activity
20242026
most citedLLM Security Guard for Code

20 citations · 36 across the 9 of their papers we have counts for

collaborators
Showing 2024Show all

6 papers · 1 filter

cs.CR2024★ 8 cited

ChatGPT's Potential in Cryptography Misuse Detection: A Comparative Analysis with Static Analysis Tools

Ehsan Firouzi, Mohammad Ghafari, Mike Ebrahimi

The correct adoption of cryptography APIs is challenging for mainstream developers, often resulting in widespread API misuse. Meanwhile, cryptography misuse detectors have demonstr…

cs.CR2024★ 1 cited

From Struggle to Simplicity with a Usable and Secure API for Encryption in Java

Ehsan Firouzi, Ammar Mansuri, Mohammad Ghafari +1

Cryptography misuses are prevalent in the wild. Crypto APIs are hard to use for developers, and static analysis tools do not detect every misuse. We developed SafEncrypt, an API th…

cs.CR2024★ 1 cited

Time to Separate from StackOverflow and Match with ChatGPT for Encryption

Ehsan Firouzi, Mohammad Ghafari

Cryptography is known as a challenging topic for developers. We studied StackOverflow posts to identify the problems that developers encounter when using Java Cryptography Architec…

cs.SE2024

Gameful Introduction to Cryptography for Dyslexic Students

Argianto Rahartomo, Harpreet Kaur, Mohammad Ghafari

Cryptography has a pivotal role in securing our digital world. Nonetheless, it is a challenging topic to learn. In this paper, we show that despite its complex nature, dyslexiaa…

cs.CR2024★ 6 cited

Mining REST APIs for Potential Mass Assignment Vulnerabilities

Arash Mazidi, Davide Corradini, Mohammad Ghafari

REST APIs have a pivotal role in accessing protected resources. Despite the availability of security testing tools, mass assignment vulnerabilities are common in REST APIs, leading…

cs.SE2024★ 20 cited

LLM Security Guard for Code

Arya Kavian, Mohammad Mehdi Pourhashem Kallehbasti, Sajjad Kazemi +2

Many developers rely on Large Language Models (LLMs) to facilitate software development. Nevertheless, these models have exhibited limited capabilities in the security domain. We i…