Research

An OpenAI language model has solved a famous 80-year-old math problem in discrete geometry (the study of geometric shapes made from separate points) by disproving a long-held belief about how many pairs of points can be exactly one unit apart. The AI found an infinite family of point arrangements that beat the previous best solution, and external mathematicians have verified the proof, marking the first time an AI has autonomously solved a prominent open problem central to a mathematical field.

This research presents LBRS, a new cryptographic method for secure anonymous voting that uses lattice-based mathematics (a post-quantum approach resistant to attacks from powerful quantum computers). The method combines blind ring signatures (a technique that hides both the voter's identity and the vote itself while allowing verification) with voting systems, solving problems with previous approaches that either were vulnerable to quantum computers or produced very large signatures that would be impractical for widespread use.

Researchers developed a new method to attack 3D point cloud models (AI systems that process 3D sensor data) using only the final prediction label, without needing access to the model's internal details or calculations. Their technique uses a spectrum-aware decision boundary algorithm to create adversarial examples (slightly modified inputs that fool the AI) that are harder to detect and more practical to deploy in real-world scenarios than existing attack methods.

SilentNoise addresses a problem in differential privacy (DP, a method for analyzing data while protecting individual privacy), which traditionally relies on one trusted party holding all sensitive data, creating a security risk. The researchers propose a decentralized system using secure multiparty computation (MPC, where multiple parties jointly compute results without fully revealing their individual data) that allows noise (random data added for privacy) to be generated securely even when some parties act maliciously, improving both efficiency and accuracy compared to previous approaches.

VOLE-PDRAA is a privacy-preserving data retrieval protocol designed to help organizations follow GDPR (General Data Protection Regulation, European privacy law) requirements while protecting personal data. The protocol uses advanced cryptographic techniques, including Vector-OLE (a method for secure computation), non-interactive zero-knowledge proofs (NIZK, a way to prove something is true without revealing details), and labeled private set intersection (labeled-PSI, a technique to find matching data without exposing the data itself) to allow data controllers to verify user requests without learning identifying information, while maintaining security even against future quantum computers.

Mobile crowdsensing (MCS, a system where mobile users contribute data to solve problems) needs ways to verify that the collected data is truthful while protecting people's privacy. This paper proposes two new truth discovery schemes: RsAnonTD for systems with a stable group of users, and McFeKDeTD for systems where workers join and leave dynamically. Both schemes use cryptographic techniques (ring signature, perturbation, and functional encryption with zero-knowledge proofs, which are mathematical ways to verify information without revealing details) to keep data private and defend against attacks like data forgery and tampering, while also reducing computational overhead by up to 98% compared to existing approaches.

Palladium is a system that protects private training data and model parameters when training deep neural networks (DNNs, AI systems with many layers that learn patterns from data) on remote cloud servers with GPUs. The system uses TEEs (trusted execution environments, secure areas of a processor that are isolated from the rest of the system) combined with a "Cloak" strategy to hide sensitive information while still allowing most computations to run on untrusted accelerators, achieving both privacy protection and reasonable performance.

Diffusion models (AI systems that generate images from text descriptions) can be misused to create unauthorized portraits or copies of artistic styles through personalization, which threatens privacy and copyright. PersGuard is a new defense framework that embeds protective backdoors (hidden mechanisms) into these models before release, so that if someone tries to personalize the model with protected images, it generates predetermined protective outputs instead, while still working normally for unprotected images.

Garland is a system for recommendation engines that use graph neural networks (GNNs, which are AI models that learn patterns from interconnected user-item relationships) in federated settings, where data stays on users' devices instead of being sent to one central server. The system addresses a key problem: untrusted servers that help expand users' local data can spy on both item information and user relationships, so Garland uses secret-shared shuffle (a cryptographic technique that mixes data while keeping it encrypted) to protect privacy while still catching if a malicious server tries to cheat.

This is a scoping review (a broad survey of existing research) that examines how small and medium-sized enterprises can prevent and respond to cyber incidents (security breaches and attacks). The paper synthesizes research findings to help SMEs understand best practices for protecting their systems and recovering when attacks occur.

Connected autonomous vehicles share sensor data to improve driving safety, but this collaboration is vulnerable to adversarial message attacks (malicious input designed to fool AI systems) from bad actors that can degrade performance. The paper describes a new blind area confusion attack that bypasses existing defenses, then proposes GCP, a framework that detects malicious agents by checking both spatial consistency (whether sensor readings from different vehicles agree) and temporal anomalies (unusual patterns over time) using statistical testing methods.

Penetration testing (PT, a security technique where experts simulate attacks to find weaknesses in networks) is traditionally slow and expensive because it relies heavily on manual expert work. This research proposes an automated and intelligent PT method using a knowledge graph (a structured database of relationships between network components) and historical decision data to create realistic test environments and make smarter attack decisions, achieving a 69% reduction in repeated testing attempts.

ROSE is a black-box watermarking method (a technique to prove ownership of AI models by embedding hidden triggers that only the owner can activate) for protecting deep neural networks (DNNs, large AI models that learn patterns from data) in machine learning services. The method uses secret trigger-label pairs connected through a hash function to verify ownership while resisting attacks like fine-tuning, pruning, and other model modifications, while maintaining the model's performance on its original task.

This paper presents CyberOps-Bots, a system that combines Large Language Models (LLMs, which are AI models trained on text) with reinforcement learning (RL, a type of AI that learns by trial and error) to defend cloud networks against attacks. The system uses a two-layer approach where an upper LLM agent handles planning and human input, while lower RL agents execute specific defense actions, and testing shows it maintains network availability much better than existing methods without needing to retrain when network conditions change.

This research presents a new AI framework for network intrusion detection systems (IDS, which are tools that identify unauthorized access attempts on computer networks) that provides both accurate threat detection and reliable confidence levels in its predictions. The framework combines transformer models (a type of neural network architecture) with ensemble methods (combining multiple AI models for better results) to break down prediction uncertainty into two types: epistemic uncertainty (uncertainty from the model itself) and aleatoric uncertainty (uncertainty from noisy or incomplete data). Testing on four benchmark datasets shows the system achieves strong detection rates (77.55% to 97.00% F1-scores, a measure of accuracy) while maintaining good calibration (accurate confidence estimates) and remaining resilient to adversarial attacks (attempts to fool the AI with specially crafted malicious inputs).

DiffHash is a new attack method that can fool deep hashing models (AI systems used to quickly search through large collections of images) by generating adversarial examples (slightly modified images that trick AI systems). Unlike older attacks that simply change individual pixels, DiffHash uses text descriptions from a Large Language Model to guide the creation of fake images that appear normal to humans but cause the hashing model to return wrong search results for a target image.

ParaVul is a framework that uses LLMs (large language models, AI systems trained on huge amounts of text) combined with RAG (retrieval-augmented generation, where an AI pulls in external documents to answer questions) to detect vulnerabilities in smart contracts (self-executing programs on blockchain networks). The framework improves detection accuracy and reduces computational costs by using a new fine-tuning technique called SLoRA (Sparse Low-Rank Adaptation) and combining multiple detection methods through a verification module.

Face-swapping deepfakes (AI-generated videos or images where one person's face is replaced with another) are widely misused for fraud and misinformation, and while detection tools exist, there has been little work on tracing and recovering the original face that was replaced. This paper presents FaceReclaim, a new AI method that uses diffusion models (neural networks trained to gradually refine noisy images into clear ones) to restore the original face from a deepfaked image by separating facial attributes like expressions from identity information.

This research addresses a security weakness in neural steganography (hiding secret messages inside audio files using AI networks), where sender and receiver models must stay perfectly synchronized, creating risks of information leakage. The researchers propose a decoupled framework based on the destruction-restoration principle, where embedding works through a destructive operation and recovery uses a separate neural network, allowing the sender to change their embedding network without breaking the receiver's ability to extract the hidden message.