Related papers: BBAEG: Towards BERT-based Biomedical Adversarial E…

The research of adversarial attacks in the text domain attracts many interests in the last few years, and many methods with a high attack success rate have been proposed. However, these attack methods are inefficient as they require lots of…

Adversarial attacks are carried out to reveal the vulnerability of deep neural networks. Textual adversarial attacking is challenging because text is discrete and a small perturbation can bring significant change to the original input.…

Recent advances in natural language processing (NLP) have been driven bypretrained language models like BERT, RoBERTa, T5, and GPT. Thesemodels excel at understanding complex texts, but biomedical literature, withits domain-specific…

Recently, generating adversarial examples has become an important means of measuring robustness of a deep learning model. Adversarial examples help us identify the susceptibilities of the model and further counter those vulnerabilities by…

Explainable AI is a strong strategy implemented to understand complex black-box model predictions in a human interpretable language. It provides the evidence required to execute the use of trustworthy and reliable AI systems. On the other…

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…

This study evaluated the effect of BioBERT in medical text processing for the task of medical named entity recognition. Through comparative experiments with models such as BERT, ClinicalBERT, SciBERT, and BlueBERT, the results showed that…

Machine Learning systems are vulnerable to adversarial attacks and will highly likely produce incorrect outputs under these attacks. There are white-box and black-box attacks regarding to adversary's access level to the victim learning…

Retrieval-Augmented Generation (RAG) enhances large language models (LLMs) by incorporating external knowledge, but its openness introduces vulnerabilities that can be exploited by poisoning attacks. Existing poisoning methods for RAG…

Natural language processing models are vulnerable to adversarial examples. Previous textual adversarial attacks adopt gradients or confidence scores to calculate word importance ranking and generate adversarial examples. However, this…

We extend BeamAttack, an adversarial attack algorithm designed to evaluate the robustness of text classification systems through word-level modifications guided by beam search. Our extensions include support for word deletions and the…

Both model developers and policymakers seek to quantify and mitigate the risk of rapidly-evolving frontier artificial intelligence (AI) models, especially large language models (LLMs), to facilitate bioterrorism or access to biological…

Adversarial attacks against deep learning models represent a major threat to the security and reliability of natural language processing (NLP) systems. In this paper, we propose a modification to the BERT-Attack framework, integrating…

The increasing depth of parametric domain knowledge in large language models (LLMs) is fueling their rapid deployment in real-world applications. Understanding model vulnerabilities in high-stakes and knowledge-intensive tasks is essential…

This paper proposes a black-box adversarial attack method to automatic speech recognition systems. Some studies have attempted to attack neural networks for speech recognition; however, these methods did not consider the robustness of…

Hypothesis generation in biomedical research has traditionally centered on uncovering hidden relationships within vast scientific literature, often using methods like Literature-Based Discovery (LBD). Despite progress, current approaches…

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…

In this work, we examine the extent to which embeddings may encode marginalized populations differently, and how this may lead to a perpetuation of biases and worsened performance on clinical tasks. We pretrain deep embedding models (BERT)…

Biomedical entity linking aims to map biomedical mentions, such as diseases and drugs, to standard entities in a given knowledge base. The specific challenge in this context is that the same biomedical entity can have a wide range of names,…

Adversarial example detection plays a vital role in adaptive cyber defense, especially in the face of rapidly evolving attacks. In adaptive cyber defense, the nature and characteristics of attacks continuously change, making it crucial to…