Related papers: Adversarial Examples for Evaluating Math Word Prob…
Deep neural network image classifiers are reported to be susceptible to adversarial evasion attacks, which use carefully crafted images created to mislead a classifier. Recently, various kinds of adversarial attack methods have been…
Adversarial examples are maliciously modified inputs created to fool deep neural networks (DNN). The discovery of such inputs presents a major issue to the expansion of DNN-based solutions. Many researchers have already contributed to the…
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…
Neural Machine Translation (NMT) models have been shown to be vulnerable to adversarial attacks, wherein carefully crafted perturbations of the input can mislead the target model. In this paper, we introduce ACT, a novel adversarial attack…
Deep neural networks have been successfully applied in various machine learning tasks. However, studies show that neural networks are susceptible to adversarial attacks. This exposes a potential threat to neural network-based intelligent…
This work studies the threats of adversarial attack on multivariate probabilistic forecasting models and viable defense mechanisms. Our studies discover a new attack pattern that negatively impact the forecasting of a target time series via…
We study the performance of a commercially available large language model (LLM) known as ChatGPT on math word problems (MWPs) from the dataset DRAW-1K. To our knowledge, this is the first independent evaluation of ChatGPT. We found that…
Large language models are now tuned to align with the goals of their creators, namely to be "helpful and harmless." These models should respond helpfully to user questions, but refuse to answer requests that could cause harm. However,…
We study an important and challenging task of attacking natural language processing models in a hard label black box setting. We propose a decision-based attack strategy that crafts high quality adversarial examples on text classification…
Adversarial Training (AT) effectively improves the robustness of Deep Neural Networks (DNNs) to adversarial attacks. Generally, AT involves training DNN models with adversarial examples obtained within a pre-defined, fixed perturbation…
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…
Currently, natural language processing (NLP) models are wildly used in various scenarios. However, NLP models, like all deep models, are vulnerable to adversarially generated text. Numerous works have been working on mitigating the…
Insensitivity to semantically-preserving variations of prompts (paraphrases) is crucial for reliable behavior and real-world deployment of large language models. However, language models exhibit significant performance degradation when…
In recent years, large pre-trained language models (PLMs) have achieved remarkable performance on many natural language processing benchmarks. Despite their success, prior studies have shown that PLMs are vulnerable to attacks from…
Recent work has demonstrated the vulnerability of modern text classifiers to universal adversarial attacks, which are input-agnostic sequences of words added to text processed by classifiers. Despite being successful, the word sequences…
Revealing the robustness issues of natural language processing models and improving their robustness is important to their performance under difficult situations. In this paper, we study the robustness of paraphrase identification models…
Deep neural networks are vulnerable to so-called adversarial examples: inputs which are intentionally constructed to cause the model to make incorrect predictions or classifications. Adversarial examples are often visually indistinguishable…
Attacking Neural Machine Translation models is an inherently combinatorial task on discrete sequences, solved with approximate heuristics. Most methods use the gradient to attack the model on each sample independently. Instead of…
Neural Machine Translation (NMT) models are known to suffer from noisy inputs. To make models robust, we generate adversarial augmentation samples that attack the model and preserve the source-side semantic meaning at the same time. To…
Semantic parsing maps natural language (NL) utterances into logical forms (LFs), which underpins many advanced NLP problems. Semantic parsers gain performance boosts with deep neural networks, but inherit vulnerabilities against adversarial…