Tags → #stories

Samsung Devices Face JSON Injection Vulnerability Concerns

A newly identified JSON injection vulnerability in Samsung devices, particularly affecting the Smart Hub mobile app, raises security concerns due to its potential to enable remote code execution.
Scrutiny of Language Models Due to Extraction Attack Vulnerabilities

Language models are under scrutiny for their vulnerability to extraction attacks, which can reveal sensitive information from their training data.
Security Vulnerabilities Identified in Quantum Computing Circuits

Security vulnerabilities in quantum computing have been identified, particularly at the interface between gate-level and pulse-level circuits, raising concerns about potential attack vectors and the need for enhanced protective measures.
Smart-LLaMA Method Enhances Smart Contract Vulnerability Detection

Smart-LLaMA is a new method aimed at improving the detection of vulnerabilities in smart contracts by utilizing large language models and a comprehensive dataset.
Study Analyzes Machine Learning for DDoS Detection in IoT

A recent study examines the use of machine learning models for detecting Distributed Denial of Service (DDoS) attacks in Internet of Things (IoT) networks, highlighting the vulnerabilities of these networks due to inconsistent security measures.
Study Develops LLM-Based Method for Malware Detection

A recent study from Pennsylvania State University introduces a Large Language Model-based workflow aimed at identifying anti-dynamic analysis techniques used by malware to evade detection in sandbox environments.
Study Examines Maximal Extractable Value in Ethereum and Rollups

A recent study has examined Maximal Extractable Value (MEV) within Ethereum and rollup-based Layer-2 solutions, revealing insights into transaction dynamics, profitability, and security concerns associated with MEV extraction.
Study Examines Undetectable Backdoors in Machine Learning Models

A recent study highlights the risks of undetectable backdoors in machine learning models, emphasizing the challenges of ensuring model integrity when training is outsourced to untrusted parties.
Study Examines Vulnerabilities of Language Models to Attacks

A recent study has identified vulnerabilities in large language models to prompt injection attacks, introducing a novel attack strategy known as Goal-guided Generative Prompt Injection Attack (G2PIA).
Study Explores Future of Quantum Cryptography Systems

Researchers from the Pritzker School of Molecular Engineering and Argonne National Laboratory have published an article discussing the future of cryptographic systems in light of quantum technology advancements, emphasizing the need for quantum-resistant systems and exploring both Quantum Key Distribution and Post-Quantum Cryptography.