Exploring Dynamic Properties of Backdoor Training Through Information Bottleneck
Understanding how backdoor data influences neural network training dynamics remains a complex and underexplored challenge. In this paper, we present a rigorous analysis of the impact of backdoor data on the learning process, with a particular focus on the distinct behaviors between the target class and other clean classes. Leveraging the Information Bottleneck (IB) principle connected with clustering of internal representation, We find that backdoor attacks create unique mutual information (MI) signatures, which evolve across training phases and differ based on the attack mechanism. Our analysis uncovers a surprising trade-off: visually conspicuous attacks like BadNets can achieve high stealthiness from an information-theoretic perspective, integrating more seamlessly into the model than many visually imperceptible attacks. Building on these insights, we propose a novel, dynamics-based stealthiness metric that quantifies an attack's integration at the model level. We validate our findings and the proposed metric across multiple datasets and diverse attack types, offering a new dimension for understanding and evaluating backdoor threats. Our code is available in: https://github.com/XinyuLiu71/Information_Bottleneck_Backdoor.git.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
ICLShield: Exploring and Mitigating In-Context Learning Backdoor Attacks
In-context learning (ICL) has demonstrated remarkable success in large language models (LLMs) due to its adaptability and parameter-free nature. However, it also introduces a critical vulnerability to backdoor attacks, w…
In-Context LearningA Survey of Recent Backdoor Attacks and Defenses in Large Language Models
Large Language Models (LLMs), which bridge the gap between human language understanding and complex problem-solving, achieve state-of-the-art performance on several NLP tasks, particularly in few-shot and zero-shot setti…
parameter-efficient fine-tuningBackdoor in Seconds: Unlocking Vulnerabilities in Large Pre-trained Models via Model Editing
Large pre-trained models have achieved notable success across a range of downstream tasks. However, recent research shows that a type of adversarial attack ($\textit{i.e.,}$ backdoor attack) can manipulate the behavior o…
Adversarial AttackBackdoor AttackImage Captioningimage-classification+3Large Language Models Are Better Adversaries: Exploring Generative Clean-Label Backdoor Attacks Against Text Classifiers
Backdoor attacks manipulate model predictions by inserting innocuous triggers into training and test data. We focus on more realistic and more challenging clean-label attacks where the adversarial training examples are c…
BadFusion: 2D-Oriented Backdoor Attacks against 3D Object Detection
3D object detection plays an important role in autonomous driving; however, its vulnerability to backdoor attacks has become evident. By injecting ''triggers'' to poison the training dataset, backdoor attacks manipulate …
2D Object Detection3D Object DetectionAutonomous DrivingBackdoor Attack+3