activity
20242026
most citedA Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations

1 citations · 2 across the 6 of their papers we have counts for

collaborators
Showing cs.LGShow all

1 paper · 1 filter

cs.LG2026

Efficient and Adaptable Detection of Malicious LLM Prompts via Bootstrap Aggregation

Shayan Ali Hassan, Tao Ni, Zaeem Mohtashim Khan +2

Large Language Models have demonstrated remarkable capabilities in natural language understanding. However, they remain susceptible to malicious prompts that induce unsafe or polic…