English
Related papers

Related papers: Detecting Backdoors in Pre-trained Encoders

200 papers

Back-door attack poses a severe threat to deep learning systems. It injects hidden malicious behaviors to a model such that any input stamped with a special pattern can trigger such behaviors. Detecting back-door is hence of pressing need.…

Machine Learning · Computer Science 2021-08-03 Guangyu Shen , Yingqi Liu , Guanhong Tao , Shengwei An , Qiuling Xu , Siyuan Cheng , Shiqing Ma , Xiangyu Zhang

The objective of Open set recognition (OSR) is to learn a classifier that can reject the unknown samples while classifying the known classes accurately. In this paper, we propose a self-supervision method, Detransformation Autoencoder…

Machine Learning · Computer Science 2022-07-07 Jingyun Jia , Philip K. Chan

Deep neural networks have been demonstrated to be vulnerable to backdoor attacks. Specifically, by injecting a small number of maliciously constructed inputs into the training set, an adversary is able to plant a backdoor into the trained…

Machine Learning · Statistics 2019-12-10 Alexander Turner , Dimitris Tsipras , Aleksander Madry

Recently, more and more images are compressed and sent to the back-end devices for the machine analysis tasks~(\textit{e.g.,} object detection) instead of being purely watched by humans. However, most traditional or learned image codecs are…

Image and Video Processing · Electrical Eng. & Systems 2022-06-14 Guo Lu , Xingtong Ge , Tianxiong Zhong , Jing Geng , Qiang Hu

With the broad application of deep neural networks (DNNs), backdoor attacks have gradually attracted attention. Backdoor attacks are insidious, and poisoned models perform well on benign samples and are only triggered when given specific…

Machine Learning · Computer Science 2022-07-12 Chang Yue , Peizhuo Lv , Ruigang Liang , Kai Chen

This work investigates three methods for calculating loss for autoencoder-based pretraining of image encoders: The commonly used reconstruction loss, the more recently introduced deep perceptual similarity loss, and a feature prediction…

Computer Vision and Pattern Recognition · Computer Science 2021-05-19 Gustav Grund Pihlgren , Fredrik Sandin , Marcus Liwicki

Backdoor attack aims to compromise a model, which returns an adversary-wanted output when a specific trigger pattern appears yet behaves normally for clean inputs. Current backdoor attacks require changing pixels of clean images, which…

Computer Vision and Pattern Recognition · Computer Science 2023-09-15 Yusheng Guo , Nan Zhong , Zhenxing Qian , Xinpeng Zhang

Masked auto-encoder pre-training has emerged as a prevalent technique for initializing and enhancing dense retrieval systems. It generally utilizes additional Transformer decoder blocks to provide sustainable supervision signals and…

Information Retrieval · Computer Science 2024-04-23 Guangyuan Ma , Xing Wu , Zijia Lin , Songlin Hu

Organisations with limited data and computational resources increasingly outsource model training to Machine Learning as a Service (MLaaS) providers, who adapt vision-language models (VLMs) such as CLIP to downstream tasks via prompt tuning…

Cryptography and Security · Computer Science 2026-04-13 Akshit Jindal , Saket Anand , Chetan Arora , Vikram Goyal

We introduce Perception Encoder (PE), a state-of-the-art vision encoder for image and video understanding trained via simple vision-language learning. Traditionally, vision encoders have relied on a variety of pretraining objectives, each…

The advancement of visual tracking has continuously been brought by deep learning models. Typically, supervised learning is employed to train these models with expensive labeled data. In order to reduce the workload of manual annotations…

Computer Vision and Pattern Recognition · Computer Science 2020-07-24 Ning Wang , Wengang Zhou , Yibing Song , Chao Ma , Wei Liu , Houqiang Li

Compressive sensing is a method to recover the original image from undersampled measurements. In order to overcome the ill-posedness of this inverse problem, image priors are used such as sparsity in the wavelet domain, minimum…

Computer Vision and Pattern Recognition · Computer Science 2018-12-20 Magauiya Zhussip , Shakarim Soltanayev , Se Young Chun

Deep neural networks have achieved remarkable success across various applications; however, their vulnerability to backdoor attacks poses severe security risks -- especially in situations where only a limited set of clean samples is…

Cryptography and Security · Computer Science 2025-06-25 Nay Myat Min , Long H. Pham , Jun Sun

In spite of intense research efforts, deep neural networks remain vulnerable to adversarial examples: an input that forces the network to confidently produce incorrect outputs. Adversarial examples are typically generated by an attack…

Artificial Intelligence · Computer Science 2023-02-02 David Aaron Nicholson , Vincent Emanuele

Supervised fine-tuning has become the predominant method for adapting large pretrained models to downstream tasks. However, recent studies have revealed that these models are vulnerable to backdoor attacks, where even a small number of…

Cryptography and Security · Computer Science 2025-01-08 Peihai Jiang , Xixiang Lyu , Yige Li , Jing Ma

Backdoor attacks threaten Deep Neural Networks (DNNs). Towards stealthiness, researchers propose clean-label backdoor attacks, which require the adversaries not to alter the labels of the poisoned training datasets. Clean-label settings…

Cryptography and Security · Computer Science 2022-06-13 Nan Luo , Yuanzhang Li , Yajie Wang , Shangbo Wu , Yu-an Tan , Quanxin Zhang

Self-supervised contrastive learning is an effective approach for addressing the challenge of limited labelled data. This study builds upon the previously established two-stage patch-level, multi-label classification method for…

Computer Vision and Pattern Recognition · Computer Science 2026-02-09 Salma Haidar , José Oramas

Self-supervised learning (SSL), a paradigm harnessing unlabeled datasets to train robust encoders, has recently witnessed substantial success. These encoders serve as pivotal feature extractors for downstream tasks, demanding significant…

Cryptography and Security · Computer Science 2023-12-07 Xiaobei Li , Changchun Yin , Liyue Zhu , Xiaogang Xu , Liming Fang , Run Wang , Chenhao Lin

In this paper, we investigate self-supervised pre-training methods for document text recognition. Nowadays, large unlabeled datasets can be collected for many research tasks, including text recognition, but it is costly to annotate them.…

Computer Vision and Pattern Recognition · Computer Science 2024-05-02 Martin Kišš , Michal Hradiš

We present a framework to learn privacy-preserving encodings of images that inhibit inference of chosen private attributes, while allowing recovery of other desirable information. Rather than simply inhibiting a given fixed pre-trained…

Machine Learning · Computer Science 2018-12-06 Francesco Pittaluga , Sanjeev J. Koppal , Ayan Chakrabarti
‹ Prev 1 4 5 6 7 8 10 Next ›