paper-with-me

Papers

Semantics Preserving Adversarial Attacks

2019-09-25 · Ousmane Amadou Dia, Elnaz Barshan, Reza Babanezhad

While progress has been made in crafting visually imperceptible adversarial examples, constructing semantically meaningful ones remains a challenge. In this paper, we propose a framework to generate semantics preserving adversarial examples. First, we present a manifold learning method to capture the semantics of the inputs. The motivating principle is to learn the low-dimensional geometric summaries of the inputs via statistical inference. Then, we perturb the elements of the learned manifold using the Gram-Schmidt process to induce the perturbed elements to remain in the manifold. To produce adversarial examples, we propose an efficient algorithm whereby we leverage the semantics of the inputs as a source of knowledge upon which we impose adversarial constraints. We apply our approach on toy data, images and text, and show its effectiveness in producing semantics preserving adversarial examples which evade existing defenses against adversarial attacks.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Preserving Semantics in Textual Adversarial Attacks

2022-11-08 · David Herel, Hugo Cisneros, Tomas Mikolov

The growth of hateful online content, or hate speech, has been associated with a global increase in violent crimes against minorities [23]. Harmful online content can be produced easily, automatically and anonymously. Ev…

Adversarial AttackSentenceSentence EmbeddingSentence-Embedding

Model Robustness with Text Classification: Semantic-preserving adversarial attacks

2020-08-12 · Rahul Singh, Tarun Joshi, Vijayan N. Nair, Agus Sudjianto

We propose algorithms to create adversarial attacks to assess model robustness in text classification problems. They can be used to create white box attacks and black box attacks while at the same time preserving the sem…

Adversarial AttackClassificationGeneral Classificationtext-classification+1

Semantics Preserving Adversarial Learning

2019-03-10 · Ousmane Amadou Dia, Elnaz Barshan, Reza Babanezhad

While progress has been made in crafting visually imperceptible adversarial examples, constructing semantically meaningful ones remains a challenge. In this paper, we propose a framework to generate semantics preserving …

Text Classification

Contrasting Human- and Machine-Generated Word-Level Adversarial Examples for Text Classification

2021-09-09 · EMNLP 2021 11 · Maximilian Mozes, Max Bartolo, Pontus Stenetorp, Bennett Kleinberg 외

Research shows that natural language processing models are generally considered to be vulnerable to adversarial attacks; but recent work has drawn attention to the issue of validating these adversarial inputs against cer…

Sentiment AnalysisSentiment Classificationtext-classificationText Classification+1

On Meaning-Preserving Adversarial Perturbations for Sequence-to-Sequence Models

2019-05-01 · ICLR 2019 5 · Paul Michel, Graham Neubig, Xi-An Li, Juan Miguel Pino

Adversarial examples have been shown to be an effective way of assessing the robustness of neural sequence-to-sequence (seq2seq) models, by applying perturbations to the input of a model leading to large degradation in p…

Adversarial RobustnessMachine TranslationTranslation