English
Related papers

Related papers: From Feature Visualization to Visual Circuits: Eff…

200 papers

As humans, we inherently perceive images based on their predominant features, and ignore noise embedded within lower bit planes. On the contrary, Deep Neural Networks are known to confidently misclassify images corrupted with meticulously…

Computer Vision and Pattern Recognition · Computer Science 2020-04-02 Sravanti Addepalli , Vivek B. S. , Arya Baburaj , Gaurang Sriramanan , R. Venkatesh Babu

The visual pathway involves complex networks of cells and regions which contribute to the encoding and processing of visual information. While some aspects of visual perception are understood, there are still many unanswered questions…

Neurons and Cognition · Quantitative Biology 2024-01-09 Peter Beech , Shanshan Jia , Zhaofei Yu , Jian K. Liu

We introduce a new type of indirect, cross-modal injection attacks against visual language models that enable creation of self-interpreting images. These images contain hidden "meta-instructions" that control how models answer users'…

Cryptography and Security · Computer Science 2025-06-16 Tingwei Zhang , Collin Zhang , John X. Morris , Eugene Bagdasarian , Vitaly Shmatikov

Vision-transformers (ViTs) and large-scale convolution-neural-networks (CNNs) have reshaped computer vision through pretrained feature representations that enable strong transfer learning for diverse tasks. However, their efficiency as…

Computer Vision and Pattern Recognition · Computer Science 2025-10-07 Alon Kaya , Igal Bilik , Inna Stainvas

Deep neural networks excel at image classification, but their performance is far less robust to input perturbations than human perception. In this work we explore whether this shortcoming may be partly addressed by incorporating…

Computer Vision and Pattern Recognition · Computer Science 2021-11-05 Bhavin Choksi , Milad Mozafari , Callum Biggs O'May , Benjamin Ador , Andrea Alamia , Rufin VanRullen

Visual-based recommender systems (VRSs) enhance recommendation performance by integrating users' feedback with the visual features of product images extracted from a deep neural network (DNN). Recently, human-imperceptible images…

Information Retrieval · Computer Science 2020-10-05 Vito Walter Anelli , Tommaso Di Noia , Daniele Malitesta , Felice Antonio Merra

Human observers engage in selective information uptake when classifying visual patterns. The same is true of deep neural networks, which currently constitute the best performing artificial vision systems. Our goal is to examine the…

Computer Vision and Pattern Recognition · Computer Science 2021-08-31 Chetan Ralekar , Shubham Choudhary , Tapan Kumar Gandhi , Santanu Chaudhury

The study of mechanistic interpretability aims to reverse-engineer a model to explain its behaviors. While recent studies have focused on the static mechanism of a certain behavior, the learning dynamics inside a model remain to be…

Machine Learning · Computer Science 2025-09-24 Yueyan Li , Wenhao Gao , Caixia Yuan , Xiaojie Wang

High-level visual brain regions contain subareas in which neurons appear to respond more strongly to examples of a particular semantic category, like faces or bodies, rather than objects. However, recent work has shown that while this…

Computer Vision and Pattern Recognition · Computer Science 2024-10-29 Alexander Lappe , Anna Bognár , Ghazaleh Ghamkhari Nejad , Albert Mukovskiy , Lucas Martini , Martin A. Giese , Rufin Vogels

Deep neural networks provide unprecedented performance in all image classification problems, taking advantage of huge amounts of data available for training. Recent studies, however, have shown their vulnerability to adversarial attacks,…

Computer Vision and Pattern Recognition · Computer Science 2020-09-24 Diego Gragnaniello , Francesco Marra , Giovanni Poggi , Luisa Verdoliva

We present FACADE, a novel probabilistic and geometric framework designed for unsupervised mechanistic anomaly detection in deep neural networks. Its primary goal is advancing the understanding and mitigation of adversarial attacks. FACADE…

Machine Learning · Computer Science 2023-07-21 Dhruv Pai , Andres Carranza , Rylan Schaeffer , Arnuv Tandon , Sanmi Koyejo

The field of deep learning is evolving in different directions, with still the need for more efficient training strategies. In this work, we present a novel and robust training scheme that integrates visual explanation techniques in the…

Computer Vision and Pattern Recognition · Computer Science 2021-07-30 David Morales , Estefania Talavera , Beatriz Remeseiro

We introduce a novel artificial neural network architecture that integrates robustness to adversarial input in the network structure. The main idea of our approach is to force the network to make predictions on what the given instance of…

Machine Learning · Computer Science 2016-07-15 Harm Berntsen , Wouter Kuijper , Tom Heskes

Understanding the mechanisms behind Vision Transformer (ViT), particularly its vulnerability to adversarial perturba tions, is crucial for addressing challenges in its real-world applications. Existing ViT adversarial attackers rely on la…

Cryptography and Security · Computer Science 2024-03-14 Chenxing Gao , Hang Zhou , Junqing Yu , YuTeng Ye , Jiale Cai , Junle Wang , Wei Yang

Deep neural networks are able to solve tasks across a variety of domains and modalities of data. Despite many empirical successes, we lack the ability to clearly understand and interpret the learned internal mechanisms that contribute to…

Artificial Intelligence · Computer Science 2018-01-03 Christopher Grimm , Dilip Arumugam , Siddharth Karamcheti , David Abel , Lawson L. S. Wong , Michael L. Littman

Fundamental questions remain about when and why adversarial examples arise in neural networks, with competing views characterising them either as artifacts of the irregularities in the decision landscape or as products of sensitivity to…

Machine Learning · Computer Science 2025-10-14 Edward Stevinson , Lucas Prieto , Melih Barsbey , Tolga Birdal

Despite the remarkable performance of deep neural networks on various computer vision tasks, they are known to be susceptible to adversarial perturbations, which makes it challenging to deploy them in real-world safety-critical…

Machine Learning · Computer Science 2020-07-03 Divyam Madaan , Jinwoo Shin , Sung Ju Hwang

Vision-language pretraining (VLP) with transformers has demonstrated exceptional performance across numerous multimodal tasks. However, the adversarial robustness of these models has not been thoroughly investigated. Existing multimodal…

Computer Vision and Pattern Recognition · Computer Science 2024-08-27 Jiwei Guan , Tianyu Ding , Longbing Cao , Lei Pan , Chen Wang , Xi Zheng

Vision Transformers (ViTs) have a radically different architecture with significantly less inductive bias than Convolutional Neural Networks. Along with the improvement in performance, security and robustness of ViTs are also of great…

Computer Vision and Pattern Recognition · Computer Science 2023-01-18 Khoa D. Doan , Yingjie Lao , Peng Yang , Ping Li

Adversarial examples raise questions about whether neural network models are sensitive to the same visual features as humans. In this paper, we first detect adversarial examples or otherwise corrupted images based on a class-conditional…

Machine Learning · Computer Science 2020-02-19 Yao Qin , Nicholas Frosst , Sara Sabour , Colin Raffel , Garrison Cottrell , Geoffrey Hinton