AGENTQ: Quantization-Conditioned Backdoor Attacks on LLM Agents
AGENTQ is proposed, an attack framework that combines layer-banded LoRA injection with partial-PGD repair over a multi-codebook quantization-equivalence class that preserves normal agentic capability while concentrating malicious behavior in the quantized model, underscoring the need to make quantization-aware safety e...
Xiao-Qun Liu, Qi-Ben Yan
· 0 citations