conftrace_

prompt injection attack

4 papers

Explore in graph

Also known as

PIA

Co-occurring keywords · papers mentioning both

large language model (2) instruction-following model (1) kv-cache editing (1) neural attribution (1) prompt hijacking (1) prompt extraction (1) tool integration (1) adversarial evaluation (1) security benchmark (1) attack success rate (1)

Papers

CachePrune: Teaching LLMs What Not to Follow via KV-Cache Editing ACL 2026 InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model Agents ACL 2024 Scaling Behavior of Machine Translation with Large Language Models under Prompt Injection Attacks EACL 2024 Tensor Trust: Interpretable Prompt Injection Attacks from an Online Game ICLR 2024