English
Related papers

Related papers: Elephant in the Room: An Evaluation Framework for …

200 papers

Adversarial examples are a major problem for machine learning models, leading to a continuous search for effective defenses. One promising direction is to leverage model explanations to better understand and defend against these attacks. We…

Cryptography and Security · Computer Science 2025-03-14 Qian Ma , Ziping Ye

With rapid progress and significant successes in a wide spectrum of applications, deep learning is being applied in many safety-critical environments. However, deep neural networks have been recently found vulnerable to well-designed input…

Machine Learning · Computer Science 2018-07-10 Xiaoyong Yuan , Pan He , Qile Zhu , Xiaolin Li

As Large Language Models (LLMs) become increasingly integrated into real-world decision-making systems, understanding their behavioural vulnerabilities remains a critical challenge for AI safety and alignment. While existing evaluation…

Artificial Intelligence · Computer Science 2025-05-20 Lili Zhang , Haomiaomiao Wang , Long Cheng , Libao Deng , Tomas Ward

Neural models of code have shown impressive results when performing tasks such as predicting method names and identifying certain kinds of bugs. We show that these models are vulnerable to adversarial examples, and introduce a novel…

Machine Learning · Computer Science 2020-10-14 Noam Yefet , Uri Alon , Eran Yahav

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 neural networks (DNNs) have achieved remarkable success in various tasks (e.g., image classification, speech recognition, and natural language processing (NLP)). However, researchers have demonstrated that DNN-based models are…

Computation and Language · Computer Science 2021-04-22 Wenqi Wang , Run Wang , Lina Wang , Zhibo Wang , Aoshuang Ye

We introduce Mischief, a simple and lightweight method to produce a class of human-readable, realistic adversarial examples for language models. We perform exhaustive experimentations of our algorithm on four transformer-based…

Computation and Language · Computer Science 2020-10-19 Adrian de Wynter

In predictive process monitoring, predictive models are vulnerable to adversarial attacks, where input perturbations can lead to incorrect predictions. Unlike in computer vision, where these perturbations are designed to be imperceptible to…

Machine Learning · Computer Science 2024-11-22 Alexander Stevens , Jari Peeperkorn , Johannes De Smedt , Jochen De Weerdt

Recently, advanced NLP models have seen a surge in the usage of various applications. This raises the security threats of the released models. In addition to the clean models' unintentional weaknesses, {\em i.e.,} adversarial attacks, the…

Computation and Language · Computer Science 2021-01-18 Lichao Sun

Adversarial examples are input examples that are specifically crafted to deceive machine learning classifiers. State-of-the-art adversarial example detection methods characterize an input example as adversarial either by quantifying the…

Computer Vision and Pattern Recognition · Computer Science 2021-01-01 Yuhang Wu , Sunpreet S. Arora , Yanhong Wu , Hao Yang

Over the last few years, convolutional neural networks (CNNs) have proved to reach super-human performance in visual recognition tasks. However, CNNs can easily be fooled by adversarial examples, i.e., maliciously-crafted images that force…

Computer Vision and Pattern Recognition · Computer Science 2021-08-17 Federico Nesti , Alessandro Biondi , Giorgio Buttazzo

It has been demonstrated that deep neural networks are prone to noisy examples particular adversarial samples during inference process. The gap between robust deep learning systems in real world applications and vulnerable neural networks…

Machine Learning · Computer Science 2018-07-03 Xinhan Di , Pengqian Yu , Meng Tian

Language Models today provide a high accuracy across a large number of downstream tasks. However, they remain susceptible to adversarial attacks, particularly against those where the adversarial examples maintain considerable similarity to…

Computation and Language · Computer Science 2023-07-25 Neel Bhandari , Pin-Yu Chen

Adversarial examples are inputs intentionally perturbed with the aim of forcing a machine learning model to produce a wrong prediction, while the changes are not easily detectable by a human. Although this topic has been intensively studied…

Machine Learning · Computer Science 2021-02-16 Jon Vadillo , Roberto Santana

Today text classification models have been widely used. However, these classifiers are found to be easily fooled by adversarial examples. Fortunately, standard attacking methods generate adversarial texts in a pair-wise way, that is, an…

Computation and Language · Computer Science 2020-03-24 Yankun Ren , Jianbin Lin , Siliang Tang , Jun Zhou , Shuang Yang , Yuan Qi , Xiang Ren

Real-world natural language processing systems need to be robust to human adversaries. Collecting examples of human adversaries for training is an effective but expensive solution. On the other hand, training on synthetic attacks with small…

Machine Learning · Computer Science 2024-02-16 Aradhana Sinha , Ananth Balashankar , Ahmad Beirami , Thi Avrahami , Jilin Chen , Alex Beutel

Adversarial machine learning, i.e., increasing the robustness of machine learning algorithms against so-called adversarial examples, is now an established field. Yet, newly proposed methods are evaluated and compared under unrealistic…

Machine Learning · Computer Science 2021-09-28 Maximilian Samsinger , Florian Merkle , Pascal Schöttle , Tomas Pevny

Language models are vulnerable to short adversarial suffixes that can reliably alter predictions. Previous works usually find such suffixes with gradient search or rule-based methods, but these are brittle and often tied to a single task or…

Computation and Language · Computer Science 2025-12-10 Sampriti Soor , Suklav Ghosh , Arijit Sur

Adversarial attacks are widely used to identify model vulnerabilities; however, their validity as proxies for robustness to random perturbations remains debated. We ask whether an adversarial example provides a representative estimate of…

Machine Learning · Computer Science 2026-01-27 Giulio Rossolini

Adversarial examples pose a significant challenge to deep neural networks (DNNs) across both image and text domains, with the intent to degrade model performance through meticulously altered inputs. Adversarial texts, however, are distinct…

Machine Learning · Computer Science 2025-01-24 Shakila Mahjabin Tonni , Pedro Faustini , Mark Dras