[PDF][PDF] Masterkey: Automated jailbreaking of large language model chatbots
Large language models (LLMs), such as chatbots, have made significant strides in various
fields but remain vulnerable to jailbreak attacks, which aim to elicit inappropriate responses …
fields but remain vulnerable to jailbreak attacks, which aim to elicit inappropriate responses …
How well does llm generate security tests?
Developers often build software on top of third-party libraries (Libs) to improve programmer
productivity and software quality. The libraries may contain vulnerabilities exploitable by …
productivity and software quality. The libraries may contain vulnerabilities exploitable by …
Cryptogo: Automatic detection of go cryptographic api misuses
Cryptographic algorithms act as essential ingredients of all secure systems. However, the
expected security guarantee from cryptographic algorithms often falls short in practice due to …
expected security guarantee from cryptographic algorithms often falls short in practice due to …
Detecting Misuses of Security APIs: A Systematic Review
Security Application Programming Interfaces (APIs) play a vital role in ensuring software
security. However, misuse of security APIs may introduce vulnerabilities that can be …
security. However, misuse of security APIs may introduce vulnerabilities that can be …
How do developers follow security-relevant best practices when using NPM packages?
Node. js has become popular among developers, partially because of its large software
ecosystem of NPM (Node Package Manager) packages. When building JavaScript (JS) …
ecosystem of NPM (Node Package Manager) packages. When building JavaScript (JS) …
An Investigation into Misuse of Java Security APIs by Large Language Models
The increasing trend of using Large Language Models (LLMs) for code generation raises
the question of their capability to generate trustworthy code. While many researchers are …
the question of their capability to generate trustworthy code. While many researchers are …
Runtime verification of crypto apis: an empirical study
A Torres, P Costa, L Amaral, J Pastro… - IEEE Transactions …, 2023 - ieeexplore.ieee.org
Misuse of cryptographic (crypto) APIs is a noteworthy cause of security vulnerabilities. For
this reason, static analyzers were recently proposed for detecting crypto API misuses. They …
this reason, static analyzers were recently proposed for detecting crypto API misuses. They …
Detecting cryptography misuses with machine learning: Graph embeddings, transfer learning and data augmentation in source code related tasks
GE de Paula Rodrigues, AM Braga… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Cryptography is a ubiquitous tool in secure software development in order to guarantee
security requirements in general. However, software developers have scarce knowledge …
security requirements in general. However, software developers have scarce knowledge …
LLM security guard for code
A Kavian, MM Pourhashem Kallehbasti… - Proceedings of the 28th …, 2024 - dl.acm.org
Many developers rely on Large Language Models (LLMs) to facilitate software development.
Nevertheless, these models have exhibited limited capabilities in the security domain. We …
Nevertheless, these models have exhibited limited capabilities in the security domain. We …
[HTML][HTML] Time to separate from StackOverflow and match with ChatGPT for encryption
Cryptography is known as a challenging topic for developers. We studied StackOverflow
posts to identify the problems that developers encounter when using Java Cryptography …
posts to identify the problems that developers encounter when using Java Cryptography …