A Relaxed Optimization Approach for Adversarial Attacks against Neural Machine Translation Models
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Adversarial AttackMachine TranslationNMTSemantic SimilaritySemantic Textual SimilarityTranslationSimilar Papers 제목 키워드 기반
Risk Analysis and Design Against Adversarial Actions
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
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…
DenoisingResilient and constrained consensus against adversarial attacks: A distributed MPC framework
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 ControlAttacking Large Language Models with Projected Gradient Descent
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
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