相关论文: HotFlip: White-Box Adversarial Examples for Text C…

Adversarial examples can be useful for identifying vulnerabilities in AI systems before they are deployed. In reinforcement learning (RL), adversarial policies can be developed by training an adversarial agent to minimize a target agent's…

Recent NLP literature pays little attention to the robustness of toxicity language predictors, while these systems are most likely to be used in adversarial contexts. This paper presents a novel adversarial attack, \texttt{ToxicTrap},…

The capabilities of large language models (LLMs) have been successfully applied in the context of table representation learning. The recently proposed tabular language models have reported state-of-the-art results across various tasks for…

Vision-language pre-training models (VLPs) have exhibited revolutionary improvements in various vision-language tasks. In VLP, some adversarial attacks fool a model into false or absurd classifications. Previous studies addressed these…

Machine learning models are powerful but fallible. Generating adversarial examples - inputs deliberately crafted to cause model misclassification or other errors - can yield important insight into model assumptions and vulnerabilities.…

Contrastive Language-Image Pre-training (CLIP) has demonstrated impressive capabilities in open-vocabulary classification. The class token in the image encoder is trained to capture the global features to distinguish different text…

Recent advances in mechanistic interpretability suggest that intermediate attention layers encode token-level hypotheses that are iteratively refined toward the final output. In this work, we exploit this property to generate adversarial…

Adversarial examples in NLP are receiving increasing research attention. One line of investigation is the generation of word-level adversarial examples against fine-tuned Transformer models that preserve naturalness and grammaticality.…

The vulnerability of deep neural networks to adversarial attacks has been widely demonstrated (e.g., adversarial example attacks). Traditional attacks perform unstructured pixel-wise perturbation to fool the classifier. An alternative…

Adversarial examples have proven to threaten speaker identification systems, and several countermeasures against them have been proposed. In this paper, we propose a method to detect the presence of adversarial examples, i.e., a binary…

Deep neural network (DNN) as a popular machine learning model is found to be vulnerable to adversarial attack. This attack constructs adversarial examples by adding small perturbations to the raw input, while appearing unmodified to human…

Multi-class text classification is one of the key problems in machine learning and natural language processing. Emerging neural networks deal with the problem using a multi-output softmax layer and achieve substantial progress, but they do…

In cross-lingual text classification, one seeks to exploit labeled data from one language to train a text classification model that can then be applied to a completely different language. Recent multilingual representation models have made…

Deep neural networks are vulnerable to adversarial attacks, which can fool them by adding minuscule perturbations to the input images. The robustness of existing defenses suffers greatly under white-box attack settings, where an adversary…

Recent work in black-box adversarial attacks for NLP systems has attracted much attention. Prior black-box attacks assume that attackers can observe output labels from target models based on selected inputs. In this work, inspired by…

The growing interest for adversarial examples, i.e. maliciously modified examples which fool a classifier, has resulted in many defenses intended to detect them, render them inoffensive or make the model more robust against them. In this…

The transferability of adversarial examples across deep neural network (DNN) models is the crux of a spectrum of black-box attacks. In this paper, we propose a novel method to enhance the black-box transferability of baseline adversarial…

Machine learning (ML) classifiers are vulnerable to adversarial examples. An adversarial example is an input sample which is slightly modified to induce misclassification in an ML classifier. In this work, we investigate white-box and…

Neural network based classifiers are still prone to manipulation through adversarial perturbations. State of the art attacks can overcome most of the defense or detection mechanisms suggested so far, and adversaries have the upper hand in…

Deep convolutional neural networks can be highly vulnerable to small perturbations of their inputs, potentially a major issue or limitation on system robustness when using deep networks as classifiers. In this paper we propose a low-cost…