English
Related papers

Related papers: Universal Adversarial Triggers

200 papers

In the past few years, it has become increasingly evident that deep neural networks are not resilient enough to withstand adversarial perturbations in input data, leaving them vulnerable to attack. Various authors have proposed strong…

Computation and Language · Computer Science 2023-04-19 Shreya Goyal , Sumanth Doddapaneni , Mitesh M. Khapra , Balaraman Ravindran

Prompt-based learning paradigm bridges the gap between pre-training and fine-tuning, and works effectively under the few-shot setting. However, we find that this learning paradigm inherits the vulnerability from the pre-training stage,…

Computation and Language · Computer Science 2022-04-12 Lei Xu , Yangyi Chen , Ganqu Cui , Hongcheng Gao , Zhiyuan Liu

Almost all adversarial attacks are formulated to add an imperceptible perturbation to an image in order to fool a model. Here, we consider the opposite which is adversarial examples that can fool a human but not a model. A large enough and…

Computer Vision and Pattern Recognition · Computer Science 2022-08-26 Ali Borji

Adversarial examples are intentionally crafted data with the purpose of deceiving neural networks into misclassification. When we talk about strategies to create such examples, we usually refer to perturbation-based methods that fabricate…

Computer Vision and Pattern Recognition · Computer Science 2018-06-28 Shih-hong Tsai

Machine Learning (ML) models are known to be vulnerable to adversarial inputs and researchers have demonstrated that even production systems, such as self-driving cars and ML-as-a-service offerings, are susceptible. These systems represent…

Machine Learning · Computer Science 2021-01-11 Marissa Dotter , Sherry Xie , Keith Manville , Josh Harguess , Colin Busho , Mikel Rodriguez

We investigate the robustness of reasoning models trained for step-by-step problem solving by introducing query-agnostic adversarial triggers - short, irrelevant text that, when appended to math problems, systematically mislead models to…

The Generative Adversarial Network (GAN) has achieved great success in generating realistic (real-valued) synthetic data. However, convergence issues and difficulties dealing with discrete data hinder the applicability of GAN to text. We…

Machine Learning · Statistics 2017-11-21 Yizhe Zhang , Zhe Gan , Kai Fan , Zhi Chen , Ricardo Henao , Dinghan Shen , Lawrence Carin

Large Language Models (LLMs) are powerful zero-shot assessors used in real-world situations such as assessing written exams and benchmarking systems. Despite these critical applications, no existing work has analyzed the vulnerability of…

Computation and Language · Computer Science 2024-07-08 Vyas Raina , Adian Liusie , Mark Gales

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

The growth of highly advanced Large Language Models (LLMs) constitutes a huge dual-use problem, making it necessary to create dependable AI-generated text detection systems. Modern detectors are notoriously vulnerable to adversarial…

Cryptography and Security · Computer Science 2025-10-06 Lekkala Sai Teja , Annepaka Yadagiri , Sangam Sai Anish , Siva Gopala Krishna Nuthakki , Partha Pakray

Targeted adversarial attacks are widely used to evaluate the robustness of neural machine translation systems. Unfortunately, this paper first identifies a critical issue in the existing settings of NMT targeted adversarial attacks, where…

Computation and Language · Computer Science 2024-07-09 Junjie Wu , Lemao Liu , Wei Bi , Dit-Yan Yeung

It has been shown that natural language processing (NLP) models are vulnerable to a kind of security threat called the Backdoor Attack, which utilizes a `backdoor trigger' paradigm to mislead the models. The most threatening backdoor attack…

Computation and Language · Computer Science 2022-02-17 Lingfeng Shen , Haiyun Jiang , Lemao Liu , Shuming Shi

Large language models (LLMs) have exhibited outstanding performance in natural language processing tasks. However, these models remain susceptible to adversarial attacks in which slight input perturbations can lead to harmful or misleading…

Computer Vision and Pattern Recognition · Computer Science 2024-12-19 Minkyoung Kim , Yunha Kim , Hyeram Seo , Heejung Choi , Jiye Han , Gaeun Kee , Soyoung Ko , HyoJe Jung , Byeolhee Kim , Young-Hak Kim , Sanghyun Park , Tae Joon Jun

Adversarial examples are perturbed inputs which can cause a serious threat for machine learning models. Finding these perturbations is such a hard task that we can only use the iterative methods to traverse. For computational efficiency,…

Computer Vision and Pattern Recognition · Computer Science 2020-06-11 Xiaofeng Mao , Yuefeng Chen , Yuhong Li , Yuan He , Hui Xue

We study an important task of attacking natural language processing models in a black box setting. We propose an attack strategy that crafts semantically similar adversarial examples on text classification and entailment tasks. Our proposed…

Computation and Language · Computer Science 2020-12-25 Rishabh Maheshwary , Saket Maheshwary , Vikram Pudi

We propose a generative model for adversarial attack. The model generates subtle but predictive patterns from the input. To perform an attack, it replaces the patterns of the input with those generated based on examples from some other…

Machine Learning · Computer Science 2019-12-02 Ziang Dong , Liang Mao , Shiliang Sun

Adversarial attacks pose significant challenges to deep neural networks (DNNs) such as Transformer models in natural language processing (NLP). This paper introduces a novel defense strategy, called GenFighter, which enhances adversarial…

Machine Learning · Computer Science 2024-04-18 Md Athikul Islam , Edoardo Serra , Sushil Jajodia

As powerful Large Language Models (LLMs) are now widely used for numerous practical applications, their safety is of critical importance. While alignment techniques have significantly improved overall safety, LLMs remain vulnerable to…

Machine Learning · Computer Science 2024-10-28 Samuel Jacob Chacko , Sajib Biswas , Chashi Mahiul Islam , Fatema Tabassum Liza , Xiuwen Liu

Classifiers trained using conventional empirical risk minimization or maximum likelihood methods are known to suffer dramatic performance degradations when tested over examples adversarially selected based on knowledge of the classifier's…

Machine Learning · Statistics 2018-03-01 Alireza Bagheri , Osvaldo Simeone , Bipin Rajendran

In the future, powerful AI systems may be deployed in high-stakes settings, where a single failure could be catastrophic. One technique for improving AI safety in high-stakes settings is adversarial training, which uses an adversary to…