Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userCertified Robustness to Word Substitution Attack with Differential Privacy
معتمدة متانة لهجوم استبدال الكلمات مع الخصوصية التفاضلية
416
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
تعد نماذج معالجة وأمن معالجة اللغة الطبيعية (NLP) مهمة بشكل ملحوظ في تطبيقات العالم الحقيقي. في سياق مهام تصنيف النص، يمكن تصميم أمثلة الخصومة من خلال استبدال الكلمات مع المرادفات تحت بعض القيود الدلالية والمنظمات الأساسية، بحيث يكون نموذج مدرب جيدا سيعطي تنبؤا خاطئا. لذلك، من الأهمية بمكان تطوير تقنيات لتوفير ضمان قوي وقضايا ضد هذه الهجمات. في هذه الورقة، نقترح WordDP لتحقيق متانة مصدقة ضد استبدال الكلمات في تصنيف النص عن طريق الخصوصية التفاضلية (DP). نحدد العلاقة بين موانئ دبي والمودة القومية لأول مرة في المجال النصي واقتراح خوارزمية قائمة على الآلية المفاهيمية التي تعتمد على الآلية لتحقيق القابة رسميا. ونحن نقدم كذلك آلية أسيانية محاكاة عملية لها استنتاج فعال مع متانة معتمدة. نحن لا نقدم فقط اشتقاق تحليلي صارم للحالة المعتمدة ولكن أيضا مقارنة فائدة WordDP أيضا بشكل تجريبي مع خوارزميات الدفاع الحالية. تظهر النتائج أن WordDP تحقق دقة أعلى وأكثر من 30x تحسن كفاءة على آلية متانة حديثة معتمدة في مهام تصنيف النص النموذجي.
The robustness and security of natural language processing (NLP) models are significantly important in real-world applications. In the context of text classification tasks, adversarial examples can be designed by substituting words with synonyms under certain semantic and syntactic constraints, such that a well-trained model will give a wrong prediction. Therefore, it is crucial to develop techniques to provide a rigorous and provable robustness guarantee against such attacks. In this paper, we propose WordDP to achieve certified robustness against word substitution at- tacks in text classification via differential privacy (DP). We establish the connection between DP and adversarial robustness for the first time in the text domain and propose a conceptual exponential mechanism-based algorithm to formally achieve the robustness. We further present a practical simulated exponential mechanism that has efficient inference with certified robustness. We not only provide a rigorous analytic derivation of the certified condition but also experimentally compare the utility of WordDP with existing defense algorithms. The results show that WordDP achieves higher accuracy and more than 30X efficiency improvement over the state-of-the-art certified robustness mechanism in typical text classification tasks.
References used
https://aclanthology.org/
rate research
Read More
Deep neural networks for natural language processing are fragile in the face of adversarial examples---small input perturbations, like synonym substitution or word duplication, which cause a neural network to change its prediction. We present an appr
oach to certifying the robustness of LSTMs (and extensions of LSTMs) and training models that can be efficiently certified. Our approach can certify robustness to intractably large perturbation spaces defined programmatically in a language of string transformations. Our evaluation shows that (1) our approach can train models that are more robust to combinations of string transformations than those produced using existing techniques; (2) our approach can show high certification accuracy of the resulting models.
Seq2seq models have demonstrated their incredible effectiveness in a large variety of applications. However, recent research has shown that inappropriate language in training samples and well-designed testing cases can induce seq2seq models to output
profanity. These outputs may potentially hurt the usability of seq2seq models and make the end-users feel offended. To address this problem, we propose a training framework with certified robustness to eliminate the causes that trigger the generation of profanity. The proposed training framework leverages merely a short list of profanity examples to prevent seq2seq models from generating a broader spectrum of profanity. The framework is composed of a pattern-eliminating training component to suppress the impact of language patterns with profanity in the training set, and a trigger-resisting training component to provide certified robustness for seq2seq models against intentionally injected profanity-triggering expressions in test samples. In the experiments, we consider two representative NLP tasks that seq2seq can be applied to, i.e., style transfer and dialogue generation. Extensive experimental results show that the proposed training framework can successfully prevent the NLP models from generating profanity.
NLP models are vulnerable to data poisoning attacks. One type of attack can plant a backdoor in a model by injecting poisoned examples in training, causing the victim model to misclassify test instances which include a specific pattern. Although defe
nces exist to counter these attacks, they are specific to an attack type or pattern. In this paper, we propose a generic defence mechanism by making the training process robust to poisoning attacks through gradient shaping methods, based on differentially private training. We show that our method is highly effective in mitigating, or even eliminating, poisoning attacks on text classification, with only a small cost in predictive accuracy.
Latent Dirichlet allocation (LDA), a widely used topic model, is often employed as a fundamental tool for text analysis in various applications. However, the training process of the LDA model typically requires massive text corpus data. On one hand,
such massive data may expose private information in the training data, thereby incurring significant privacy concerns. On the other hand, the efficiency of the LDA model training may be impacted, since LDA training often needs to handle these massive text corpus data. To address the privacy issues in LDA model training, some recent works have combined LDA training algorithms that are based on collapsed Gibbs sampling (CGS) with differential privacy. Nevertheless, these works usually have a high accumulative privacy budget due to vast iterations in CGS. Moreover, these works always have low efficiency due to handling massive text corpus data. To improve the privacy guarantee and efficiency, we combine a subsampling method with CGS and propose a novel LDA training algorithm with differential privacy, SUB-LDA. We find that subsampling in CGS naturally improves efficiency while amplifying privacy. We propose a novel metric, the efficiency--privacy function, to evaluate improvements of the privacy guarantee and efficiency. Based on a conventional subsampling method, we propose an adaptive subsampling method to improve the model's utility produced by SUB-LDA when the subsampling ratio is small. We provide a comprehensive analysis of SUB-LDA, and the experiment results validate its efficiency and privacy guarantee improvements.
Neural language models are known to have a high capacity for memorization of training samples. This may have serious privacy im- plications when training models on user content such as email correspondence. Differential privacy (DP), a popular choice
to train models with privacy guarantees, comes with significant costs in terms of utility degradation and disparate impact on subgroups of users. In this work, we introduce two privacy-preserving regularization methods for training language models that enable joint optimization of utility and privacy through (1) the use of a discriminator and (2) the inclusion of a novel triplet-loss term. We compare our methods with DP through extensive evaluation. We show the advantages of our regularizers with favorable utility-privacy trade-off, faster training with the ability to tap into existing optimization approaches, and ensuring uniform treatment of under-represented subgroups.
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
