Showing cs.CRShow all
2 papers · 1 filter
cs.CR2026
Defending against Adaptive Prompt Injection Attacks via Reasoning-enabled Task Alignment
Lipeng He, Yihan Wang, Jiawen Zhang +1
Indirect prompt injection attacks hijack LLM-based agents by embedding malicious instructions in third-party data that the agent retrieves during task execution. Existing defenses…
cs.CR2026
Backdooring Bias in Large Language Models
Anudeep Das, Prach Chantasantitam, Gurjot Singh +3
Large language models (LLMs) are increasingly deployed in settings where inducing a bias toward a certain topic can have significant consequences, and backdoor attacks can be used…