Semantics 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 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.
Tasks
Text ClassificationSimilar Papers 제목 키워드 기반
Semantics-Preserving Adversarial Training
Adversarial training is a defense technique that improves adversarial robustness of a deep neural network (DNN) by including adversarial examples in the training data. In this paper, we identify an overlooked problem of …
Adversarial RobustnessSemantics 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 …
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-EmbeddingSemantic-preserving Reinforcement Learning Attack Against Graph Neural Networks for Malware Detection
As an increasing number of deep-learning-based malware scanners have been proposed, the existing evasion techniques, including code obfuscation and polymorphic malware, are found to be less effective. In this work, we pr…
Malware Detectionreinforcement-learningReinforcement LearningReinforcement Learning (RL)Zero-Shot Visual Recognition using Semantics-Preserving Adversarial Embedding Networks
We propose a novel framework called Semantics-Preserving Adversarial Embedding Network (SP-AEN) for zero-shot visual recognition (ZSL), where test images and their classes are both unseen during training. SP-AEN aims to …
General ClassificationZero-Shot Learning