paper-with-me

Papers

Backdoor Mitigation in Deep Neural Networks via Strategic Retraining

2022-12-14 · Akshay Dhonthi, Ernst Moritz Hahn, Vahid Hashemi

Deep Neural Networks (DNN) are becoming increasingly more important in assisted and automated driving. Using such entities which are obtained using machine learning is inevitable: tasks such as recognizing traffic signs cannot be developed reasonably using traditional software development methods. DNN however do have the problem that they are mostly black boxes and therefore hard to understand and debug. One particular problem is that they are prone to hidden backdoors. This means that the DNN misclassifies its input, because it considers properties that should not be decisive for the output. Backdoors may either be introduced by malicious attackers or by inappropriate training. In any case, detecting and removing them is important in the automotive area, as they might lead to safety violations with potentially severe consequences. In this paper, we introduce a novel method to remove backdoors. Our method works for both intentional as well as unintentional backdoors. We also do not require prior knowledge about the shape or distribution of backdoors. Experimental evidence shows that our method performs well on several medium-sized examples.

📄 PDF Abstract BibTeX arXiv:2212.07278

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Unlearn to Relearn Backdoors: Deferred Backdoor Functionality Attacks on Deep Learning Models

2024-11-10 · Jeongjin Shin, Sangdon Park

Deep learning models are vulnerable to backdoor attacks, where adversaries inject malicious functionality during training that activates on trigger inputs at inference time. Extensive research has focused on developing s…

Backdoor Attack

Plan2Cleanse: Test-Time Backdoor Defense via Monte-Carlo Planning in Deep Reinforcement Learning

2026-05-10 · Sze-Ann Chen, Zhi-Yi Chin, Kui-Yuan Chen, Chi-Yu Li 외 arxiv

Ensuring the security of reinforcement learning (RL) models is critical, particularly when they are trained by third parties and deployed in real-world systems. Attackers can implant backdoors into these models, causing …

Reinforcement LearningAtari Games

Exploiting Layer-Specific Vulnerabilities to Backdoor Attack in Federated Learning

2026-02-16 · Mohammad Hadi Foroughi, Seyed Hamed Rastegar, Mohammad Sabokrou, Ahmad Khonsari arxiv

Federated learning (FL) enables distributed model training across edge devices while preserving data locality. This decentralized approach has emerged as a promising solution for collaborative learning on sensitive user …

Federated Learning

SPBA: Utilizing Speech Large Language Model for Backdoor Attacks on Speech Classification Models

2025-06-10 · Wenhan Yao, Fen Xiao, Xiarun Chen, Jia Liu 외

Deep speech classification tasks, including keyword spotting and speaker verification, are vital in speech-based human-computer interaction. Recently, the security of these technologies has been revealed to be susceptibl…

Backdoor AttackKeyword SpottingLanguage ModelingLanguage Modelling+2

Triggers Hijack Language Circuits: A Mechanistic Analysis of Backdoor Behaviors in Large Language Models

2026-02-11 · Théo Lasnier, Wissam Antoun, Francis Kulumba, Djamé Seddah arxiv

Backdoor attacks pose significant security risks for Large Language Models (LLMs), yet the internal mechanisms by which triggers operate remain poorly understood. We present the first mechanistic analysis of language-swi…