QuantGuard: Learnable Rounding for Repairing Quantization-Conditioned Backdoors in LLMs

[2606.29239] QuantGuard: Learnable Rounding for Repairing Quantization-Conditioned Backdoors in LLMs Skip to main content Search Submit Donate Log in Computer Science > Cryptography and Security arXiv:2606.29239 (cs) [Submitted on 28 Jun 2026 ( v1 ), last revised 27 Aug 2026 (this version, v3)] Title: QuantGuard: Learnable Rounding for Repairing Quantization-Conditioned Backdoors in LLMs Authors: Aoying Zheng , Anqi Du , Zizhuang Deng , Yuxuan Chen , Shanqing Guo , Kening Zheng View PDF HTML (experimental) Abstract: Model quantization is a key technique for reducing storage and inference costs in large language model deployment. However, recent studies show that the discretization and rounding errors introduced by quantization can be exploited by adversaries to construct quantization-conditioned backdoor (QCB) attacks. Under such attacks, malicious behavior remains dormant at full precision and activates only after quantization, thereby bypassing conventional security auditing and detection. To address this threat, we propose QuantGuard, a proactive pre-quantization defense that learns safe rounding adjustments through differentiable optimization. Our method introduces differentiable rounding control variables and combines error-guided rounding reversal constraints, output-distribution consistency, and weight-distance regularization to regulate critical rounding behaviors. Crucially, QuantGuard utilizes only a small calibration dataset and does not modify existing quantization algorithms. This design disrupts the alignment between attacker-crafted weight patterns and quantization boundaries, suppressing post-quantization backdoor activation while preserving model functionality and performance. We conduct systematic experiments on six mainstream LLMs (including the LLaMA-3 and Qwen2.5-Coder) using three quantization precisions (INT8, FP4, and NF4) across three representative scenarios: vulnerable code generation, content injection, and over-refusal. The results show that QuantGuard consistently mitigates QCB attacks, reducing the attack success rate to a level comparable to the clean model while largely preserving general capability. With low computational overhead, QuantGuard provides a practical defense for secure quantized LLM deployment. Subjects: Cryptography and Security (cs.CR) Cite as: arXiv:2606.29239 [cs.CR] (or arXiv:2606.29239v3 [cs.CR] for this version) https://doi.org/10.48550/arXiv.2606.29239 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Aoying Zheng [ view email ] [v1] Sun, 28 Jun 2026 07:06:46 UTC (1,576 KB) [v2] Mon, 3 Aug 2026 15:22:02 UTC (1,577 KB) [v3] Thu, 27 Aug 2026 05:28:18 UTC (1,556 KB) Full-text links: Access Paper: View PDF HTML (experimental) TeX Source view license Additional Features Audio Summary Current browse context: cs.CR < prev | next > new | recent | 2026-06 Change to browse by: cs References & Citations SciX 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 Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab)

Related documents

• QuantGuard: Learnable Rounding for Repairing Quantization-Conditioned Backdoors in LLMs#677658
• Breaking the Rounding Trap: Securing LLMs against Quantization-Conditioned Backdoors#321770
• Contextual Utility of Quantization Moves in Extreme Low-Bit LLMs#673611
• GenTI: Benchmarking LLMs for Autonomous IDPS Rule Generation for Unseen Attacks#259351
• Generating Attacks for LLMs with GFlowNets#444582