Federated learning, differential privacy, and privacy-preserving machine learning. We cover how models train across devices and institutions without centralizing data, what privacy guarantees actually cost in accuracy, and the benchmarks and frameworks shaping the field, always traced back to the original research.
A surgeon at a hospital near Dresden removes an inflamed appendix through three small incisions, and the laparoscope records every second. Those recordings could teach an AI system to judge how severe the inflammation is, a call that shapes antibiotics,…
FedSurg Challenge Tests Federated Learning on Surgical Video Read More »
Edge computing exists because sending everything to the cloud is slow, expensive, and increasingly a privacy liability. Cameras, routers, industrial sensors, and vehicles now do a meaningful share of their own processing, which is great for latency and bandwidth. It…
What 131 Studies Reveal About Federated Learning for Edge Cyberattack Detection Read More »
Survey papers in cybersecurity often stop at cataloging techniques. This one tries to do something harder, and says so directly in its motivation section, arguing that prior MTD surveys treat timing constraints as an afterthought even though cyber physical systems,…
Moving Target Defense For Mission Critical Systems Explained Read More »
For decades, security teams have leaned on MITRE ATT&CK to reason about attackers. It gives everyone the same vocabulary for phishing, privilege escalation, lateral movement, all the familiar beats of a network intrusion. What it was never built for is…
MITRE ATLAS and the Shape of Adversarial Attacks on AI Read More »
Start with the basic shape of the system. A healthcare IoT device, whether it is a glucose monitor, a smart inhaler, or an implanted cardiac sensor, collects data and has to get that data somewhere useful. The obvious answer is…
What 72 Studies Reveal About Healthcare IoT Security Read More »
Adversarial machine learning is not a new worry. Since researchers first showed that tiny, carefully chosen changes to an input could flip a neural network’s classification, the idea has spread into every domain where models make consequential decisions, and network…
Adversarial Machine Learning Meets Intrusion Detection Read More »
Federated learning lets many devices or institutions train one shared model without shipping their raw data anywhere. Almost every popular recipe, from Google’s original FedAvg to Local SGD, follows the same parallel shape. Every client starts from the same global…
Why Training Clients One At A Time Can Beat Averaging In Federated Learning Read More »
Adversarial examples have been an open problem in deep learning since Szegedy and colleagues first described them over a decade ago. Add a small, carefully chosen pattern of noise to an image, invisible to a human eye, and a neural…
S4ST: The Simple Scaling Trick That Fools AI Vision Models Read More »
Weakly supervised video anomaly detection has become the dominant approach to flagging unusual events in surveillance footage, precisely because it sidesteps the need for frame by frame labels. A human only has to tag whether a whole video contains an…
Federated Learning Lets Surveillance Cameras Learn Without Sharing Read More »
Most of what the research community knows about backdoor attacks on graphs comes from homogeneous graphs, where every node and every edge is the same type. In that setting, an attacker can attach almost any subgraph to almost any node,…
Backdoor Attacks Now Target Heterogeneous Graph Neural Networks Read More »