paper-with-me

Papers

RAP: Robustness-Aware Perturbations for Defending against Backdoor Attacks on NLP Models

2021-10-15 · EMNLP 2021 11 · Wenkai Yang, Yankai Lin, Peng Li, Jie zhou, Xu sun

Backdoor attacks, which maliciously control a well-trained model's outputs of the instances with specific triggers, are recently shown to be serious threats to the safety of reusing deep neural networks (DNNs). In this work, we propose an efficient online defense mechanism based on robustness-aware perturbations. Specifically, by analyzing the backdoor training process, we point out that there exists a big gap of robustness between poisoned and clean samples. Motivated by this observation, we construct a word-based robustness-aware perturbation to distinguish poisoned samples from clean samples to defend against the backdoor attacks on natural language processing (NLP) models. Moreover, we give a theoretical analysis about the feasibility of our robustness-aware perturbation-based defense method. Experimental results on sentiment analysis and toxic detection tasks show that our method achieves better defending performance and much lower computational costs than existing online defense methods. Our code is available at https://github.com/lancopku/RAP.

📄 PDF Abstract BibTeX arXiv:2110.07831

Code (1)

lancopku/rap 공식 구현 pytorch

Tasks

Sentiment Analysis

Similar Papers 제목 키워드 기반

Backdoor or Manipulation? Graph Mixture of Experts Can Defend Against Various Graph Adversarial Attacks

2025-10-17 · Yuyuan Feng, Bin Ma, Enyan Dai arxiv

Extensive research has highlighted the vulnerability of graph neural networks (GNNs) to adversarial attacks, including manipulation, node injection, and the recently emerging threat of backdoor attacks. However, existing…

Defending Text-to-image Diffusion Models: Surprising Efficacy of Textual Perturbations Against Backdoor Attacks

2024-08-28 · Oscar Chew, Po-Yi Lu, Jayden Lin, Hsuan-Tien Lin

Text-to-image diffusion models have been widely adopted in real-world applications due to their ability to generate realistic images from textual descriptions. However, recent studies have shown that these methods are vu…

backdoor defense

On Certifying Robustness against Backdoor Attacks via Randomized Smoothing

2020-02-26 · Binghui Wang, Xiaoyu Cao, Jinyuan Jia, Neil Zhenqiang Gong

Backdoor attack is a severe security threat to deep neural networks (DNNs). We envision that, like adversarial examples, there will be a cat-and-mouse game for backdoor attacks, i.e., new empirical defenses are developed…

Backdoor Attack

DECK: Model Hardening for Defending Pervasive Backdoors

2022-06-18 · Guanhong Tao, Yingqi Liu, Siyuan Cheng, Shengwei An 외

Pervasive backdoors are triggered by dynamic and pervasive input perturbations. They can be intentionally injected by attackers or naturally exist in normally trained models. They have a different nature from the traditi…

Decodermodel

Robustness Inspired Graph Backdoor Defense

2024-06-14 · Zhiwei Zhang, Minhua Lin, Junjie Xu, Zongyu Wu 외

Graph Neural Networks (GNNs) have achieved promising results in tasks such as node classification and graph classification. However, recent studies reveal that GNNs are vulnerable to backdoor attacks, posing a significan…

backdoor defenseGraph ClassificationNode Classification