3 papers
cs.LG2025
TwinBreak: Jailbreaking LLM Security Alignments based on Twin Prompts
Torsten Krauß, Hamid Dashtbani, Alexandra Dmitrienko
Machine learning is advancing rapidly, with applications bringing notable benefits, such as improvements in translation and code generation. Models like ChatGPT, powered by Large L…
cs.CR2024
GNN-Based Code Annotation Logic for Establishing Security Boundaries in C Code
Varun Gadey, Raphael Goetz, Christoph Sendner +2
Securing sensitive operations in today's interconnected software landscape is crucial yet challenging. Modern platforms rely on Trusted Execution Environments (TEEs), such as Intel…
cs.CR2024
Memory Backdoor Attacks on Neural Networks
Eden Luzon, Guy Amit, Roy Weiss +3
Neural networks are often trained on proprietary datasets, making them attractive attack targets. We present a novel dataset extraction method leveraging an innovative training tim…