Semantics Preserving Adversarial Attacks
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.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Preserving Semantics in Textual Adversarial Attacks
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-EmbeddingModel Robustness with Text Classification: Semantic-preserving adversarial attacks
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+1Semantics Preserving Adversarial Learning
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 ClassificationContrasting Human- and Machine-Generated Word-Level Adversarial Examples for Text Classification
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+1On Meaning-Preserving Adversarial Perturbations for Sequence-to-Sequence Models
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