Research

This research presents NatIMG-FL, a framework that improves X-ray image classification using federated learning (a technique where multiple hospitals train an AI model together without sharing sensitive patient data). The framework addresses two key problems: hospitals have limited X-ray image collections, and they may use different AI model architectures. NatIMG-FL solves these issues by using regular natural images as extra training data and introducing a knowledge transfer method that lets different models learn from each other effectively.

This paper surveys Direct Preference Optimization (DPO), a method for aligning large language models (AI systems trained on massive amounts of text) with human values and preferences without using reinforcement learning (a training approach that rewards desired behaviors). The survey reviews the theoretical foundations, different versions of DPO, available datasets of human preferences, and real-world applications, while also identifying current limitations and suggesting directions for future research.

Domain shift, a problem where AI models perform worse when applied to different data than they were trained on, is a major challenge for deploying deep learning systems. Current methods require expensive retraining of feature extractors (the parts of models that learn to recognize patterns), which is computationally costly and hard to understand. The authors propose Feature-space Planes Searcher (FPS), a new approach that keeps the feature extractor frozen and instead adjusts the decision boundaries (the dividing lines the model uses to classify data) by analyzing geometric patterns in the model's learned feature space, reducing computation while maintaining interpretability.

This research paper presents a new security framework called TFSEA that combines feature selection (choosing which data points matter most), classification (sorting data into categories), and authentication (verifying user identity) to detect unauthorized access attempts in cloud computing environments. The paper proposes using this hybrid approach to improve how well systems can identify and prevent intrusions in cloud infrastructure.

Researchers found a security weakness in fingerprinting methods for image generation AI models (systems that embed hidden identifiers into generated images to protect ownership). Existing fingerprinting techniques are vulnerable to collusion attacks, where multiple attackers combine their models to remove or hide these fingerprints. The researchers propose a new fingerprinting method that encodes fingerprints into a personalized normalization module (PNM, a customization layer in the model) and uses anti-collusion mechanisms based on mathematical transformations that severely degrade image quality if models are combined, making colluded models unusable.

This article examines how ransomware (malicious software that locks files and demands payment to unlock them) defense strategies need to change as generative AI (AI systems that create new content like text or code) becomes more common. The piece suggests that traditional security approaches may be less effective in an environment where AI is widely used.

This academic survey paper reviews methods for testing how well neural networks (AI systems trained to recognize patterns in data) perform when faced with unexpected or manipulated images. The paper examines various approaches researchers use to assess whether image recognition systems remain accurate and reliable under challenging conditions.

Researchers discovered that they can figure out what actions industrial robots are performing just by analyzing encrypted network traffic (data traveling across networks in scrambled form) without being able to read the actual messages. The study shows both practical attacks that successfully identified robot movements and theoretical limits on how much information can be extracted from this type of traffic. This reveals a security gap where encryption alone may not fully protect sensitive robot operations from being monitored.

This paper presents a new cryptographic method called certificateless lattice-based matchmaking encryption (CLLME) designed to secure data sharing on cloud platforms while meeting regulations like GDPR. CLLME provides post-quantum security (protection against future quantum computers), allows both senders and receivers to control who can access data, and includes a filtering mechanism to avoid decrypting irrelevant encrypted files. The researchers proved the method is mathematically secure and showed it works efficiently in real-world scenarios.

Thumbnail-preserving encryption (TPE, a method that keeps some visual information visible in encrypted images to balance usability and privacy) has a security weakness: existing approaches encrypt pixels, blocks, or channels separately, creating vulnerabilities. Researchers propose a new 'triple-chain architecture' that links encryption at three levels (pixels, blocks, and channels) so that any small change to an image causes completely different encryption results, making the system more secure while still maintaining TPE benefits.

This paper addresses the challenge of training prohibited item detection models for X-ray security screening, which normally requires large amounts of manually collected and labeled images. The authors propose Xsyn, a one-stage synthetic image generation pipeline using text-to-image generation (a type of AI that creates images from text descriptions) that automatically creates realistic X-ray security images without requiring labor-intensive manual image extraction and annotation.

This research paper describes methods for making neural networks (AI models that learn patterns from data) more private by using fully homomorphic encryption (a type of encryption that lets computers perform calculations on encrypted data without decrypting it first). The work focuses on optimizing how these privacy-protecting neural networks search through and train on data while keeping information secure.

This research paper proposes a new cryptographic method for securing communication in IoT (Internet of Things) devices that is lightweight and preserves privacy. The scheme uses certificateless signcryption (a technique that combines digital signatures for authentication with encryption for confidentiality, without requiring traditional certificates) and designated-verifier privacy (meaning only a chosen recipient can verify that a message is authentic), designed to work efficiently on resource-constrained IoT devices.

This research paper describes a watermarking technique that allows AI model creators to prove they own their models without revealing the watermark during normal use. The watermark remains hidden when the model is deployed but becomes detectable when the model is updated, helping prevent unauthorized copying or theft of AI models.

Researchers demonstrated that large language models (AI systems trained on vast text data) can be used to generate attack strategies against industrial control systems (the computers that manage power plants, factories, and critical infrastructure). The study shows a concerning security risk where these powerful AI tools could be misused to help attackers plan harmful activities against systems that society depends on.

This academic publication examines security vulnerabilities in the mechanisms that deliver software updates to computers and systems. The article, published in June 2026, analyzes how attackers might exploit the update process itself to compromise systems, rather than targeting the software after it's already installed.

Researchers describe a method for creating hidden communication channels within networks by using hash-based filtering to disguise data inside normal-looking network traffic. This technique, called a covert channel (a hidden path for sending information that shouldn't be detectable), could allow attackers to secretly send data through systems without being noticed by security tools.

Text-to-image diffusion models (AI systems that generate images from text descriptions) can be misused to create fake or harmful images, and current defenses using hidden noise patterns don't work well enough. Researchers propose DANP (Dual Attention-Guided Noise Perturbation), a defense method that adds imperceptible perturbations (tiny, invisible changes) to confuse the model's understanding by manipulating how it pays attention to different parts of the image and how it predicts noise during generation.

Researchers created SOOM, a defense method that obfuscates (hides or disguises) deep learning operators to protect against model extraction attacks, where attackers reverse-engineer compiled neural network code to recreate trainable models. Built on TVM (a deep learning compiler), SOOM uses a machine learning cost model to scramble how operators work while keeping inference fast, achieving a 89% failure rate against extraction attacks with minimal performance slowdown.