Tags → #large language models

Vulnerabilities
Study Introduces Benchmark for Evaluating Cryptographic Protocols
Nov 23, 2024 A recent study highlights the critical importance of cryptographic protocols in digital security and introduces a benchmark, CryptoFormalEval, to evaluate the effectiveness of Large Language Models in identifying vulnerabilities within these protocols.
Vulnerabilities
Advancements in LLM Agents for Software Vulnerability Repair
Nov 22, 2024 Recent advancements in software security have highlighted the use of fuzz testing and Large Language Model agents, such as AutoCodeRover, to identify and autonomously fix vulnerabilities in open source software systems.
Vulnerabilities
Study Reveals Vulnerabilities of LLMs to Bit-Flip Attacks
Nov 22, 2024 A recent study reveals that large language models (LLMs) are vulnerable to bit-flip attacks, which can drastically reduce their performance, prompting the introduction of a new framework called AttentionBreaker to identify and exploit these vulnerabilities.
Tools
New Model MERLOT Developed for Encrypted Traffic Classification
Nov 21, 2024 A recent study presents MERLOT, a scalable mixture-of-expert model designed for the efficient classification of encrypted traffic while reducing computational costs.
Tools
ProSec Introduces New Approach for Secure Code Generation
Nov 21, 2024 A new paper introduces ProSec, a proactive security alignment approach that enhances code-specific large language models by synthesizing error-inducing coding scenarios to improve secure coding practices.
Vulnerabilities
Research Highlights Vulnerabilities in Large Language Models Security
Nov 21, 2024 A new paper examines the vulnerabilities of large language models in enterprise settings, emphasizing the need for a comprehensive understanding of security risks across software and hardware components in compound AI systems.
Education
Study Examines Information Security Awareness of Large Language Models
Nov 21, 2024 A study from Ben-Gurion University of the Negev examines the information security awareness of large language models, revealing gaps in their ability to provide safe security advice and highlighting the need for caution in their use.
Vulnerabilities
Study Identifies Vulnerabilities in LLM-Integrated Frameworks
Nov 21, 2024 A recent study introduced LLMSmith, a tool designed to detect and exploit Remote Code Execution vulnerabilities in Large Language Model-integrated frameworks and applications, highlighting significant security concerns in this area.
Vulnerabilities
Security Vulnerabilities in IoT Devices Using HTTP Protocol
Nov 20, 2024 The article discusses the security vulnerabilities of IoT devices using the HTTP protocol and introduces ChatHTTPFuzz, a novel method that utilizes large language models to improve vulnerability detection in these devices.
Vulnerabilities
Study Analyzes Security Scanners for Large Language Models
Nov 20, 2024 A recent study analyzes open-source tools for scanning conversational large language models (LLMs) for vulnerabilities, highlighting the need for improved detection capabilities and collaboration to enhance their security.