English
Related papers

Related papers: HotFlip: White-Box Adversarial Examples for Text C…

200 papers

Adversarial examples can be useful for identifying vulnerabilities in AI systems before they are deployed. In reinforcement learning (RL), adversarial policies can be developed by training an adversarial agent to minimize a target agent's…

Artificial Intelligence · Computer Science 2023-10-17 Stephen Casper , Taylor Killian , Gabriel Kreiman , Dylan Hadfield-Menell

Recent NLP literature pays little attention to the robustness of toxicity language predictors, while these systems are most likely to be used in adversarial contexts. This paper presents a novel adversarial attack, \texttt{ToxicTrap},…

Computation and Language · Computer Science 2024-04-16 Dmitriy Bespalov , Sourav Bhabesh , Yi Xiang , Liutong Zhou , Yanjun Qi

The capabilities of large language models (LLMs) have been successfully applied in the context of table representation learning. The recently proposed tabular language models have reported state-of-the-art results across various tasks for…

Computation and Language · Computer Science 2023-09-19 Aneta Koleva , Martin Ringsquandl , Volker Tresp

Vision-language pre-training models (VLPs) have exhibited revolutionary improvements in various vision-language tasks. In VLP, some adversarial attacks fool a model into false or absurd classifications. Previous studies addressed these…

Computer Vision and Pattern Recognition · Computer Science 2023-09-07 Hiroki Azuma , Yusuke Matsui

Machine learning models are powerful but fallible. Generating adversarial examples - inputs deliberately crafted to cause model misclassification or other errors - can yield important insight into model assumptions and vulnerabilities.…

Machine Learning · Computer Science 2017-12-18 Catherine Wong

Contrastive Language-Image Pre-training (CLIP) has demonstrated impressive capabilities in open-vocabulary classification. The class token in the image encoder is trained to capture the global features to distinguish different text…

Computer Vision and Pattern Recognition · Computer Science 2023-12-21 Yuqi Lin , Minghao Chen , Kaipeng Zhang , Hengjia Li , Mingming Li , Zheng Yang , Dongqin Lv , Binbin Lin , Haifeng Liu , Deng Cai

Recent advances in mechanistic interpretability suggest that intermediate attention layers encode token-level hypotheses that are iteratively refined toward the final output. In this work, we exploit this property to generate adversarial…

Computation and Language · Computer Science 2026-01-01 Kaustubh Dhole

Adversarial examples in NLP are receiving increasing research attention. One line of investigation is the generation of word-level adversarial examples against fine-tuned Transformer models that preserve naturalness and grammaticality.…

Computation and Language · Computer Science 2022-10-24 Maximilian Mozes , Bennett Kleinberg , Lewis D. Griffin

The vulnerability of deep neural networks to adversarial attacks has been widely demonstrated (e.g., adversarial example attacks). Traditional attacks perform unstructured pixel-wise perturbation to fool the classifier. An alternative…

Machine Learning · Computer Science 2022-05-23 Shuo Wang , Surya Nepal , Carsten Rudolph , Marthie Grobler , Shangyu Chen , Tianle Chen

Adversarial examples have proven to threaten speaker identification systems, and several countermeasures against them have been proposed. In this paper, we propose a method to detect the presence of adversarial examples, i.e., a binary…

Sound · Computer Science 2024-03-01 Sonal Joshi , Thomas Thebaud , Jesús Villalba , Najim Dehak

Deep neural network (DNN) as a popular machine learning model is found to be vulnerable to adversarial attack. This attack constructs adversarial examples by adding small perturbations to the raw input, while appearing unmodified to human…

Machine Learning · Computer Science 2018-09-14 Pengcheng Li , Jinfeng Yi , Lijun Zhang

Multi-class text classification is one of the key problems in machine learning and natural language processing. Emerging neural networks deal with the problem using a multi-output softmax layer and achieve substantial progress, but they do…

Computation and Language · Computer Science 2020-03-26 Haiyang Xu , Junwen Chen , Kun Han , Xiangang Li

In cross-lingual text classification, one seeks to exploit labeled data from one language to train a text classification model that can then be applied to a completely different language. Recent multilingual representation models have made…

Computation and Language · Computer Science 2020-07-31 Xin Dong , Yaxin Zhu , Yupeng Zhang , Zuohui Fu , Dongkuan Xu , Sen Yang , Gerard de Melo

Deep neural networks are vulnerable to adversarial attacks, which can fool them by adding minuscule perturbations to the input images. The robustness of existing defenses suffers greatly under white-box attack settings, where an adversary…

Computer Vision and Pattern Recognition · Computer Science 2019-07-30 Aamir Mustafa , Salman Khan , Munawar Hayat , Roland Goecke , Jianbing Shen , Ling Shao

Recent work in black-box adversarial attacks for NLP systems has attracted much attention. Prior black-box attacks assume that attackers can observe output labels from target models based on selected inputs. In this work, inspired by…

Machine Learning · Computer Science 2022-09-21 Siddhartha Datta

The growing interest for adversarial examples, i.e. maliciously modified examples which fool a classifier, has resulted in many defenses intended to detect them, render them inoffensive or make the model more robust against them. In this…

Machine Learning · Computer Science 2021-03-04 Rémi Bernhard , Pierre-Alain Moellic , Jean-Max Dutertre

The transferability of adversarial examples across deep neural network (DNN) models is the crux of a spectrum of black-box attacks. In this paper, we propose a novel method to enhance the black-box transferability of baseline adversarial…

Computer Vision and Pattern Recognition · Computer Science 2020-08-21 Qizhang Li , Yiwen Guo , Hao Chen

Machine learning (ML) classifiers are vulnerable to adversarial examples. An adversarial example is an input sample which is slightly modified to induce misclassification in an ML classifier. In this work, we investigate white-box and…

Cryptography and Security · Computer Science 2019-04-17 Yonghong Huang , Utkarsh Verma , Celeste Fralick , Gabriel Infante-Lopez , Brajesh Kumarz , Carl Woodward

Neural network based classifiers are still prone to manipulation through adversarial perturbations. State of the art attacks can overcome most of the defense or detection mechanisms suggested so far, and adversaries have the upper hand in…

Machine Learning · Computer Science 2018-12-05 Ziv Katzir , Yuval Elovici

Deep convolutional neural networks can be highly vulnerable to small perturbations of their inputs, potentially a major issue or limitation on system robustness when using deep networks as classifiers. In this paper we propose a low-cost…

Machine Learning · Computer Science 2019-12-16 Amir Nazemi , Paul Fieguth