Research

Researchers proposed DFM (Distributed Functional Mechanism), a method for training AI models while protecting user privacy in systems where multiple people contribute data. Unlike older privacy-focused training methods like DP-SGD (differentially private stochastic gradient descent, which adds noise to the mathematical directions the model learns), DFM protects privacy by adding noise to polynomial approximations (simplified mathematical descriptions) of the training process, making it faster and more stable while maintaining privacy guarantees across all users.

Access control in IoT (Internet of Things, networks of connected devices) is complex because policies need to consider dynamic factors like time and location, but existing systems are too rigid or require experts to manually translate natural language requirements into code, creating errors. LACE (Language-based Access Control Engine) is a new system that uses LLMs (large language models, AI systems trained on text) combined with retrieval-augmented reasoning (pulling in relevant information to help the AI decide) and formal validation (checking rules are logically correct) to let users write access control policies in plain English, which the system automatically converts into machine-enforced rules.

This research paper proposes a cloud-assisted protocol for privacy-preserving machine learning that allows AI models to be trained on distributed data (data stored in different locations) without exposing users' private information. The protocol uses ID-Private data joins, a technique that matches data from different sources while keeping sensitive details hidden from the cloud and other parties involved.

This academic survey examines fairness, bias, threats, and privacy issues in recommender systems (AI systems that suggest products, content, or services to users). The paper analyzes insights from existing research and identifies areas needing future investigation, but does not present or evaluate specific technical fixes.

This is a comprehensive academic review article published in ACM Computing Surveys that examines how machine learning (algorithms that learn patterns from data) is being used in Security Operations Centres (SOCs, which are teams and systems that monitor networks for threats). The article surveys the current state of ML applications across security operations but does not focus on a specific vulnerability or problem requiring a mitigation.

MambaTIG is a new AI system designed to detect malicious activity hidden in encrypted network traffic (data sent over secure connections). Unlike existing detection systems that require huge amounts of labeled attack data and struggle when conditions change, MambaTIG uses self-supervised learning (training on unlabeled benign traffic) combined with state-space modeling (a mathematical approach that efficiently processes sequences of data) to be faster, more robust, and better at handling new or unfamiliar attack types.

Modern communication systems use multilayer networks (interconnected systems where different devices connect through multiple linked layers), which improve performance but create security risks because malware can spread across connections between layers. This research uses the SIR epidemic model (a mathematical framework that simulates how diseases or malware spread through populations) to find the optimal balance: the right number of connections that keeps the network from being isolated by cyberattacks while preventing malware from spreading between layers. The study proposes a weighted scoring method to help determine this optimal number based on specific needs.

Researchers developed RFA-Tex, a method to create adversarial textures (specially designed patterns that trick AI systems) that can hide people from person detection AI at long distances. Previous adversarial textures only worked within 5 meters because fine details in the patterns broke down during long-range imaging, but RFA-Tex uses a new framework that preserves important details and reduces fragile structures, extending the attack range to 25-45 meters in real-world tests.

Researchers have developed DSFDU, a detection method that identifies when attackers use unicode modifier letters (special invisible characters that change how other characters display) to hide malicious commands in living-off-the-land attacks (tactics where hackers exploit legitimate system tools already installed on a computer, rather than bringing their own malware). This technique allows defenders to catch obfuscated (disguised or hidden) commands that traditional security tools might miss.

This is a survey paper that examines XAI (explainable AI, which means making AI systems' decisions understandable to humans) techniques used in cybersecurity, along with the challenges researchers face when trying to apply these methods and potential future research directions. The paper reviews how organizations can make AI-powered security tools more transparent so that security teams can understand why the AI flagged something as a threat.

Split learning (SL, a technique where a deep neural network is divided between a client's local computer and a server to reduce computation on the client side) faces challenges in protecting intellectual property through watermarking (a hidden mark added to prove ownership) in multi-client settings, because the server can erase watermarks, later clients can overwrite earlier ones, and malicious clients can deliberately remove them. This paper proposes MarkSplit and MarkSplit+, two methods that embed watermarks more robustly by jointly training the main task with watermark samples in a three-tiered training structure, with MarkSplit+ using dynamic adjustment for adversarial environments with malicious participants.

FlowCrypt is a new method for encrypting photos on phones and cloud storage that protects privacy by using flow-based neural networks (a type of AI model that can reverse its operations). Unlike older encryption systems, FlowCrypt can recover the original photo nearly perfectly after decryption, uses no extra reference images, and is lightweight enough to run on mobile devices while maintaining strong security.

This research addresses vulnerabilities in cyber-physical systems (CPSs, which are physical machines controlled and monitored by computers) that use event-triggered mechanisms (ETMs, systems that send data only when something important happens rather than continuously). The paper proposes a defense method combining machine learning-based adaptive thresholding (automatically adjusting sensitivity levels using AI) and encryption to protect against strategic DoS attacks (targeted jamming where attackers selectively block critical data packets based on what they learn about the system).

MHcast is a system that hides metadata (information like who is sending and receiving messages) in multicast communications (sending messages to multiple recipients at once), while also protecting against malicious clients and servers that might try to break the system or reveal identities. The system uses distributed comparison functions and access control to prevent attacks and can deliver messages much faster than existing metadata-hiding systems, especially when sending to larger groups of recipients.

This research paper presents a lightweight defense method against advanced phishing emails (fraudulent messages designed to steal information) using a distilled attention-augmented BiLSTM (a type of neural network architecture that learns patterns in sequential data like email text). The approach aims to detect sophisticated phishing attempts more efficiently than existing methods by combining attention mechanisms (which help the AI focus on the most important parts of an email) with a smaller, optimized model.

This research paper proposes FedDC, a protection scheme designed to secure federated learning (a training method where multiple computers train an AI model together without sharing raw data) by using a chaotic system (a mathematical approach based on unpredictable behavior). The scheme aims to make federated learning more efficient while protecting the privacy and security of the distributed training process.

This academic paper proposes a new method for federated learning (training AI models across multiple computers without sharing raw data) that uses attribute-based homomorphic encryption (a type of math that lets computers do calculations on encrypted data without decrypting it first). The approach aims to make federated learning both more secure and faster by protecting data privacy while reducing computational overhead.

SEO-DBSCAN is a secure framework for running DBSCAN (a clustering algorithm that groups similar data points together based on density) on cloud servers without exposing sensitive data to the cloud provider. The system maintains the accuracy of normal clustering while protecting privacy through mathematical techniques, and it is much faster and more efficient than previous secure approaches.

Ariadne is a framework that helps security teams reconstruct full attack sequences on web applications by working backward from a detected malicious request. Modern web attacks often require multiple preparatory requests to set up the backend state before the final harmful payload is sent, but security systems typically only detect the final malicious request while the earlier setup requests get lost in traffic logs. Ariadne automatically finds these hidden prerequisite requests using a state-space search method (a technique that explores possible system configurations to find the target state), successfully reconstructing complete attack chains up to 8 steps long where existing tools failed.