Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userUniversal Adversarial Attacks with Natural Triggers for Text Classification
الهجمات الخصومة العالمية مع المشغلات الطبيعية لتصنيف النص
399
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
أظهر العمل الحديث مدى ضعف مصنف النصوص الحديثة للهجمات الخصومة العالمية، والتي هي تسلسل مدخلات غير مرغقة من الكلمات المضافة إلى النص المصنوع من قبل المصنفين. على الرغم من أن تكون ناجحة، فإن تسلسل الكلمات المنتجة في هذه الهجمات غالبا ما تكون غير رسمية ويمكن تمييزها بسهولة عن النص الطبيعي. نقوم بتطوير هجمات عدائية تظهر أقرب إلى عبارات اللغة الإنجليزية الطبيعية وحتى الآن أنظمة التصنيف عند إضافتها إلى المدخلات الحميدة. نحن نستفيد من AutoNCoder المنعصنة (ARAE) لتوليد المشغلات واقتراح بحث يستند إلى التدرج يهدف إلى زيادة فقدان تنبؤ التنبؤ بالتنبؤ في المصب. تقلل هجماتنا بشكل فعال دقة النموذج على مهام التصنيف مع كونها أقل تحديدا من النماذج السابقة وفقا لمقاييس الكشف التلقائي والدراسات البشرية. هدفنا هو إثبات أن الهجمات المشنة يمكن أن تكتشف أكثر صعوبة مما كان يعتقد سابقا وتمكين تطوير الدفاعات المناسبة.
Recent work has demonstrated the vulnerability of modern text classifiers to universal adversarial attacks, which are input-agnostic sequences of words added to text processed by classifiers. Despite being successful, the word sequences produced in such attacks are often ungrammatical and can be easily distinguished from natural text. We develop adversarial attacks that appear closer to natural English phrases and yet confuse classification systems when added to benign inputs. We leverage an adversarially regularized autoencoder (ARAE) to generate triggers and propose a gradient-based search that aims to maximize the downstream classifier's prediction loss. Our attacks effectively reduce model accuracy on classification tasks while being less identifiable than prior models as per automatic detection metrics and human-subject studies. Our aim is to demonstrate that adversarial attacks can be made harder to detect than previously thought and to enable the development of appropriate defenses.
References used
https://aclanthology.org/
rate research
Read More
Deep neural networks are vulnerable to adversarial attacks, where a small perturbation to an input alters the model prediction. In many cases, malicious inputs intentionally crafted for one model can fool another model. In this paper, we present the
first study to systematically investigate the transferability of adversarial examples for text classification models and explore how various factors, including network architecture, tokenization scheme, word embedding, and model capacity, affect the transferability of adversarial examples. Based on these studies, we propose a genetic algorithm to find an ensemble of models that can be used to induce adversarial examples to fool almost all existing models. Such adversarial examples reflect the defects of the learning process and the data bias in the training set. Finally, we derive word replacement rules that can be used for model diagnostics from these adversarial examples.
Contextual representations learned by language models can often encode undesirable attributes, like demographic associations of the users, while being trained for an unrelated target task. We aim to scrub such undesirable attributes and learn fair re
presentations while maintaining performance on the target task. In this paper, we present an adversarial learning framework Adversarial Scrubber'' (AdS), to debias contextual representations. We perform theoretical analysis to show that our framework converges without leaking demographic information under certain conditions. We extend previous evaluation techniques by evaluating debiasing performance using Minimum Description Length (MDL) probing. Experimental evaluations on 8 datasets show that AdS generates representations with minimal information about demographic attributes while being maximally informative about the target task.
Continual learning has become increasingly important as it enables NLP models to constantly learn and gain knowledge over time. Previous continual learning methods are mainly designed to preserve knowledge from previous tasks, without much emphasis o
n how to well generalize models to new tasks. In this work, we propose an information disentanglement based regularization method for continual learning on text classification. Our proposed method first disentangles text hidden spaces into representations that are generic to all tasks and representations specific to each individual task, and further regularizes these representations differently to better constrain the knowledge required to generalize. We also introduce two simple auxiliary tasks: next sentence prediction and task-id prediction, for learning better generic and specific representation spaces. Experiments conducted on large-scale benchmarks demonstrate the effectiveness of our method in continual text classification tasks with various sequences and lengths over state-of-the-art baselines. We have publicly released our code at https://github.com/GT-SALT/IDBR.
Deep learning is at the heart of the current rise of artificial intelligence. In the field of Computer Vision, it has become the workhorse for applications ranging from self-driving cars to surveillance and security. Whereas deep neural networks have
demonstrated phenomenal success (often beyond human capabilities) in solving complex problems, recent studies show that they are vulnerable to adversarial attacks in the form of subtle perturbations to inputs that lead a model to predict incorrect outputs. For images, such perturbations are often too small to be perceptible, yet they completely fool the deep learning models. Adversarial attacks pose a serious threat to the success of deep learning in practice. This fact has recently lead to a large influx of contributions in this direction. This article presents a survey on adversarial attacks on deep learning in Computer Vision. We review the works that design adversarial attacks, analyze the existence of such attacks and propose defenses against them
Providing pretrained language models with simple task descriptions in natural language enables them to solve some tasks in a fully unsupervised fashion. Moreover, when combined with regular learning from examples, this idea yields impressive few-shot
results for a wide range of text classification tasks. It is also a promising direction to improve data efficiency in generative settings, but there are several challenges to using a combination of task descriptions and example-based learning for text generation. In particular, it is crucial to find task descriptions that are easy to understand for the pretrained model and to ensure that it actually makes good use of them; furthermore, effective measures against overfitting have to be implemented. In this paper, we show how these challenges can be tackled: We introduce GenPET, a method for text generation that is based on pattern-exploiting training, a recent approach for combining textual instructions with supervised learning that only works for classification tasks. On several summarization and headline generation datasets, GenPET gives consistent improvements over strong baselines in few-shot settings.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
