English
Related papers

Related papers: Attention Hijacking in Trojan Transformers

200 papers

Intrigued by the inherent ability of the human visual system to identify salient regions in complex scenes, attention mechanisms have been seamlessly integrated into various Computer Vision (CV) tasks. Building upon this paradigm, Vision…

Transformer models are revolutionizing machine learning, but their inner workings remain mysterious. In this work, we present a new visualization technique designed to help researchers understand the self-attention mechanism in transformers…

Human-Computer Interaction · Computer Science 2023-08-10 Catherine Yeh , Yida Chen , Aoyu Wu , Cynthia Chen , Fernanda Viégas , Martin Wattenberg

Machine learning models that use deep neural networks (DNNs) are vulnerable to backdoor attacks. An adversary carrying out a backdoor attack embeds a predefined perturbation called a trigger into a small subset of input samples and trains…

Cryptography and Security · Computer Science 2023-09-06 Arezoo Rajabi , Surudhi Asokraj , Fengqing Jiang , Luyao Niu , Bhaskar Ramasubramanian , Jim Ritcey , Radha Poovendran

Vision Transformers (ViTs) have emerged as powerful architectures in medical image analysis, excelling in tasks such as disease detection, segmentation, and classification. However, their reliance on large, attention-driven models makes…

Cryptography and Security · Computer Science 2025-10-30 Banafsheh Saber Latibari , Najmeh Nazari , Hossein Sayadi , Houman Homayoun , Abhijit Mahalanobis

Vision Transformers (ViTs) are becoming a very popular paradigm for vision tasks as they achieve state-of-the-art performance on image classification. However, although early works implied that this network structure had increased…

Computer Vision and Pattern Recognition · Computer Science 2023-02-01 Hugo Lemarchant , Liangzi Li , Yiming Qian , Yuta Nakashima , Hajime Nagahara

Vision Transformers (ViT) have recently demonstrated exemplary performance on a variety of vision tasks and are being used as an alternative to CNNs. Their design is based on a self-attention mechanism that processes images as a sequence of…

Computer Vision and Pattern Recognition · Computer Science 2022-06-20 Akshayvarun Subramanya , Aniruddha Saha , Soroush Abbasi Koohpayegani , Ajinkya Tejankar , Hamed Pirsiavash

The multi-head self-attention mechanism of the transformer model has been thoroughly investigated recently. In one vein of study, researchers are interested in understanding why and how transformers work. In another vein, researchers…

Computation and Language · Computer Science 2022-10-28 Raymond Li , Wen Xiao , Linzi Xing , Lanjun Wang , Gabriel Murray , Giuseppe Carenini

Deep Neural Networks (DNNs) have been applied successfully in computer vision. However, their wide adoption in image-related applications is threatened by their vulnerability to trojan attacks. These attacks insert some misbehavior at…

Computer Vision and Pattern Recognition · Computer Science 2020-07-03 Miguel Villarreal-Vasquez , Bharat Bhargava

Neural networks are growing more capable on their own, but we do not understand their neural mechanisms. Understanding these mechanisms' decision-making processes, or mechanistic interpretability, enables (1) accountability and control in…

Computation and Language · Computer Science 2026-03-02 Mason Kadem , Rong Zheng

Recent studies show that Vision Transformers(ViTs) exhibit strong robustness against various corruptions. Although this property is partly attributed to the self-attention mechanism, there is still a lack of systematic understanding. In…

Computer Vision and Pattern Recognition · Computer Science 2022-11-09 Daquan Zhou , Zhiding Yu , Enze Xie , Chaowei Xiao , Anima Anandkumar , Jiashi Feng , Jose M. Alvarez

Deep Neural Networks (DNNs) have found extensive applications in safety-critical artificial intelligence systems, such as autonomous driving and facial recognition systems. However, recent research has revealed their susceptibility to…

Cryptography and Security · Computer Science 2024-08-20 Lingxin Jin , Xianyu Wen , Wei Jiang , Jinyu Zhan

Language models for code such as CodeBERT offer the capability to learn advanced source code representation, but their opacity poses barriers to understanding of captured properties. Recent attention analysis studies provide initial…

Software Engineering · Computer Science 2023-11-23 Mootez Saad , Tushar Sharma

Along with the success of deep neural network (DNN) models, rise the threats to the integrity of these models. A recent threat is the Trojan attack where an attacker interferes with the training pipeline by inserting triggers into some of…

Computer Vision and Pattern Recognition · Computer Science 2020-12-09 Marzieh Edraki , Nazmul Karim , Nazanin Rahnavard , Ajmal Mian , Mubarak Shah

The encoder-decoder is the typical framework for Neural Machine Translation (NMT), and different structures have been developed for improving the translation performance. Transformer is one of the most promising structures, which can…

Computation and Language · Computer Science 2018-12-11 Kaitao Song , Xu Tan , Furong Peng , Jianfeng Lu

Vision transformers rely on a patch token based self attention mechanism, in contrast to convolutional networks. We investigate fundamental differences between these two families of models, by designing a block sparsity based adversarial…

Computer Vision and Pattern Recognition · Computer Science 2021-10-12 Ameya Joshi , Gauri Jagatap , Chinmay Hegde

Neural architectures based on attention such as vision transformers are revolutionizing image recognition. Their main benefit is that attention allows reasoning about all parts of a scene jointly. In this paper, we show how the global…

Computer Vision and Pattern Recognition · Computer Science 2022-03-28 Giulio Lovisotto , Nicole Finnie , Mauricio Munoz , Chaithanya Kumar Mummadi , Jan Hendrik Metzen

We present a novel attention mechanism: Causal Attention (CATT), to remove the ever-elusive confounding effect in existing attention-based vision-language models. This effect causes harmful bias that misleads the attention module to focus…

Computer Vision and Pattern Recognition · Computer Science 2021-03-08 Xu Yang , Hanwang Zhang , Guojun Qi , Jianfei Cai

In recent years, knowledge distillation has become a cornerstone of efficiently deployed machine learning, with labs and industries using knowledge distillation to train models that are inexpensive and resource-optimized. Trojan attacks…

Machine Learning · Computer Science 2023-03-13 Leonard Tang , Tom Shlomi , Alexander Cai

Large pre-trained neural networks such as BERT have had great recent success in NLP, motivating a growing body of research investigating what aspects of language they are able to learn from unlabeled data. Most recent analysis has focused…

Computation and Language · Computer Science 2019-06-12 Kevin Clark , Urvashi Khandelwal , Omer Levy , Christopher D. Manning

Large Language Models (LLMs) have revolutionized various domains but remain vulnerable to prompt injection attacks, where malicious inputs manipulate the model into ignoring original instructions and executing designated action. In this…

Cryptography and Security · Computer Science 2025-04-24 Kuo-Han Hung , Ching-Yun Ko , Ambrish Rawat , I-Hsin Chung , Winston H. Hsu , Pin-Yu Chen
‹ Prev 1 4 5 6 7 8 10 Next ›