2 papers
cs.CR2025
Anti-Phishing Training (Still) Does Not Work: A Large-Scale Reproduction of Phishing Training Inefficacy Grounded in the NIST Phish Scale
Andrew T. Rozema, James C. Davis
Social engineering attacks delivered via email, commonly known as phishing, represent a persistent cybersecurity threat leading to significant organizational incidents and data bre…
cs.CL2025
Advancing Jailbreak Strategies: A Hybrid Approach to Exploiting LLM Vulnerabilities and Bypassing Modern Defenses
Mohamed Ahmed, Mohamed Abdelmouty, Mingyu Kim +3
The advancement of Pre-Trained Language Models (PTLMs) and Large Language Models (LLMs) has led to their widespread adoption across diverse applications. Despite their success, the…