English
Related papers

Related papers: Attacking interpretable NLP systems

200 papers

Deep neural networks are vulnerable to adversarial attacks. White-box adversarial attacks can fool neural networks with small adversarial perturbations, especially for large size images. However, keeping successful adversarial perturbations…

Computer Vision and Pattern Recognition · Computer Science 2020-11-11 Yongwei Wang , Mingquan Feng , Rabab Ward , Z. Jane Wang , Lanjun Wang

Numerous recent studies have demonstrated how Deep Neural Network (DNN) classifiers can be fooled by adversarial examples, in which an attacker adds perturbations to an original sample, causing the classifier to misclassify the sample.…

Machine Learning · Computer Science 2021-02-09 Yigit Alparslan , Ken Alparslan , Jeremy Keim-Shenk , Shweta Khade , Rachel Greenstadt

DNN-based image classifiers are susceptible to adversarial attacks. Most previous adversarial attacks do not have clear patterns, making it difficult to interpret attacks' results and gain insights into classifiers' mechanisms. Therefore,…

Computer Vision and Pattern Recognition · Computer Science 2024-09-12 Ryoya Nara , Yusuke Matsui

Recent works have revealed the vulnerability of automatic speech recognition (ASR) models to adversarial examples (AEs), i.e., small perturbations that cause an error in the transcription of the audio signal. Studying audio adversarial…

Sound · Computer Science 2022-03-21 Marie Biolková , Bac Nguyen

We demonstrate that state-of-the-art optical character recognition (OCR) based on deep learning is vulnerable to adversarial images. Minor modifications to images of printed text, which do not change the meaning of the text to a human…

Machine Learning · Computer Science 2018-02-16 Congzheng Song , Vitaly Shmatikov

Deep learning models are susceptible to adversarial attacks, where slight perturbations to input data lead to misclassification. Adversarial attacks become increasingly effective with access to information about the targeted classifier. In…

Machine Learning · Computer Science 2024-05-29 Yu Zhe , Rei Nagaike , Daiki Nishiyama , Kazuto Fukuchi , Jun Sakuma

With the rapid development of deep learning, object detectors have demonstrated impressive performance; however, vulnerabilities still exist in certain scenarios. Current research exploring the vulnerabilities using adversarial patches…

Computer Vision and Pattern Recognition · Computer Science 2025-03-04 Boming Miao , Chunxiao Li , Yao Zhu , Weixiang Sun , Zizhe Wang , Xiaoyi Wang , Chuanlong Xie

Recent research showed that deep neural networks are highly sensitive to so-called adversarial perturbations, which are tiny perturbations of the input data purposely designed to fool a machine learning classifier. Most classification…

Machine Learning · Computer Science 2018-01-15 Akram Erraqabi , Aristide Baratin , Yoshua Bengio , Simon Lacoste-Julien

Deep learning-based object detection has become ubiquitous in the last decade due to its high accuracy in many real-world applications. With this growing trend, these models are interested in being attacked by adversaries, with most of the…

Computer Vision and Pattern Recognition · Computer Science 2024-12-30 Pham Phuc , Son Vuong , Khang Nguyen , Tuan Dang

Deep neural networks (DNNs) are known to be vulnerable to adversarial examples. Existing works have mostly focused on either digital adversarial examples created via small and imperceptible perturbations, or physical-world adversarial…

Computer Vision and Pattern Recognition · Computer Science 2020-06-23 Ranjie Duan , Xingjun Ma , Yisen Wang , James Bailey , A. K. Qin , Yun Yang

Despite the great success of deep neural networks, the adversarial attack can cheat some well-trained classifiers by small permutations. In this paper, we propose another type of adversarial attack that can cheat classifiers by significant…

Machine Learning · Computer Science 2019-07-23 Sanli Tang , Xiaolin Huang , Mingjian Chen , Chengjin Sun , Jie Yang

Adversarial examples seem to be inevitable. These specifically crafted inputs allow attackers to arbitrarily manipulate machine learning systems. Even worse, they often seem harmless to human observers. In our digital society, this poses a…

Cryptography and Security · Computer Science 2021-06-04 Thorsten Eisenhofer , Lea Schönherr , Joel Frank , Lars Speckemeier , Dorothea Kolossa , Thorsten Holz

Deep neural networks are susceptible to \emph{adversarial} attacks. In computer vision, well-crafted perturbations to images can cause neural networks to make mistakes such as confusing a cat with a computer. Previous adversarial attacks…

Machine Learning · Computer Science 2019-09-12 Gamaleldin F. Elsayed , Ian Goodfellow , Jascha Sohl-Dickstein

Adversarial attacks, wherein slight inputs are carefully crafted to mislead intelligent models, have attracted increasing attention. However, a critical gap persists between theoretical advancements and practical application, particularly…

Cryptography and Security · Computer Science 2025-06-26 Sabrine Ennaji , Elhadj Benkhelifa , Luigi V. Mancini

Deep neural networks have been shown to be fooled rather easily using adversarial attack algorithms. Practical methods such as adversarial patches have been shown to be extremely effective in causing misclassification. However, these…

Computer Vision and Pattern Recognition · Computer Science 2019-09-26 Akshayvarun Subramanya , Vipin Pillai , Hamed Pirsiavash

Machine learning approaches for speech enhancement are becoming increasingly expressive, enabling ever more powerful modifications of input signals. In this paper, we demonstrate that this expressiveness introduces a vulnerability: advanced…

Audio and Speech Processing · Electrical Eng. & Systems 2026-05-01 Rostislav Makarov , Lea Schönherr , Timo Gerkmann

In recent years, deep learning has shown performance breakthroughs in many applications, such as image detection, image segmentation, pose estimation, and speech recognition. However, this comes with a major concern: deep networks have been…

Machine Learning · Computer Science 2019-01-11 Felix Kreuk , Assi Barak , Shir Aviv-Reuven , Moran Baruch , Benny Pinkas , Joseph Keshet

Deep learning models are used in safety-critical tasks such as automated driving and face recognition. However, small perturbations in the model input can significantly change the predictions. Adversarial attacks are used to identify small…

Cryptography and Security · Computer Science 2025-12-03 Issa Oe , Keiichiro Yamamura , Hiroki Ishikura , Ryo Hamahira , Katsuki Fujisawa

The ability to deploy neural networks in real-world, safety-critical systems is severely limited by the presence of adversarial examples: slightly perturbed inputs that are misclassified by the network. In recent years, several techniques…

Machine Learning · Computer Science 2018-02-21 Nicholas Carlini , Guy Katz , Clark Barrett , David L. Dill

Deep learning models are susceptible to adversarial samples in white and black-box environments. Although previous studies have shown high attack success rates, coupling DNN models with interpretation models could offer a sense of security…

Computer Vision and Pattern Recognition · Computer Science 2023-07-14 Eldor Abdukhamidov , Mohammed Abuhamad , Simon S. Woo , Eric Chan-Tin , Tamer Abuhmed