paper-with-me

Papers

Don't FREAK Out: A Frequency-Inspired Approach to Detecting Backdoor Poisoned Samples in DNNs

2023-03-23 · Hasan Abed Al Kader Hammoud, Adel Bibi, Philip H. S. Torr, Bernard Ghanem

In this paper we investigate the frequency sensitivity of Deep Neural Networks (DNNs) when presented with clean samples versus poisoned samples. Our analysis shows significant disparities in frequency sensitivity between these two types of samples. Building on these findings, we propose FREAK, a frequency-based poisoned sample detection algorithm that is simple yet effective. Our experimental results demonstrate the efficacy of FREAK not only against frequency backdoor attacks but also against some spatial attacks. Our work is just the first step in leveraging these insights. We believe that our analysis and proposed defense mechanism will provide a foundation for future research and development of backdoor defenses.

📄 PDF Abstract BibTeX arXiv:2303.13211

Code (0)

등록된 구현이 없습니다.

Tasks

Sensitivity

Similar Papers 제목 키워드 기반

Backdoor Defense via Test-Time Detecting and Repairing

2024-01-01 · CVPR 2024 1 · Jiyang Guan, Jian Liang, Ran He

Deep neural networks have played a crucial part in many critical domains such as autonomous driving face recognition and medical diagnosis. However deep neural networks are facing security threats from backdoor attac…

Autonomous Drivingbackdoor defenseFace RecognitionMedical Diagnosis

Acquiring Clean Language Models from Backdoor Poisoned Datasets by Downscaling Frequency Space

2024-02-19 · Zongru Wu, Zhuosheng Zhang, Pengzhou Cheng, Gongshen Liu

Despite the notable success of language models (LMs) in various natural language processing (NLP) tasks, the reliability of LMs is susceptible to backdoor attacks. Prior research attempts to mitigate backdoor learning wh…

Robust Backdoor Removal by Reconstructing Trigger-Activated Changes in Latent Representation

2025-11-12 · Kazuki Iwahana, Yusuke Yamasaki, Akira Ito, Takayuki Miura 외 arxiv

Backdoor attacks pose a critical threat to machine learning models, causing them to behave normally on clean data but misclassify poisoned data into a poisoned class. Existing defenses often attempt to identify and remov…

When Backdoors Speak: Understanding LLM Backdoor Attacks Through Model-Generated Explanations

2024-11-19 · Huaizhi Ge, Yiming Li, Qifan Wang, Yongfeng Zhang 외

Large Language Models (LLMs) are known to be vulnerable to backdoor attacks, where triggers embedded in poisoned samples can maliciously alter LLMs' behaviors. In this paper, we move beyond attacking LLMs and instead exa…

Backdoor AttackExplanation GenerationSentence

From Poisoned to Aware: Fostering Backdoor Self-Awareness in LLMs

2025-10-05 · Guangyu Shen, Siyuan Cheng, Xiangzhe Xu, Yuan Zhou 외 arxiv

Large Language Models (LLMs) can acquire deceptive behaviors through backdoor attacks, where the model executes prohibited actions whenever secret triggers appear in the input. Existing safety training methods largely fa…

Reinforcement Learning