Translate your gibberish: black-box adversarial attack on machine translation systems
Neural networks are deployed widely in natural language processing tasks on the industrial scale, and perhaps the most often they are used as compounds of automatic machine translation systems. In this work, we present a simple approach to fool state-of-the-art machine translation tools in the task of translation from Russian to English and vice versa. Using a novel black-box gradient-free tensor-based optimizer, we show that many online translation tools, such as Google, DeepL, and Yandex, may both produce wrong or offensive translations for nonsensical adversarial input queries and refuse to translate seemingly benign input phrases. This vulnerability may interfere with understanding a new language and simply worsen the user's experience while using machine translation systems, and, hence, additional improvements of these tools are required to establish better translation.
Code (1)
Tasks
Adversarial AttackMachine TranslationTranslationSimilar Papers 제목 키워드 기반
AmpleGCG-Plus: A Strong Generative Model of Adversarial Suffixes to Jailbreak LLMs with Higher Success Rates in Fewer Attempts
Although large language models (LLMs) are typically aligned, they remain vulnerable to jailbreaking through either carefully crafted prompts in natural language or, interestingly, gibberish adversarial suffixes. However,…
Erased but Exploitable: Black-box Embedding-Aware Prompting Against Unlearned Text-to-Image Diffusion Models
Machine unlearning aims to remove specific concepts from pretrained text-to-image diffusion models, yet several white- and black-box attacks have been introduced to make the model generate such unlearned concepts. These …
AutoDAN: Interpretable Gradient-Based Adversarial Attacks on Large Language Models
Safety alignment of Large Language Models (LLMs) can be compromised with manual jailbreak attacks and (automatic) adversarial attacks. Recent studies suggest that defending against these attacks is possible: adversarial …
Adversarial AttackBlockingSafety AlignmentBoosting the Transferability of Video Adversarial Examples via Temporal Translation
Although deep-learning based video recognition models have achieved remarkable success, they are vulnerable to adversarial examples that are generated by adding human-imperceptible perturbations on clean video samples. A…
Adversarial AttackTranslationVideo RecognitionAre Deep Speech Denoising Models Robust to Adversarial Noise?
Deep noise suppression (DNS) models enjoy widespread use throughout a variety of high-stakes speech applications. However, in this paper, we show that four recent DNS models can each be reduced to outputting unintelligib…
DenoisingSpeech Denoising