paper-with-me

홈 › Papers

A Relaxed Optimization Approach for Adversarial Attacks against Neural Machine Translation Models

2023-06-14 · Sahar Sadrizadeh, Clément Barbier, Ljiljana Dolamic, Pascal Frossard

In this paper, we propose an optimization-based adversarial attack against Neural Machine Translation (NMT) models. First, we propose an optimization problem to generate adversarial examples that are semantically similar to the original sentences but destroy the translation generated by the target NMT model. This optimization problem is discrete, and we propose a continuous relaxation to solve it. With this relaxation, we find a probability distribution for each token in the adversarial example, and then we can generate multiple adversarial examples by sampling from these distributions. Experimental results show that our attack significantly degrades the translation quality of multiple NMT models while maintaining the semantic similarity between the original and adversarial sentences. Furthermore, our attack outperforms the baselines in terms of success rate, similarity preservation, effect on translation quality, and token error rate. Finally, we propose a black-box extension of our attack by sampling from an optimized probability distribution for a reference model whose gradients are accessible.

📄 PDF Abstract BibTeX arXiv:2306.08492

Code (0)

등록된 구현이 없습니다.

Tasks

Adversarial AttackMachine TranslationNMTSemantic SimilaritySemantic Textual SimilarityTranslation

Similar Papers 제목 키워드 기반

Risk Analysis and Design Against Adversarial Actions

2025-05-02 · Marco C. Campi, Algo Carè, Luis G. Crespo, Simone Garatti 외

Learning models capable of providing reliable predictions in the face of adversarial actions has become a central focus of the machine learning community in recent years. This challenge arises from observing that data en…

Robustifying Models Against Adversarial Attacks by Langevin Dynamics

2018-05-30 · Vignesh Srinivasan, Arturo Marban, Klaus-Robert Müller, Wojciech Samek 외

Adversarial attacks on deep learning models have compromised their performance considerably. As remedies, a lot of defense methods were proposed, which however, have been circumvented by newer attacking strategies. In th…

Denoising

Resilient and constrained consensus against adversarial attacks: A distributed MPC framework

2023-11-10 · Henglai Wei, Kunwu Zhang, HUI ZHANG, Yang Shi

There has been a growing interest in realizing the resilient consensus of the multi-agent system (MAS) under cyber-attacks, which aims to achieve the consensus of normal agents (i.e., agents without attacks) in a network…

Adversarial AttackAdversarial Attack DetectionModel Predictive Control

Attacking Large Language Models with Projected Gradient Descent

2024-02-14 · Simon Geisler, Tom Wollschläger, M. H. I. Abdalla, Johannes Gasteiger 외

Current LLM alignment methods are readily broken through specifically crafted adversarial prompts. While crafting adversarial prompts using discrete optimization is highly effective, such attacks typically use more than …

Defending Against Adversarial Machine Learning

2019-11-26 · Alison Jenkins

An Adversarial System to attack and an Authorship Attribution System (AAS) to defend itself against the attacks are analyzed. Defending a system against attacks from an adversarial machine learner can be done by randomly…

Authorship AttributionBIG-bench Machine Learning