Research

This research paper presents a method for detecting deepfakes (synthetic videos or images created by AI to look realistic) using a dual-mode Swin Transformer, which is a type of neural network architecture. The approach uses multi-scale feature learning (analyzing visual details at different zoom levels) and local ambiguity mitigation (reducing confusion in uncertain areas) to improve detection accuracy. This is a technical contribution to security research, not a response to an existing vulnerability or security incident.

This research addresses a privacy risk in teleoperated robotics (systems where humans remotely control robots by having their movements tracked and converted into robot commands). The problem is that motion-tracking data can leak biometric information (unique physical characteristics) that could allow someone to re-identify the operator. The authors propose using a VAE (variational autoencoder, a type of machine learning model that learns compressed representations of data) to filter out identity-revealing patterns while keeping the motion information needed for the robot to complete tasks.

QS-BTrust is a new security protocol designed for Integrated Vehicular Networks (IVNs, which are connected vehicle communication systems) that authenticates broadcast messages while resisting attacks from quantum computers. The protocol combines Physical Unclonable Functions (PUFs, unique digital fingerprints built into hardware), post-quantum digital signatures (cryptographic techniques that remain secure even with quantum computers), and a Hashgraph-based system to verify messages with low overhead and support revoking compromised vehicles without slowing down traffic.

Researchers discovered a new security vulnerability in graph-based RAG (retrieval-augmented generation, where an AI system pulls information from external knowledge graphs to answer questions) systems used with large language models. Attackers can poison the external database by inserting hidden triggers and false information into the knowledge graph, causing the AI to give wrong answers when those triggers appear in user queries while still answering normal questions correctly. The attack uses three types of triggers at different complexity levels, from simple words to semantic patterns, and tests showed the attack works across multiple AI systems.

This paper presents a mathematical framework for making cybersecurity decisions when facing uncertain threats in turn-based security games (scenarios where defenders and attackers take turns making moves). The framework handles uncertainty about both what the attacker might do and how well defensive controls will work, using game theory (the study of strategic decision-making between competing parties) and robust optimization (techniques for finding solutions that work well even when future conditions are unknown). The researchers show their approach outperforms traditional defensive strategies and demonstrate its usefulness through a network attack example.

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.

BadBone is a backdoor attack (a type of hidden vulnerability where an attacker secretly compromises a model to make it misbehave on specific tasks) that targets backbone models (large pre-trained neural networks that serve as the foundation for smaller AI systems) used in prompt learning (a technique where users guide AI behavior by providing example inputs called prompts). The attack is stealthy because it hides the backdoor in the backbone model rather than in the prompt learning process itself, so downstream tasks using prompt learning inherit the vulnerability while the model appears to work normally. Testing shows that current security defenses against backdoors are largely ineffective against BadBone, indicating the need for stronger protections.

Large language models raise privacy concerns because the knowledge they learn becomes deeply entangled in their structure, making it hard to make them "forget" specific information. Researchers developed a privacy-preserving machine unlearning method (a technique to remove learned data from AI models) that eliminates high-risk information from model outputs and uses differentially-private randomization (adding statistical noise to hide sensitive data) to ensure unlearned information cannot be identified, without requiring model parameter adjustments.

This paper addresses the problem of detecting partially spoofed utterances (audio that contains both real and fake segments mixed together) without needing labeled data marking where the fake parts are. The researchers propose FMG, a method using Graph Neural Networks (GNNs, a type of AI model that understands relationships between connected pieces of data) to better track how different audio segments relate to each other over time and to identify which segments are likely fake.

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.

Ridesharing apps need to protect user location privacy, but adding random noise to locations (Laplace noise, a mathematical technique that obscures exact positions) makes it harder to match drivers with passengers efficiently. This paper proposes using linear programming (a mathematical optimization method for finding the best solution among many options) to solve the real-time matching problem between ridesharing requests and drivers while maintaining both privacy and matching quality.

This research proposes new cryptographic methods (PKEET-VPG and its verifiable version) to improve traceable anonymous credentials, which are systems that let users prove they have certain attributes without revealing their identity while still allowing regulators to trace misuse if needed. The key innovation uses session-specific tracing keys (temporary permission codes tied to single authentication sessions) to prevent abuse, and the methods reduce the computational burden on regulators who need to handle large numbers of authentication records.

This research introduces QAFD (Quality-Assisted Forgery Detection), a new system for detecting AI-generated images by analyzing both visual features and quality-related artifacts that different generative models produce. The system uses a quality-guided approach to help AI models better understand degradation patterns in fake images, allowing it to detect AI-generated content more reliably even when tested on unseen generative models and images that have been edited after creation.

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.