Research

Cloud computing systems face side-channel attacks (SCAs, where attackers exploit information leaked through physical resources like CPU cache to compromise VMs on shared servers) when multiple VMs run on the same physical machine. This paper proposes a framework that analyzes user behavior patterns to intelligently place VMs across servers and then continuously moves them around to prevent attackers from keeping their malicious VM next to a target VM long enough to launch an attack, achieving up to 25% reduction in attack risk while improving resource efficiency.

This research proposes a framework for authenticating people based on their faces while protecting their facial privacy in systems like smart building access. The system uses homomorphic encryption (a technique that lets computers perform calculations on encrypted data without decrypting it first) and a multi-party secure authentication process, where multiple parties verify identity together rather than relying on a single trusted server, to prevent privacy breaches and single points of failure.

Knowledge graph embedding (KGE, a technique that converts graph structures into numerical representations for AI tasks) systems can be attacked by deleting or adding false information, which corrupts their learned representations. This paper introduces PathAttack, a new attack method that uses reasoning paths (multi-hop connections between entities) to identify which pieces of data to attack without needing to know targets in advance, showing 5% improvement in attack effectiveness on test datasets.

N/A -- The provided content is a navigation menu and feature listing from GitHub's website, not an AI/LLM security issue, vulnerability, or technical problem.

Researchers created SemBugger, a polymorphic backdoor attack (a type of hidden malicious code that can change its behavior) against semantic communication (SC, a system where AI learns shared knowledge to compress and transmit information efficiently). The attack uses variable-intensity triggers to poison training data and manipulate the system into producing different malicious outputs while appearing normal, but the researchers also developed a defense mechanism using controlled noise that can resist these attacks.

Person re-identification (ReID) systems, which match images of the same person across different camera views, are vulnerable to a new attack called DSCA (diffusion-based semantic camouflage attack). Instead of changing individual pixels, DSCA uses a generative model to subtly alter high-level features like clothing color and texture to trick the system into matching an attacker with a target identity without needing access to the victim system. The researchers demonstrated this attack succeeds over 95% of the time and evades existing defenses, revealing important security gaps that developers should address.

PixOOD is an algorithm that detects out-of-distribution data (inputs that don't match patterns the AI learned from) at the pixel level, meaning it can identify anomalies in individual image pixels without needing to train on examples of bad data. The method uses a data condensation algorithm (a technique to compress training information efficiently) to model normal image variation and provides two different calibration approaches depending on the application's needs.

ABIGX is a framework that makes fault detection and classification (the process of identifying when a system is broken and what type of problem it is) more explainable by showing which parts of the input data matter most. The framework uses a technique called Adversarial Fault Reconstruction (AFR, which treats fault diagnosis like an adversarial attack problem to better identify what causes failures) and proves it can improve on older explanation methods, particularly by fixing a problem called fault class smearing where explanations become unclear when multiple failure types are present.

This research addresses privacy and data quality challenges in federated learning (FL, a technique where multiple computers train an AI model together without sharing raw data) for skeleton-based action recognition (identifying human movements from body joint positions). The authors propose Fed-C&E, a system that uses data condensation on client devices to reduce privacy risks, then expands the condensed data on a central server using techniques like a prototype-to-sequence similarity transformation matrix pool and feature expansion with second-order statistics to recover lost information and prevent overfitting.

This research proposes K-TCDP (K-Temporal Correlated Differential Privacy), a new method for training large language models privately using LoRA (a technique that adds small trainable adapters to a model). Standard privacy-preserving training adds random noise that degrades model quality, but K-TCDP uses strategically correlated noise over time so that noise added in early steps can be partially canceled out by noise in later steps, improving model performance while maintaining privacy guarantees.

AmbShield is a security method that uses ambient backscatter devices (AmBDs, which are passive devices that reflect wireless signals without needing their own power source) to protect wireless networks from eavesdropping. The system works by having these devices act as both friendly jammers that create interference to disrupt eavesdroppers and as passive relays that strengthen the signal for legitimate users, all without requiring extra power or complex deployment.

BlockAthena is a new forensic framework designed to detect long-term crimes on blockchains (distributed ledgers that record transactions) by analyzing transaction patterns over extended periods. The system identifies criminal behavior by recognizing botnet-style activity (coordinated malicious networks) and APT tactics (advanced persistent threat methods used by sophisticated attackers), segmenting transaction data into meaningful chunks based on crime phases, and using graph analysis to spot suspicious patterns while using less computer memory than previous approaches.

Multi-view clustering (MvC, a technique that combines information from multiple data sources to improve clustering) often fails to use all available information effectively because some data views dominate the learning process while others are neglected. This paper proposes Balanced Multi-View Clustering (BMvC), which uses view-specific contrastive regularization (VCR, a technique that adjusts how each data source is learned to maintain balanced importance) to ensure all views contribute fairly to the final clustering result.

This paper proposes DFedCata, an algorithm that improves decentralized federated learning (a distributed AI training method where multiple devices train models together without a central server). The main problem addressed is that when training data differs across devices (called data heterogeneity), the models converge slowly and perform poorly. DFedCata uses two mathematical techniques, the Moreau envelope function and Nesterov's extrapolation step, to handle these inconsistencies and speed up training.

This paper presents a method to improve indirect time-of-flight (iToF) imaging, a technology that measures depth by analyzing how light bounces off objects. The researchers use machine learning to optimize how the imaging system encodes and decodes light signals, guided by Fisher information (a measure of how much useful information data contains), while also incorporating visual data from regular RGB cameras to make depth measurements more accurate, especially in noisy conditions.

This research presents a unified framework for understanding how vision models (AI systems that analyze images) work by focusing on pointwise feature vectors (PFVs, individual numerical representations at specific locations in an image) and their instance-specific Effective Receptive Fields (iERFs, the regions of an input image that influence those representations). The framework includes three complementary approaches: Sharing Ratio Decomposition for local explanations, Concept-Anchored Feature Explanation for connecting abstract features to visible pixels, and Interlayer Concept Graph for tracking how representations evolve through the model's layers. The authors demonstrate that their approach provides clearer, more reliable explanations of model decisions across different vision architectures (ResNet50, VGG16, and Vision Transformers) compared to existing methods.

FinBot is an interactive training platform (CTF, or capture-the-flag competition) created by OWASP to help builders and defenders understand how agentic AI systems (AI agents that plan, act, and make decisions in complex workflows) can fail and be attacked. It simulates a financial services application where users encounter real security risks like prompt injection (tricking an AI by hiding instructions in its input), tool misuse, data theft, and privilege escalation (gaining unauthorized higher-level access), with connections to industry security frameworks like the OWASP Top 10 for Agentic Applications.

This research studies how to securely communicate using drones (autonomous aerial vehicles, or AAVs) that transmit data through free space using light beams (FSO, or free-space optical communication) rather than radio waves. The researchers analyze physical layer security (PLS, which means protecting data at the lowest level of how information is transmitted) when multiple users share the connection and an eavesdropper tries to intercept the signal, accounting for real-world challenges like atmospheric turbulence and pointing errors. They propose optimizing certain communication parameters to reduce the chance that secret information leaks to unauthorized listeners while maintaining good data transmission speeds.

High-frequency traders on decentralized applications (DApps, which are programs built on blockchains) are vulnerable to honeypots, which are traps created by attackers that use publicly visible transaction data to trick users into executing transactions that will fail. Researchers identified 636 honeypot incidents affecting 99 smart contracts (self-executing programs on blockchains) that caused over 25 million dollars in losses, and developed methods to detect these traps and analyze why transactions fail. The study proposes mitigation strategies based on understanding the causes of transaction reversions (when a transaction fails and is undone), though detailed implementation specifics are not provided in this summary.