Jailbreaking Large Language Models through Iterative Tool-Disguised Attacks Via Reinforcement Learning

Large language models LLMs have demonstrated remarkable capabilities across diverse applications, however, they remain critically vulnerable to jailbreak attacks that elicit harmful responses violating human values and safety guidelines. Despite extensive research on defense mechanisms, existing...

HackWorld: Evaluating Computer-Use Agents on Exploiting Web Application Vulnerabilities

Web applications are prime targets for cyberattacks as gateways to critical services and sensitive data. Traditional penetration testing is costly and expertise-intensive, making it difficult to scale with the growing web ecosystem. While language model agents show promise in cybersecurity, moder...

CVE-2021-41170

neoan3-apps/template is a neoan3 minimal template engine. Versions prior to 1.1.1 have allowed for passing in closures directly into the template engine. As a result values that are callable are executed by the template engine. The issue arises if a value has the same name as a method or function...

CVE-2021-41170

neoan3-apps/template is a neoan3 minimal template engine. Versions prior to 1.1.1 have allowed for passing in closures directly into the template engine. As a result values that are callable are executed by the template engine. The issue arises if a value has the same name as a method or function...