Related papers: Reformulation is All You Need: Addressing Maliciou…
While Deep Neural Networks (DNNs) excel in many tasks, the huge training resources they require become an obstacle for practitioners to develop their own models. It has become common to collect data from the Internet or hire a third party…
Beyond its highly publicized victories in Go, there have been numerous successful applications of deep learning in information retrieval, computer vision and speech recognition. In cybersecurity, an increasing number of companies have…
Although Deep Neural Network (DNN) has led to unprecedented progress in various natural language processing (NLP) tasks, research shows that deep models are extremely vulnerable to backdoor attacks. The existing backdoor attacks mainly…
Deep neural network (DNN) is a popular model implemented in many systems to handle complex tasks such as image classification, object recognition, natural language processing etc. Consequently DNN structural vulnerabilities become part of…
This paper provides a unified view to explain different adversarial attacks and defense methods, \emph{i.e.} the view of multi-order interactions between input variables of DNNs. Based on the multi-order interaction, we discover that…
Despite excellent performance on many tasks, NLP systems are easily fooled by small adversarial perturbations of inputs. Existing procedures to defend against such perturbations are either (i) heuristic in nature and susceptible to stronger…
Deep neural networks are vulnerable to adversarial attacks, where a small perturbation to an input alters the model prediction. In many cases, malicious inputs intentionally crafted for one model can fool another model. In this paper, we…
Large Language Models (LLMs) have transformed artificial intelligence by advancing natural language understanding and generation, enabling applications across fields beyond healthcare, software engineering, and conversational systems.…
Interpretability is crucial to understand the inner workings of deep neural networks (DNNs) and many interpretation methods generate saliency maps that highlight parts of the input image that contribute the most to the prediction made by…
Pre-trained language models (PLMs) have driven substantial progress in natural language processing but remain vulnerable to adversarial attacks, raising concerns about their robustness in real-world applications. Previous studies have…
Recurrent Neural Networks (RNNs) yield attractive properties for constructing Intrusion Detection Systems (IDSs) for network data. With the rise of ubiquitous Machine Learning (ML) systems, malicious actors have been catching up quickly to…
Recent advances in federated learning have demonstrated its promising capability to learn on decentralized datasets. However, a considerable amount of work has raised concerns due to the potential risks of adversaries participating in the…
Large Language Models (LLMs) represent a transformative leap in artificial intelligence, enabling the comprehension, generation, and nuanced interaction with human language on an unparalleled scale. However, LLMs are increasingly vulnerable…
Deep Learning is currently used to perform multiple tasks, such as object recognition, face recognition, and natural language processing. However, Deep Neural Networks (DNNs) are vulnerable to perturbations that alter the network prediction…
Deep neural networks (DNNs) are vulnerable to subtle adversarial perturbations applied to the input. These adversarial perturbations, though imperceptible, can easily mislead the DNN. In this work, we take a control theoretic approach to…
The language models, especially the basic text classification models, have been shown to be susceptible to textual adversarial attacks such as synonym substitution and word insertion attacks. To defend against such attacks, a growing body…
Despite neural networks have achieved prominent performance on many natural language processing (NLP) tasks, they are vulnerable to adversarial examples. In this paper, we propose Dirichlet Neighborhood Ensemble (DNE), a randomized…
Adversarial attacks are a major challenge faced by current machine learning research. These purposely crafted inputs fool even the most advanced models, precluding their deployment in safety-critical applications. Extensive research in…
Word-level adversarial attacks have shown success in NLP models, drastically decreasing the performance of transformer-based models in recent years. As a countermeasure, adversarial defense has been explored, but relatively few efforts have…
Adversarial attacks are a type of attack on machine learning models where an attacker deliberately modifies the inputs to cause the model to make incorrect predictions. Adversarial attacks can have serious consequences, particularly in…