Related papers: ReinforceBug: A Framework to Generate Adversarial …
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…
Black box attacks, where adversaries have limited knowledge of the target model, pose a significant threat to machine learning systems. Adversarial examples generated with a substitute model often suffer from limited transferability to the…
Adversarial attacks have verified the existence of the vulnerability of neural networks. By adding small perturbations to a benign example, adversarial attacks successfully generate adversarial examples that lead misclassification of deep…
Machine learning models are vulnerable to adversarial examples formed by applying small carefully chosen perturbations to inputs that cause unexpected classification errors. In this paper, we perform experiments on various adversarial…
Reliable deployment of machine learning models such as neural networks continues to be challenging due to several limitations. Some of the main shortcomings are the lack of interpretability and the lack of robustness against adversarial…
We present a novel framework for augmenting data sets for machine learning based on counterexamples. Counterexamples are misclassified examples that have important properties for retraining and improving the model. Key components of our…
Adversarial attacks expose vulnerabilities of deep learning models by introducing minor perturbations to the input, which lead to substantial alterations in the output. Our research focuses on the impact of such adversarial attacks on…
Adversarial examples expose the vulnerabilities of natural language processing (NLP) models, and can be used to evaluate and improve their robustness. Existing techniques of generating such examples are typically driven by local heuristic…
Adversarial examples reveal the blind spots of deep neural networks (DNNs) and represent a major concern for security-critical applications. The transferability of adversarial examples makes real-world attacks possible in black-box…
Tree ensembles are powerful models that are widely used. However, they are susceptible to adversarial examples, which are examples that purposely constructed to elicit a misprediction from the model. This can degrade performance and erode a…
Adversarial attacks have proven effective in deceiving machine learning models by subtly altering input images, motivating extensive research in recent years. Traditional methods constrain perturbations within $l_p$-norm bounds, but…
Despite the remarkable performance and generalization levels of deep learning models in a wide range of artificial intelligence tasks, it has been demonstrated that these models can be easily fooled by the addition of imperceptible yet…
The vulnerability of deep neural networks (DNNs) to black-box adversarial attacks is one of the most heated topics in trustworthy AI. In such attacks, the attackers operate without any insider knowledge of the model, making the cross-model…
Deep neural networks (DNNs) are vulnerable to adversarial examples (AEs) that mislead the model while appearing benign to human observers. A critical concern is the transferability of AEs, which enables black-box attacks without direct…
Deep learning-based natural language processing (NLP) models, particularly pre-trained language models (PLMs), have been revealed to be vulnerable to adversarial attacks. However, the adversarial examples generated by many mainstream…
Adversarial examples are vital to expose the vulnerability of machine learning models. Despite the success of the most popular substitution-based methods which substitutes some characters or words in the original examples, only substitution…
We propose a new method for event extraction (EE) task based on an imitation learning framework, specifically, inverse reinforcement learning (IRL) via generative adversarial network (GAN). The GAN estimates proper rewards according to the…
Adversarial examples --- perturbations to the input of a model that elicit large changes in the output --- have been shown to be an effective way of assessing the robustness of sequence-to-sequence (seq2seq) models. However, these…
We introduce the concept of deceptive diffusion -- training a generative AI model to produce adversarial images. Whereas a traditional adversarial attack algorithm aims to perturb an existing image to induce a misclassificaton, the…
When the world changes, so does the text that humans write about it. How do we build language models that can be easily updated to reflect these changes? One popular approach is retrieval-augmented generation, in which new documents are…