Research

This academic article examines how organizations can protect sensitive information and comply with privacy regulations when managing supply chains (the networks of companies and processes involved in getting products from makers to customers). The paper discusses the difficulties companies face in securing data across multiple partners, identifies new opportunities to improve privacy practices, and describes emerging technological and organizational approaches to address these challenges.

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.

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.

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 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).

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.

OpenAI discovered that SWE-Bench Pro, a widely-used benchmark for measuring AI coding abilities, has significant quality problems that make it unreliable for evaluating model capabilities. Approximately 30% of the tasks in the benchmark are broken due to issues like overly strict tests, unclear instructions, insufficient test coverage, or misleading prompts, meaning the benchmark no longer accurately measures whether AI models can actually write software.

This research proposes a framework for making AI hiring systems more fair by addressing algorithmic bias (when AI systems make systematically unfair decisions against certain groups). The study analyzes real applicant data and finds that language differences in interviews and how interview questions are structured can cause unfair outcomes, but these problems can be reduced by modifying linguistic features (the words and language patterns used) and making interview questions more consistent across all applicants.

In early 2024, Google's Gemini AI model generated historically inaccurate and racially offensive images, such as depicting non-White figures in Nazi-era settings, exposing failures in AI training and ethical oversight. The root cause was a flawed "diversity injection" mechanism (a technique meant to reduce bias in training data) that lacked safeguards to understand historical context, resulting in distorted outputs. The incident caused significant financial and reputational damage to Google and raised broader questions about how to build fairness and accuracy into generative AI systems.

AI systems used by organizations often appear reliable but actually suffer from algorithmic fragility, a persistent instability caused by how machine learning interacts with complex real-world environments, leading to biased outputs and performance drift (a decline in accuracy over time). Organizations manage this instability through stabilization work, which involves three practices: buffering (absorbing problems), reframing (reinterpreting failures), and patching (fixing issues), that become routine organizational processes to maintain the appearance of reliability. The paper argues that algorithmic fragility is a structural condition of AI systems rather than a temporary bug, and that effective AI governance requires continuous practice-based management rather than one-time technical fixes.

Neural Radiance Fields (NeRF, a technique for representing 3D objects and scenes) need better ways to track which datasets were used to train them, especially since existing watermarking methods require changes during training that don't work well for this purpose. Researchers introduced TraceNeRF, a new method that embeds owner-specific identifying marks directly into training datasets using a hybrid approach combining spatial masking and discrete cosine transform (a mathematical technique for breaking images into frequency components), along with special modules to make these marks harder to remove or alter.