SOURCE-LINKED INTELLIGENCE

AGENTQ: Quantization-Conditioned Backdoor Attacks on LLM Agents

arXiv · AI, language, vision and robotics · article · Sep 12, 2026 · UTC

Quantization is one of the default deployment paths for open-weight LLM agents, but it is not behavior-preserving: an adversary can release a full-precision checkpoint that passes audits yet misbehaves once quantized, termed as quantization-conditioned attack (QCA). Prior QCA work targets free-text generation, where harm is mediated by a human reader. In contrast, the agentic setting poses a more severe risk: the triggered payload is a structured function that can be executed without human oversight. We present the first study of QCA against LLM agents. We find that directly adapting prior bac

Read original source ↗ Open in workspace

recordType

paper

region

Global