3 papers
cs.CR2025
Supporting Students in Navigating LLM-Generated Insecure Code
Jaehwan Park, Seonhye Park, Kyungchan Lim +2
The advent of Artificial Intelligence (AI), particularly large language models (LLMs), has revolutionized software development by enabling developers to specify tasks in natural la…
cs.CR2024
UniHENN: Designing Faster and More Versatile Homomorphic Encryption-based CNNs without im2col
Hyunmin Choi, Jihun Kim, Seungho Kim +4
Homomorphic encryption (HE) enables privacy-preserving deep learning by allowing computations on encrypted data without decryption. However, deploying convolutional neural networks…
cs.CR2023
Poisoned ChatGPT Finds Work for Idle Hands: Exploring Developers' Coding Practices with Insecure Suggestions from Poisoned AI Models
Sanghak Oh, Kiho Lee, Seonhye Park +2
AI-powered coding assistant tools have revolutionized the software engineering ecosystem. However, prior work has demonstrated that these tools are vulnerable to poisoning attacks.…