Tag: Help Net Security

Researchers automated jailbreaking of LLMs with other LLMs

AI security researchers from Robust Intelligence and Yale University have designed a machine learning technique that can speedily jailbreak large language models (LLMs) in an automated fashion. “The method, known as the Tree of Attacks with Pruning (TAP), can be…

Using AI and automation to manage human cyber risk

Despite advanced security protocols, many cybersecurity incidents are still caused by employee actions. In this Help Net Security video, John Scott, Lead Cybersecurity Researcher at CultureAI, discusses how integrating AI and automation into your cybersecurity strategy can improve employee behaviors…

OpenTofu: Open-source alternative to Terraform

OpenTofu is an open-source alternative to Terraform’s widely used Infrastructure as Code provisioning tool. Previously named OpenTF, OpenTofu is an open and community-driven response to Terraform’s recently announced license change from a Mozilla Public License v2.0 (MPLv2) to a Business…

Atlassian fixes four critical RCE vulnerabilities, patch quickly!

Atlassian has released security updates for four critical vulnerabilities (CVE-2023-1471, CVE-2023-22522, CVE-2023-22524, CVE-2023-22523) in its various offerings that could be exploited to execute arbitrary code. About the vulnerabilities CVE-2022-1471 is a deserialization flaw in the SnakeYAML library for Java that…