English
Related papers

Related papers: Transformers -- Messages in Disguise

200 papers

Deep Neural Networks (DNNs) are known to be vulnerable to adversarial attacks, i.e., an imperceptible perturbation to the input can mislead DNNs trained on clean images into making erroneous predictions. To tackle this, adversarial training…

Machine Learning · Computer Science 2025-01-07 Yonggan Fu , Qixuan Yu , Yang Zhang , Shang Wu , Xu Ouyang , David Cox , Yingyan Celine Lin

In this work, we study the performance of Reed-Solomon codes against an adversary that first permutes the symbols of the codeword and then performs insertions and deletions. This adversarial model is motivated by the recent interest in…

Information Theory · Computer Science 2025-06-27 Roni Con

Deep networks are highly vulnerable to adversarial attacks, yet conventional attack methods utilize static adversarial perturbations that induce fixed mispredictions. In this work, we exploit an overlooked property of adversarial…

Computer Vision and Pattern Recognition · Computer Science 2025-03-11 Yaoteng Tan , Zikui Cai , M. Salman Asif

We propose a new homomorphic encryption scheme based on the hardness of decoding under independent random noise from certain affine families of codes. Unlike in previous lattice-based homomorphic encryption schemes, where the message is…

Cryptography and Security · Computer Science 2011-11-21 Andrej Bogdanov , Chin Ho Lee

Convolutional neural networks have been used to achieve a string of successes during recent years, but their lack of interpretability remains a serious issue. Adversarial examples are designed to deliberately fool neural networks into…

Machine Learning · Computer Science 2020-04-28 Jan Philip Göpfert , André Artelt , Heiko Wersing , Barbara Hammer

Inspired by the principles of speed reading, we introduce Skim-RNN, a recurrent neural network (RNN) that dynamically decides to update only a small fraction of the hidden state for relatively unimportant input tokens. Skim-RNN gives…

Computation and Language · Computer Science 2018-03-30 Minjoon Seo , Sewon Min , Ali Farhadi , Hannaneh Hajishirzi

In the past decades, the rise of artificial intelligence has given us the capabilities to solve the most challenging problems in our day-to-day lives, such as cancer prediction and autonomous navigation. However, these applications might…

Cryptography and Security · Computer Science 2022-09-13 Ehsan Nowroozi , Mohammadreza Mohammadi , Pargol Golmohammadi , Yassine Mekdad , Mauro Conti , Selcuk Uluagac

The adversarial attacks against deep neural networks on computer vision tasks have spawned many new technologies that help protect models from avoiding false predictions. Recently, word-level adversarial attacks on deep models of Natural…

Computation and Language · Computer Science 2020-06-15 Zhaoyang Wang , Hongtao Wang

This paper contributes to a development of randomized methods for neural networks. The proposed learner model is generated incrementally by stochastic configuration (SC) algorithms, termed as Stochastic Configuration Networks (SCNs). In…

Neural and Evolutionary Computing · Computer Science 2018-02-14 Dianhui Wang , Ming Li

Today, the security of many domains rely on the use of Machine Learning to detect threats, identify vulnerabilities, and safeguard systems from attacks. Recently, transformer architectures have improved the state-of-the-art performance on a…

Cryptography and Security · Computer Science 2023-10-19 Kunyang Li , Kyle Domico , Jean-Charles Noirot Ferrand , Patrick McDaniel

We present a new algorithm to train a robust neural network against adversarial attacks. Our algorithm is motivated by the following two ideas. First, although recent work has demonstrated that fusing randomness can improve the robustness…

Machine Learning · Computer Science 2019-05-07 Xuanqing Liu , Yao Li , Chongruo Wu , Cho-Jui Hsieh

Ethereum 2.0 is a major upgrade to improve its scalability, throughput, and security. In this version, RANDAO is the scheme to randomly select the users who propose, confirm blocks, and get rewards. However, a vulnerability, referred to as…

Cryptography and Security · Computer Science 2024-03-15 Do Hai Son , Tran Thi Thuy Quynh , Le Quang Minh

Recurrent neural network (RNN) is an effective neural network in solving very complex supervised and unsupervised tasks. There has been a significant improvement in RNN field such as natural language processing, speech processing, computer…

Cryptography and Security · Computer Science 2019-01-15 Mohammed Harun Babu R , Vinayakumar R , Soman KP

Though CNNs have achieved the state-of-the-art performance on various vision tasks, they are vulnerable to adversarial examples --- crafted by adding human-imperceptible perturbations to clean images. However, most of the existing…

Computer Vision and Pattern Recognition · Computer Science 2019-06-04 Cihang Xie , Zhishuai Zhang , Yuyin Zhou , Song Bai , Jianyu Wang , Zhou Ren , Alan Yuille

The results of the Anomalous Diffusion Challenge (AnDi Challenge) have shown that machine learning methods can outperform classical statistical methodology at the characterization of anomalous diffusion in both the inference of the…

Machine Learning · Computer Science 2023-01-18 Nicolás Firbas , Òscar Garibo-i-Orts , Miguel Ángel Garcia-March , J. Alberto Conejero

This study presents a novel model for invertible sentence embeddings using a residual recurrent network trained on an unsupervised encoding task. Rather than the probabilistic outputs common to neural machine translation models, our…

Computation and Language · Computer Science 2023-04-07 Jeremy Wilkerson

Deep learning is widely applied to modern problems through neural networks, but the growing computational and energy demands of these models have driven interest in more efficient approaches. Spiking Neural Networks (SNNs), the third…

Cryptography and Security · Computer Science 2025-11-18 Mahitha Pulivathi , Ana Fontes Rodrigues , Isibor Kennedy Ihianle , Andreas Oikonomou , Srinivas Boppu , Pedro Machado

As deep neural networks (DNNs) are widely applied in the physical world, many researches are focusing on physical-world adversarial examples (PAEs), which introduce perturbations to inputs and cause the model's incorrect outputs. However,…

Computer Vision and Pattern Recognition · Computer Science 2024-12-24 Yichen Wang , Yuxuan Chou , Ziqi Zhou , Hangtao Zhang , Wei Wan , Shengshan Hu , Minghui Li

Neural machine translation systems tend to fail on less decent inputs despite its significant efficacy, which may significantly harm the credibility of this systems-fathoming how and when neural-based systems fail in such cases is critical…

Computation and Language · Computer Science 2020-05-27 Wei Zou , Shujian Huang , Jun Xie , Xinyu Dai , Jiajun Chen

We consider the problem of secure unicast transmission between two nodes in a directed graph, where an adversary eavesdrops/jams a subset of nodes. This adversarial setting is in contrast to traditional ones where the adversary controls a…

Information Theory · Computer Science 2013-03-04 Pak Hou Che , Minghua Chen , Tracey Ho , Sidharth Jaggi , Michael Langberg