InfoWorld

19 large language models redefining AI safety—and danger

Whether you are looking for an LLM with more safety guardrails or one completely without them, someone has probably built it.
Scientific Research Publishing

Cybersecurity and Forensic Audio Analysis: Deepfake Detection Based on Mfcc, Audio-Text Disconsistency, and Prosodic Features ()

1 Department of Computer and Instructional Technologies Education, Gazi Faculty of Education, Gazi University, Ankara, Türkiye. 2 Department of Forensic Informatics, Institute of Informatics, Gazi ...
IEEE

Adversarial Machine Learning in Cybersecurity: Attacks, Defenses, Robustness, and Explainability

Abstract: Most modern cybersecurity systems, including intrusion detection, malware classification, anomaly detection, and authentication, utilize machine learning. However, ML models are susceptible ...
IEEE

Adversarial Machine Learning for Robust and Secure UAV Detection in Consumer Applications

Abstract: This research evaluates a cognitive AI model for unmanned aerial vehicles (UAV) detection using adversarial machine learning (AML) techniques. We test the model using the VisDrone dataset ...