English
Related papers

Related papers: Breaking the Illusion of Security via Interpretati…

200 papers

While transformer-based models dominate NLP and vision applications, their underlying mechanisms to map the input space to the label space semantically are not well understood. In this paper, we study the sources of known representation…

Computer Vision and Pattern Recognition · Computer Science 2025-02-10 Chashi Mahiul Islam , Samuel Jacob Chacko , Mao Nishino , Xiuwen Liu

Foundation models represent the most prominent and recent paradigm shift in artificial intelligence. Foundation models are large models, trained on broad data that deliver high accuracy in many downstream tasks, often without fine-tuning.…

Cryptography and Security · Computer Science 2025-09-15 Hondamunige Prasanna Silva , Federico Becattini , Lorenzo Seidenari

Recent studies have demonstrated the vulnerability of Automatic Speech Recognition systems to adversarial examples, which can deceive these systems into misinterpreting input speech commands. While previous research has primarily focused on…

Sound · Computer Science 2025-11-21 Aravindhan G , Yuvaraj Govindarajulu , Parin Shah

Providing explanations for deep neural network (DNN) models is crucial for their use in security-sensitive domains. A plethora of interpretation models have been proposed to help users understand the inner workings of DNNs: how does a DNN…

Cryptography and Security · Computer Science 2019-09-19 Xinyang Zhang , Ningfei Wang , Hua Shen , Shouling Ji , Xiapu Luo , Ting Wang

Vision Transformers (ViT) are competing to replace Convolutional Neural Networks (CNN) for various computer vision tasks in medical imaging such as classification and segmentation. While the vulnerability of CNNs to adversarial attacks is a…

Computer Vision and Pattern Recognition · Computer Science 2022-08-08 Faris Almalik , Mohammad Yaqub , Karthik Nandakumar

Vision Transformers (ViTs) have recently achieved competitive performance in broad vision tasks. Unfortunately, on popular threat models, naturally trained ViTs are shown to provide no more adversarial robustness than convolutional neural…

Computer Vision and Pattern Recognition · Computer Science 2022-10-17 Yichuan Mo , Dongxian Wu , Yifei Wang , Yiwen Guo , Yisen Wang

Many machine learning models are vulnerable to adversarial examples: inputs that are specially crafted to cause a machine learning model to produce an incorrect output. Adversarial examples that affect one model often affect another model,…

Cryptography and Security · Computer Science 2016-05-25 Nicolas Papernot , Patrick McDaniel , Ian Goodfellow

Although researchers' attention is more focused on the performance of Transformer models, the interpretation of Transformer can never be ignored. Gradient is widely utilized in Transformer interpretation. From the perspective of attention…

Artificial Intelligence · Computer Science 2026-05-13 Yongjin Cui , Xiaohui Fan , Huajun Chen

Studies have shown that machine learning systems are vulnerable to adversarial examples in theory and practice. Where previous attacks have focused mainly on visual models that exploit the difference between human and machine perception,…

Cryptography and Security · Computer Science 2025-07-23 Eldor Abdukhamidov , Tamer Abuhmed , Joanna C. S. Santos , Mohammed Abuhamad

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

The major part of the vanilla vision transformer (ViT) is the attention block that brings the power of mimicking the global context of the input image. For better performance, ViT needs large-scale training data. To overcome this data…

Computer Vision and Pattern Recognition · Computer Science 2021-09-21 Ahmed Aldahdooh , Wassim Hamidouche , Olivier Deforges

A common belief is that intrinsically interpretable deep learning models ensure a correct, intuitive understanding of their behavior and offer greater robustness against accidental errors or intentional manipulation. However, these beliefs…

Machine Learning · Computer Science 2025-11-24 Hubert Baniecki , Przemyslaw Biecek

Due to the high cost of training, large model (LM) practitioners commonly use pretrained models downloaded from untrusted sources, which could lead to owning compromised models. In-context learning is the ability of LMs to perform multiple…

Cryptography and Security · Computer Science 2024-09-09 Gorka Abad , Stjepan Picek , Lorenzo Cavallaro , Aitor Urbieta

With the perpetual increase of complexity of the state-of-the-art deep neural networks, it becomes a more and more challenging task to maintain their interpretability. Our work aims to evaluate the effects of adversarial training utilized…

Computer Vision and Pattern Recognition · Computer Science 2023-11-21 Delyan Boychev

Vision Transformers are increasingly embedded in industrial systems due to their superior performance, but their memory and power requirements make deploying them to edge devices a challenging task. Hence, model compression techniques are…

Machine Learning · Computer Science 2022-09-29 Swapnil Parekh , Devansh Shah , Pratyush Shukla

Although attention mechanisms have become fundamental components of deep learning models, they are vulnerable to perturbations, which may degrade the prediction performance and model interpretability. Adversarial training (AT) for attention…

Computation and Language · Computer Science 2022-12-27 Shunsuke Kitada , Hitoshi Iyatomi

In this paper, we ask whether Vision Transformers (ViTs) can serve as an underlying architecture for improving the adversarial robustness of machine learning models against evasion attacks. While earlier works have focused on improving…

Computer Vision and Pattern Recognition · Computer Science 2023-02-03 Edoardo Debenedetti , Vikash Sehwag , Prateek Mittal

In this work we demonstrate the vulnerability of vision transformers (ViTs) to gradient-based inversion attacks. During this attack, the original data batch is reconstructed given model weights and the corresponding gradients. We introduce…

Computer Vision and Pattern Recognition · Computer Science 2022-03-29 Ali Hatamizadeh , Hongxu Yin , Holger Roth , Wenqi Li , Jan Kautz , Daguang Xu , Pavlo Molchanov

The success of adversarial attacks to speaker recognition is mainly in white-box scenarios. When applying the adversarial voices that are generated by attacking white-box surrogate models to black-box victim models, i.e.…

Sound · Computer Science 2023-02-22 Jiadi Yao , Hong Luo , Xiao-Lei Zhang

Thanks to recent advances in deep neural networks (DNNs), face recognition systems have become highly accurate in classifying a large number of face images. However, recent studies have found that DNNs could be vulnerable to adversarial…

Machine Learning · Computer Science 2020-01-29 Kazuya Kakizaki , Kosuke Yoshida