Tags → #machine learning

Tools
Study Explores Machine Learning for Defect Detection in Additive Manufacturing
Nov 19, 2024 A study by researchers from the University of Connecticut and the University of California, Irvine, explores the integration of Machine Learning models with in-situ sensing technologies to improve defect detection in Additive Manufacturing while addressing data privacy concerns.
Tools
New Framework LMDetect Enhances Detection of APT Attacks
Nov 18, 2024 Researchers at Zhejiang University of Technology have developed LMDetect, a framework aimed at improving the detection of lateral movement in advanced persistent threat attacks by utilizing a graph-based analysis of host authentication log data.
Threats
Study Analyzes Machine Learning Models for Phishing Detection
Nov 18, 2024 Phishing remains a significant cybersecurity threat, with recent studies highlighting the effectiveness of machine learning models in detecting phishing URLs while also raising concerns about the generalizability of their features across different datasets.
Threats
Jailbreaking Techniques and Security Risks in Large Language Models
Nov 17, 2024 The practice of jailbreaking Large Language Models (LLMs) involves manipulating AI systems to produce unintended outputs, raising concerns about potential security vulnerabilities and prompting research into enhancing their security.
Tools
Advancements in Privacy-Preserving Machine Learning Protocols
Nov 15, 2024 A recent research article examines advancements in privacy-preserving machine learning, highlighting the role of secure multi-party computation and presenting an efficient protocol for secure linear function evaluation that enhances performance on GPUs.
Vulnerabilities
Research Paper Proposes New Method to Combat Backdoor Attacks
Nov 15, 2024 A research paper from The Chinese University of Hong Kong, Shenzhen, introduces a novel method called Distance-Driven Detoxification (D3) to enhance defenses against backdoor attacks in machine learning models.
Vulnerabilities
O-RAN's Role in Wireless Communication and Security Challenges
Nov 14, 2024 The Open Radio Access Network (O-RAN) architecture enhances wireless communication systems through increased flexibility and security, while also introducing new vulnerabilities and challenges.
Industry
Study Examines Environmental Impact of AI and Energy Use
Nov 14, 2024 A study from the Polytechnic of Porto explores the environmental impact of Artificial Intelligence, focusing on energy consumption and carbon footprint while introducing the concept of "Green AI" to promote sustainable AI practices.
Tools
Microsoft Introduces SecEncoder Language Model for Security Applications
Nov 13, 2024 Microsoft Security AI Research has introduced SecEncoder, a new language model tailored for security applications, which outperforms established models in tasks such as log analysis and incident classification.
Tools
Advancements in Membership Inference Attacks Research Introduced
Nov 12, 2024 A recent research paper presents the Loss Trace IQR (LT-IQR) method, which improves the efficiency of Membership Inference Attacks by identifying vulnerable data samples with reduced computational resources compared to traditional approaches.