paper-with-me

홈 › Papers

BEAGLE: Forensics of Deep Learning Backdoor Attack for Better Defense

2023-01-16 · Siyuan Cheng, Guanhong Tao, Yingqi Liu, Shengwei An, Xiangzhe Xu, Shiwei Feng, Guangyu Shen, Kaiyuan Zhang, QiuLing Xu, Shiqing Ma, Xiangyu Zhang

Deep Learning backdoor attacks have a threat model similar to traditional cyber attacks. Attack forensics, a critical counter-measure for traditional cyber attacks, is hence of importance for defending model backdoor attacks. In this paper, we propose a novel model backdoor forensics technique. Given a few attack samples such as inputs with backdoor triggers, which may represent different types of backdoors, our technique automatically decomposes them to clean inputs and the corresponding triggers. It then clusters the triggers based on their properties to allow automatic attack categorization and summarization. Backdoor scanners can then be automatically synthesized to find other instances of the same type of backdoor in other models. Our evaluation on 2,532 pre-trained models, 10 popular attacks, and comparison with 9 baselines show that our technique is highly effective. The decomposed clean inputs and triggers closely resemble the ground truth. The synthesized scanners substantially outperform the vanilla versions of existing scanners that can hardly generalize to different kinds of attacks.

📄 PDF Abstract BibTeX arXiv:2301.06241

Code (1)

megum1/beagle 공식 구현 pytorch

Tasks

Backdoor AttackDeep Learning

Similar Papers 제목 키워드 기반

Poison Forensics: Traceback of Data Poisoning Attacks in Neural Networks

2021-10-13 · Shawn Shan, Arjun Nitin Bhagoji, Haitao Zheng, Ben Y. Zhao

In adversarial machine learning, new defenses against attacks on deep learning systems are routinely broken soon after their release by more powerful attacks. In this context, forensic tools can offer a valuable compleme…

Data PoisoningMalware Classification

Rethink the Evaluation for Attack Strength of Backdoor Attacks in Natural Language Processing

2022-01-09 · Lingfeng Shen, Haiyun Jiang, Lemao Liu, Shuming Shi

It has been shown that natural language processing (NLP) models are vulnerable to a kind of security threat called the Backdoor Attack, which utilizes a `backdoor trigger' paradigm to mislead the models. The most threate…

Backdoor AttackText Classification

Fine-Tuning Is All You Need to Mitigate Backdoor Attacks

2022-12-18 · Zeyang Sha, Xinlei He, Pascal Berrang, Mathias Humbert 외

Backdoor attacks represent one of the major threats to machine learning models. Various efforts have been made to mitigate backdoors. However, existing defenses have become increasingly complex and often require high com…

All

From Shortcuts to Triggers: Backdoor Defense with Denoised PoE

2023-05-24 · Qin Liu, Fei Wang, Chaowei Xiao, Muhao Chen

Language models are often at risk of diverse backdoor attacks, especially data poisoning. Thus, it is important to investigate defense solutions for addressing them. Existing backdoor defense methods mainly focus on back…

backdoor defenseData PoisoningDenoisingSentence+1

Tracing Back the Malicious Clients in Poisoning Attacks to Federated Learning

2024-07-09 · Yuqi Jia, Minghong Fang, Hongbin Liu, Jinghuai Zhang 외

Poisoning attacks compromise the training phase of federated learning (FL) such that the learned global model misclassifies attacker-chosen inputs called target inputs. Existing defenses mainly focus on protecting the tr…

Federated Learning