and face attribute editing (changing features in images) threaten privacy and identity security, but existing defense methods work poorly against both types of attacks in a unified way. Researchers developed EA-APO (Epoch-Adaptive Adversarial Perturbation Optimization), a defense framework that adds specially designed invisible noise patterns to face images to disrupt both face-swapping and attribute-editing AI models, even ones the defense hasn't seen before. The method was tested across multiple commercial facial manipulation tools and remained effective even after common image processing and social media compression.

This paper presents a method for performing skyline optimization (a technique that filters data to find the most important records based on multiple criteria) on encrypted data that is split across multiple locations in a vertical data federation (a system where different organizations each hold different columns of the same dataset). The researchers developed an asynchronous structured skyline predicate that improves both efficiency and security while protecting sensitive data from unauthorized access.

Researchers developed a new method to attack deep neural networks that analyze 3D point clouds (collections of data points representing 3D objects) by using cage-based deformation, which smoothly warps the entire shape rather than moving individual points. The method generates adversarial attacks (malicious inputs designed to fool AI systems) that look natural to humans while successfully tricking classifiers, and these attacks remain effective even against defense methods.

This research paper studies how to estimate discrete distributions (collections of data categories and their frequencies) while protecting sensitive information using utility-optimized local differential privacy (ULDP, a privacy protection method that keeps data private locally while allowing more accurate results for non-sensitive information). The authors mathematically prove the fundamental limits of this privacy-utility trade-off and propose new optimal mechanisms called utility-optimized block design schemes to achieve the best possible accuracy under these privacy constraints.

This paper presents MGRNet, a graph reasoning model (a method that uses network structures to understand relationships between data points) designed to improve multi-modal object re-identification (ReID, the task of matching the same object across different image types like visible and infrared photos). The approach handles low-quality local features by constructing modality-aware graphs (structures that represent relationships between image patches while accounting for different image types) and selectively swapping graph nodes to combine local and global information, ultimately creating more reliable object representations.

Federated Learning (FL, a technique where multiple computers train an AI model together without sharing raw data) faces security challenges from adversarial attacks (attempts to trick the model with carefully crafted inputs) and data heterogeneity (when each computer has different types of data). The paper introduces Fed-CDP (Federated Contrastive Diffusion Prototypes), a new approach that uses a server to actively synthesize improved features from client data rather than just collecting them, which helps make the shared model more robust against attacks and reduces model drift (when local models diverge from each other).

This research paper describes a defense technique called Infer-Shield that protects AI models trained across multiple organizations (federated learning, where different parties train a shared model without sharing raw data) from membership inference attacks (attempts to determine if specific individuals' data was used in training). The paper proposes using adaptive distillation (a technique where a smaller model learns from a larger one to reduce information leakage) as a way to make these distributed AI systems more secure.