activity
20212026
most citedDARTSRepair: Core-failure-set Guided DARTS for Network Robustness to Common Corruptions

12 citations · 14 across the 5 of their papers we have counts for

collaborators
Showing cs.CRShow all

1 paper · 1 filter

cs.CR2026

Toward Metacognitive One-Shot Indirect Prompt Injection: Strategy Abstraction Via Outcome-Conditioned Reflection

Sihan Hou, Xinmeng Hou, Zhijun Zhang +5

Tool-using large language model (LLM) agents are vulnerable to indirect prompt injection (IPI), in which malicious instructions embedded in external observations manipulate subsequ…