English
Related papers

Related papers: MINIMAL: Mining Models for Data Free Universal Adv…

200 papers

Discrete adversarial attacks are symbolic perturbations to a language input that preserve the output label but lead to a prediction error. While such attacks have been extensively explored for the purpose of evaluating model robustness,…

Machine Learning · Computer Science 2021-11-02 Maor Ivgi , Jonathan Berant

The natural language generation (NLG) module in a task-oriented dialogue system produces user-facing utterances conveying required information. Thus, it is critical for the generated response to be natural and fluent. We propose to…

Computation and Language · Computer Science 2020-05-07 Chenguang Zhu

Adversarial attacks present a significant threat to modern machine learning systems. Yet, existing detection methods often lack the ability to detect unseen attacks or detect different attack types with a high level of accuracy. In this…

Cryptography and Security · Computer Science 2025-10-06 Chinthana Wimalasuriya , Spyros Tragoudas

Many adversarial attacks target natural language processing systems, most of which succeed through modifying the individual tokens of a document. Despite the apparent uniqueness of each of these attacks, fundamentally they are simply a…

Computation and Language · Computer Science 2024-01-09 Tom Roth , Yansong Gao , Alsharif Abuadbba , Surya Nepal , Wei Liu

To guarantee safe and robust deployment of large language models (LLMs) at scale, it is critical to accurately assess their adversarial robustness. Existing adversarial attacks typically target harmful responses in single-point greedy…

Machine Learning · Computer Science 2026-02-24 Tim Beyer , Yan Scholten , Leo Schwinn , Stephan Günnemann

Neural Networks (NNs) are vulnerable to adversarial examples. Such inputs differ only slightly from their benign counterparts yet provoke misclassifications of the attacked NNs. The required perturbations to craft the examples are often…

Cryptography and Security · Computer Science 2020-09-30 Philip Sperl , Konstantin Böttinger

We consider the problem of learning textual entailment models with limited supervision (5K-10K training examples), and present two complementary approaches for it. First, we propose knowledge-guided adversarial example generators for…

Computation and Language · Computer Science 2018-05-15 Dongyeop Kang , Tushar Khot , Ashish Sabharwal , Eduard Hovy

Vulnerability of various machine learning methods to adversarial examples has been recently explored in the literature. Power systems which use these vulnerable methods face a huge threat against adversarial examples. To this end, we first…

Cryptography and Security · Computer Science 2022-02-16 Jiwei Tian , Buhong Wang , Jing Li , Zhen Wang , Mete Ozay

Adversarial examples are data points misclassified by neural networks. Originally, adversarial examples were limited to adding small perturbations to a given image. Recent work introduced the generalized concept of unrestricted adversarial…

Machine Learning · Computer Science 2020-05-20 Martin Kotuliak , Sandro E. Schoenborn , Andrei Dan

The rapid growth of deep learning has brought about powerful models that can handle various tasks, like identifying images and understanding language. However, adversarial attacks, an unnoticed alteration, can deceive models, leading to…

Computer Vision and Pattern Recognition · Computer Science 2025-11-18 Sampriti Soor , Alik Pramanick , Jothiprakash K , Arijit Sur

Adversarial training is one of the most effective methods for enhancing model robustness. Recent approaches incorporate adversarial distillation in adversarial training architectures. However, we notice two scenarios of defense methods that…

Machine Learning · Computer Science 2024-08-26 Zhenyu Liu , Haoran Duan , Huizhi Liang , Yang Long , Vaclav Snasel , Guiseppe Nicosia , Rajiv Ranjan , Varun Ojha

Adversarial attacks on machine learning algorithms have been a key deterrent to the adoption of AI in many real-world use cases. They significantly undermine the ability of high-performance neural networks by forcing misclassifications.…

Machine Learning · Computer Science 2024-04-04 Nandish Chattopadhyay , Atreya Goswami , Anupam Chattopadhyay

Standard language model training employs gold human documents or human-human interaction data, and treats all training data as positive examples. Growing evidence shows that even with very large amounts of positive training data, issues…

Computation and Language · Computer Science 2022-11-14 Leonard Adolphs , Tianyu Gao , Jing Xu , Kurt Shuster , Sainbayar Sukhbaatar , Jason Weston

Adversarial machine learning concerns situations in which learners face attacks from active adversaries. Such scenarios arise in applications such as spam email filtering, malware detection and fake image generation, where security methods…

Machine Learning · Computer Science 2025-10-07 David Benfield , Stefano Coniglio , Phan Tu Vuong , Alain Zemkoho

To understand the complexity of sequence classification tasks, Hahn et al. (2021) proposed sensitivity as the number of disjoint subsets of the input sequence that can each be individually changed to change the output. Though effective,…

Computation and Language · Computer Science 2025-02-12 Saurabh Kumar Pandey , Sachin Vashistha , Debrup Das , Somak Aditya , Monojit Choudhury

We study an important and challenging task of attacking natural language processing models in a hard label black box setting. We propose a decision-based attack strategy that crafts high quality adversarial examples on text classification…

Computation and Language · Computer Science 2021-04-30 Rishabh Maheshwary , Saket Maheshwary , Vikram Pudi

Deep neural networks have been shown to exhibit an intriguing vulnerability to adversarial input images corrupted with imperceptible perturbations. However, the majority of adversarial attacks assume global, fine-grained control over the…

Computer Vision and Pattern Recognition · Computer Science 2019-08-19 Ameya Joshi , Amitangshu Mukherjee , Soumik Sarkar , Chinmay Hegde

Masked language models like BERT can perform text classification in a zero-shot fashion by reformulating downstream tasks as text infilling. However, this approach is highly sensitive to the template used to prompt the model, yet…

Computation and Language · Computer Science 2022-10-27 Mozes van de Kar , Mengzhou Xia , Danqi Chen , Mikel Artetxe

Adversarial training, a method for learning robust deep neural networks, constructs adversarial examples during training. However, recent methods for generating NLP adversarial examples involve combinatorial search and expensive sentence…

Computation and Language · Computer Science 2021-09-14 Jin Yong Yoo , Yanjun Qi

Adversarial training has become the primary method to defend against adversarial samples. However, it is hard to practically apply due to many shortcomings. One of the shortcomings of adversarial training is that it will reduce the…

Machine Learning · Computer Science 2021-08-31 Zhishen Nie , Ying Lin , Sp Ren , Lan Zhang