activity
20222025
most citedEvaluating the Susceptibility of Pre-Trained Language Models via Handcrafted Adversarial Examples

14 citations · 15 across the 3 of their papers we have counts for

collaborators
Showing cs.CRShow all

1 paper · 1 filter

cs.CR2025

Prompt Injection 2.0: Hybrid AI Threats

Jeremy McHugh, Kristina Šekrst, Jon Cefalu

Prompt injection attacks, where malicious input is designed to manipulate AI systems into ignoring their original instructions and following unauthorized commands instead, were fir…