Your Compiler is Backdooring Your Model: Understanding and Exploiting Compilation Inconsistency Vulnerabilities in Deep Learning Compilers
Deep learning (DL) compilers are core infrastructure in modern DL systems, offering flexibility and scalability beyond vendor-specific libraries. This work uncovers a fundamental vulnerability in their design: can an official, unmodified compiler alter a model's semantics during compilation and introduce hidden backdoors? We study both adversarial and natural settings. In the adversarial case, we craft benign models where triggers have no effect pre-compilation but become effective backdoors after compilation. Tested on six models, three commercial compilers, and two hardware platforms, our attack yields 100% success on triggered inputs while preserving normal accuracy and remaining undetected by state-of-the-art detectors. The attack generalizes across compilers, hardware, and floating-point settings. In the natural setting, we analyze the top 100 HuggingFace models (including one with 220M+ downloads) and find natural triggers in 31 models. This shows that compilers can introduce risks even without adversarial manipulation. Our results reveal an overlooked threat: unmodified DL compilers can silently alter model semantics. To our knowledge, this is the first work to expose inherent security risks in DL compiler design, opening a new direction for secure and trustworthy ML.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Turning Your Weakness Into a Strength: Watermarking Deep Neural Networks by Backdooring
Deep Neural Networks have recently gained lots of success after enabling several breakthroughs in notoriously challenging problems. Training these networks is computationally expensive and requires vast amounts of traini…
General ClassificationBring Your Own Codegen to Deep Learning Compiler
Deep neural networks (DNNs) have been ubiquitously applied in many applications, and accelerators are emerged as an enabler to support the fast and efficient inference tasks of these applications. However, to achieve hig…
Code GenerationDeep LearningBootstrap Your Own Variance
Understanding model uncertainty is important for many applications. We propose Bootstrap Your Own Variance (BYOV), combining Bootstrap Your Own Latent (BYOL), a negative-free Self-Supervised Learning (SSL) algorithm, wit…
Self-Supervised LearningKnowYourNyms? A Game of Semantic Relationships
Semantic relation knowledge is crucial for natural language understanding. We introduce {``}KnowYourNyms?{''}, a web-based game for learning semantic relations. While providing users with an engaging experience, the appl…
Natural Language UnderstandingRelationText ClassificationRun Away From your Teacher: Understanding BYOL by a Novel Self-Supervised Approach
Recently, a newly proposed self-supervised framework Bootstrap Your Own Latent (BYOL) seriously challenges the necessity of negative samples in contrastive learning frameworks. BYOL works like a charm despite the fact th…
Contrastive LearningSelf-Supervised Learning