Quantization as a Malicious Task: Removing Quantization-Conditioned Backdoors via Task Arithmetic

Computer Science > Cryptography and Security [Submitted on 18 Jun 2026] Quantization as a Malicious Task: Removing Quantization-Conditioned Backdoors via Task Arithmetic Kaihsun Yang, Min-Yan Tsai, Chia-Mu Yu Model quantization is widely adopted to reduce memory usage and inference cost when deploying deep neural networks on resource-constrained devices. However, recent studies have revealed a new security threat known as Quantization-Conditioned Backdoors (QCBs), where a model behaves normally in full precision but activates malicious behavior only after quantization. Existing defenses typically modify quantization procedures or correct activation statistics, often introducing additional computational overhead or relying on specific quantization settings. Here, we present QVec, a parameter-space perspective for defending against QCBs. We observe that the weight difference between a full-precision model and its quantized counterpart encodes a structured behavioral shift, which can be interpreted as a malicious task vector rather than random quantization noise. Based on this insight, QVec counteracts this malicious direction through controlled parameter correction prior to deployment. QVec requires no retraining, no trigger samples, and only a single quantization pass to estimate the parameter shift, together with a lightweight hyperparameter search. Extensive experiments across image classification benchmarks and multiple Large Language Model (LLM) attack scenarios demonstrate that QVec consistently suppresses backdoor activation while preserving clean performance. Subjects: Cryptography and Security (cs.CR) Cite as: arXiv:2606.20254 [cs.CR]   (or arXiv:2606.20254v1 [cs.CR] for this version)   https://doi.org/10.48550/arXiv.2606.20254 Focus to learn more Submission history From: Chia-Mu Yu [view email] [v1] Thu, 18 Jun 2026 14:05:19 UTC (1,002 KB) Access Paper: HTML (experimental) view license Current browse context: cs.CR < prev   |   next > new | recent | 2026-06 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)