paper-with-me

홈 › Papers

Deep Learning Backdoors

2020-07-16 · Shaofeng Li, Shiqing Ma, Minhui Xue, Benjamin Zi Hao Zhao

Intuitively, a backdoor attack against Deep Neural Networks (DNNs) is to inject hidden malicious behaviors into DNNs such that the backdoor model behaves legitimately for benign inputs, yet invokes a predefined malicious behavior when its input contains a malicious trigger. The trigger can take a plethora of forms, including a special object present in the image (e.g., a yellow pad), a shape filled with custom textures (e.g., logos with particular colors) or even image-wide stylizations with special filters (e.g., images altered by Nashville or Gotham filters). These filters can be applied to the original image by replacing or perturbing a set of image pixels.

📄 PDF Abstract BibTeX arXiv:2007.08273

Code (0)

등록된 구현이 없습니다.

Tasks

Backdoor AttackDeep Learning

Similar Papers 제목 키워드 기반

Backdoor Vulnerabilities in Normally Trained Deep Learning Models

2022-11-29 · Guanhong Tao, Zhenting Wang, Siyuan Cheng, Shiqing Ma 외

We conduct a systematic study of backdoor vulnerabilities in normally trained Deep Learning models. They are as dangerous as backdoors injected by data poisoning because both can be equally exploited. We leverage 20 diff…

Data PoisoningDeep Learning

Interactive Simulations of Backdoors in Neural Networks

2024-05-21 · Peter Bajcsy, Maxime Bros

This work addresses the problem of planting and defending cryptographic-based backdoors in artificial intelligence (AI) models. The motivation comes from our lack of understanding and the implications of using cryptograp…

backdoor defense

Backdoor Unlearning Generalization: A Path Toward the Removal of Unknown Triggers in LLMs

2026-06-02 · Lisa Bouger, Théo Lasnier, Philippe Loubet Moundi, Yannick Teglia 외 arxiv

Backdoor attacks in Large Language Models (LLMs) are a growing security concern, where models can generate adversary-chosen content. Existing defenses target backdoors one at a time and typically require knowledge of the…

Continual Pretraining

Blind Backdoors in Deep Learning Models

2020-05-08 · Eugene Bagdasaryan, Vitaly Shmatikov

We investigate a new method for injecting backdoors into machine learning models, based on compromising the loss-value computation in the model-training code. We use it to demonstrate new classes of backdoors strictly mo…

Deep Learning

Backdoors in Neural Models of Source Code

2020-06-11 · Goutham Ramakrishnan, Aws Albarghouthi

Deep neural networks are vulnerable to a range of adversaries. A particularly pernicious class of vulnerabilities are backdoors, where model predictions diverge in the presence of subtle triggers in inputs. An attacker c…