English
Related papers

Related papers: CLIP-Inspector: Model-Level Backdoor Detection for…

200 papers

Multimodal contrastive learning uses various data modalities to create high-quality features, but its reliance on extensive data sources on the Internet makes it vulnerable to backdoor attacks. These attacks insert malicious behaviors…

Cryptography and Security · Computer Science 2024-10-01 Kuanrong Liu , Siyuan Liang , Jiawei Liang , Pengwen Dai , Xiaochun Cao

In an out-of-distribution (OOD) detection problem, samples of known classes(also called in-distribution classes) are used to train a special classifier. In testing, the classifier can (1) classify the test samples of known classes to their…

Computer Vision and Pattern Recognition · Computer Science 2023-02-06 Sepideh Esmaeilpour , Bing Liu , Eric Robertson , Lei Shu

Backdoor data poisoning is an emerging form of adversarial attack usually against deep neural network image classifiers. The attacker poisons the training set with a relatively small set of images from one (or several) source class(es),…

Machine Learning · Computer Science 2020-10-16 Zhen Xiang , David J. Miller , George Kesidis

Detection of out-of-distribution (OOD) samples is crucial for safe real-world deployment of machine learning models. Recent advances in vision language foundation models have made them capable of detecting OOD samples without requiring…

Computer Vision and Pattern Recognition · Computer Science 2024-11-12 Hao Fu , Naman Patel , Prashanth Krishnamurthy , Farshad Khorrami

Prompt-based learning paradigm bridges the gap between pre-training and fine-tuning, and works effectively under the few-shot setting. However, we find that this learning paradigm inherits the vulnerability from the pre-training stage,…

Computation and Language · Computer Science 2022-04-12 Lei Xu , Yangyi Chen , Ganqu Cui , Hongcheng Gao , Zhiyuan Liu

Few-shot, fine-grained classification in computer vision poses significant challenges due to the need to differentiate subtle class distinctions with limited data. This paper presents a novel method that enhances the Contrastive…

Computer Vision and Pattern Recognition · Computer Science 2025-04-24 Eric Brouwer , Jan Erik van Woerden , Gertjan Burghouts , Matias Valdenegro-Toro , Marco Zullich

Vision-language models (VLMs), such as CLIP, have demonstrated impressive zero-shot capabilities for various downstream tasks. Their performance can be further enhanced through few-shot prompt tuning methods. However, current studies…

Computer Vision and Pattern Recognition · Computer Science 2024-06-04 Zhi Zhou , Ming Yang , Jiang-Xin Shi , Lan-Zhe Guo , Yu-Feng Li

Confidence calibration is critical for the safe deployment of machine learning models in the real world. However, such issue in vision-language models like CLIP, particularly after fine-tuning, has not been fully addressed. In this work, we…

Machine Learning · Computer Science 2025-05-30 Shuoyuan Wang , Yixuan Li , Hongxin Wei

The industry increasingly relies on deep learning (DL) technology for manufacturing inspections, which are challenging to automate with rule-based machine vision algorithms. DL-powered inspection systems derive defect patterns from labeled…

Machine Learning · Computer Science 2024-09-17 Altaf Allah Abbassi , Houssem Ben Braiek , Foutse Khomh , Thomas Reid

Fine-tuning large pre-trained computer vision models is infeasible for resource-limited users. Visual prompt learning (VPL) has thus emerged to provide an efficient and flexible alternative to model fine-tuning through Visual Prompt as a…

Cryptography and Security · Computer Science 2023-10-12 Hai Huang , Zhengyu Zhao , Michael Backes , Yun Shen , Yang Zhang

This paper tackles the challenge of detecting partially manipulated facial deepfakes, which involve subtle alterations to specific facial features while retaining the overall context, posing a greater detection difficulty than fully…

Computer Vision and Pattern Recognition · Computer Science 2025-03-27 Andrii Yermakov , Jan Cech , Jiri Matas

Contrastive Learning (CL) has attracted enormous attention due to its remarkable capability in unsupervised representation learning. However, recent works have revealed the vulnerability of CL to backdoor attacks: the feature extractor…

Cryptography and Security · Computer Science 2024-04-12 Weiyu Sun , Xinyu Zhang , Hao Lu , Yingcong Chen , Ting Wang , Jinghui Chen , Lu Lin

With the rise of deep learning in various applications, privacy concerns around the protection of training data have become a critical area of research. Whereas prior studies have focused on privacy risks in single-modal models, we…

Machine Learning · Computer Science 2024-07-10 Dominik Hintersdorf , Lukas Struppek , Manuel Brack , Felix Friedrich , Patrick Schramowski , Kristian Kersting

Stealthy data poisoning during fine-tuning can backdoor large language models (LLMs), threatening downstream safety. Existing detectors either use classifier-style probability signals--ill-suited to generation--or rely on rewriting, which…

Computation and Language · Computer Science 2025-11-13 Jinwen Chen , Hainan Zhang , Fei Sun , Qinnan Zhang , Sijia Wen , Ziwei Wang , Zhiming Zheng

Multimodal models like CLIP have gained significant attention due to their remarkable zero-shot performance across various tasks. However, studies have revealed that CLIP can inadvertently learn spurious associations between target…

Computer Vision and Pattern Recognition · Computer Science 2025-05-26 Wei Jie Yeo , Rui Mao , Moloud Abdar , Erik Cambria , Ranjan Satapathy

Backdoor attack introduces artificial vulnerabilities into the model by poisoning a subset of the training data via injecting triggers and modifying labels. Various trigger design strategies have been explored to attack text classifiers,…

Computation and Language · Computer Science 2021-09-23 Zichao Li , Dheeraj Mekala , Chengyu Dong , Jingbo Shang

With the swift advancement of deep learning, state-of-the-art algorithms have been utilized in various social situations. Nonetheless, some algorithms have been discovered to exhibit biases and provide unequal results. The current debiasing…

Machine Learning · Computer Science 2024-07-02 Shangxi Wu , Qiuyang He , Jian Yu , Jitao Sang

Model reprogramming adapts pretrained models to downstream tasks by modifying only the input and output spaces. Visual reprogramming (VR) is one instance for vision tasks that adds a trainable noise pattern (i.e., a visual prompt) to input…

Machine Learning · Computer Science 2025-06-03 Chengyi Cai , Zesheng Ye , Lei Feng , Jianzhong Qi , Feng Liu

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 remove backdoor neurons…

Machine Learning · Computer Science 2025-11-13 Kazuki Iwahana , Yusuke Yamasaki , Akira Ito , Takayuki Miura , Toshiki Shibahara

Large Language Models (LLMs), which bridge the gap between human language understanding and complex problem-solving, achieve state-of-the-art performance on several NLP tasks, particularly in few-shot and zero-shot settings. Despite the…

Cryptography and Security · Computer Science 2025-01-07 Shuai Zhao , Meihuizi Jia , Zhongliang Guo , Leilei Gan , Xiaoyu Xu , Xiaobao Wu , Jie Fu , Yichao Feng , Fengjun Pan , Luu Anh Tuan