Proceedings of the 13th ACM Workshop on Artificial Intelligence and Security最新文献

Session details: Session 3: Machine Learning for Security and Privacy 会议详情:会议3:机器学习的安全和隐私

Proceedings of the 13th ACM Workshop on Artificial Intelligence and Security Pub Date : 2020-11-13 DOI: 10.1145/3433220

Sadia Afroz

引用次数: 0

Session details: Session 2: Malware Detection 会话详细信息:会话2:恶意软件检测

Proceedings of the 13th ACM Workshop on Artificial Intelligence and Security Pub Date : 2020-11-13 DOI: 10.1145/3433219

Ambra Demontis

引用次数: 0

Disabling Backdoor and Identifying Poison Data by using Knowledge Distillation in Backdoor Attacks on Deep Neural Networks 基于知识蒸馏的深度神经网络后门攻击去后门与有毒数据识别

Proceedings of the 13th ACM Workshop on Artificial Intelligence and Security Pub Date : 2020-11-09 DOI: 10.1145/3411508.3421375

Kota Yoshida, T. Fujino

{"title":"Disabling Backdoor and Identifying Poison Data by using Knowledge Distillation in Backdoor Attacks on Deep Neural Networks","authors":"Kota Yoshida, T. Fujino","doi":"10.1145/3411508.3421375","DOIUrl":"https://doi.org/10.1145/3411508.3421375","url":null,"abstract":"Backdoor attacks are poisoning attacks and serious threats to deep neural networks. When an adversary mixes poison data into a training dataset, the training dataset is called a poison training dataset. A model trained with the poison training dataset becomes a backdoor model and it achieves high stealthiness and attack-feasibility. The backdoor model classifies only a poison image into an adversarial target class and other images into the correct classes. We propose an additional procedure to our previously proposed countermeasure against backdoor attacks by using knowledge distillation. Our procedure removes poison data from a poison training dataset and recovers the accuracy of the distillation model. Our countermeasure differs from previous ones in that it does not require detecting and identifying backdoor models, backdoor neurons, and poison data. A characteristic assumption in our defense scenario is that the defender can collect clean images without labels. A defender distills clean knowledge from a backdoor model (teacher model) to a distillation model (student model) with knowledge distillation. Subsequently, the defender removes poison-data candidates from the poison training dataset by comparing the predictions of the backdoor and distillation models. The defender fine-tunes the distillation model with the detoxified training dataset to improve classification accuracy. We evaluated our countermeasure by using two datasets. The backdoor is disabled by distillation and fine-tuning further improves the classification accuracy of the distillation model. The fine-tuning model achieved comparable accuracy to a baseline model when the number of clean images for a distillation dataset was more than 13% of the training data. Our results indicate that our countermeasure can be applied for general image-classification tasks and that it works well whether the defender's received training dataset is a poison dataset or not.","PeriodicalId":132987,"journal":{"name":"Proceedings of the 13th ACM Workshop on Artificial Intelligence and Security","volume":"61 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129216222","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 30

E-ABS: Extending the Analysis-By-Synthesis Robust Classification Model to More Complex Image Domains E-ABS:将综合分析鲁棒分类模型扩展到更复杂的图像域

Proceedings of the 13th ACM Workshop on Artificial Intelligence and Security Pub Date : 2020-11-09 DOI: 10.1145/3411508.3421382

An Ju, D. Wagner

引用次数: 8

Risk-based Authentication Based on Network Latency Profiling 基于网络延迟分析的风险认证

Proceedings of the 13th ACM Workshop on Artificial Intelligence and Security Pub Date : 2020-11-09 DOI: 10.1145/3411508.3421377

Esteban Rivera, Lizzy Tengana, Jesus Solano, Alejandra Castelblanco, Christian Lopez, Martín Ochoa

引用次数: 9

eNNclave eNNclave

Proceedings of the 13th ACM Workshop on Artificial Intelligence and Security Pub Date : 2020-11-09 DOI: 10.1145/3411508.3421376

Alexander Schlögl, Rainer Böhme

{"title":"eNNclave","authors":"Alexander Schlögl, Rainer Böhme","doi":"10.1145/3411508.3421376","DOIUrl":"https://doi.org/10.1145/3411508.3421376","url":null,"abstract":"Outsourcing machine learning inference creates a confidentiality dilemma: either the client has to trust the server with potentially sensitive input data, or the server has to share his commercially valuable model. Known remedies include homomorphic encryption, multi-party computation, or placing the entire model in a trusted enclave. None of these are suitable for large models. For two relevant use cases, we show that it is possible to keep all confidential model parameters in the last (dense) layers of deep neural networks. This allows us to split the model such that the confidential parts fit into a trusted enclave on the client side. We present the eNNclave toolchain to cut TensorFlow models at any layer, splitting them into public and enclaved layers. This preserves TensorFlow's performance optimizations and hardware support for public layers, while keeping the parameters of the enclaved layers private. Evaluations on several machine learning tasks spanning multiple domains show that fast inference is possible while keeping the sensitive model parameters confidential. Accuracy results are close to the baseline where all layers carry sensitive information and confirm our approach is practical.","PeriodicalId":132987,"journal":{"name":"Proceedings of the 13th ACM Workshop on Artificial Intelligence and Security","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132031320","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 11

SCRAP 废

Proceedings of the 13th ACM Workshop on Artificial Intelligence and Security Pub Date : 2020-11-09 DOI: 10.1145/3411508.3421378

Jesus Solano, Christian Lopez, Esteban Rivera, Alejandra Castelblanco, Lizzy Tengana, Martín Ochoa

引用次数: 7

Session details: Session 1: Adversarial Machine Learning 会议详情:会议1:对抗性机器学习

Proceedings of the 13th ACM Workshop on Artificial Intelligence and Security Pub Date : 2020-11-09 DOI: 10.1145/3433218

Nicholas Carlini

引用次数: 0

Mind the Gap: On Bridging the Semantic Gap between Machine Learning and Malware Analysis 注意差距:关于弥合机器学习和恶意软件分析之间的语义差距

Proceedings of the 13th ACM Workshop on Artificial Intelligence and Security Pub Date : 2020-11-01 DOI: 10.1145/3411508.3421373

Michael R. Smith, Nicholas T. Johnson, J. Ingram, A. Carbajal, Bridget I. Haus, Eva Domschot, Ramyaa, Christopher C. Lamb, Stephen J Verzi, W. Kegelmeyer

{"title":"Mind the Gap: On Bridging the Semantic Gap between Machine Learning and Malware Analysis","authors":"Michael R. Smith, Nicholas T. Johnson, J. Ingram, A. Carbajal, Bridget I. Haus, Eva Domschot, Ramyaa, Christopher C. Lamb, Stephen J Verzi, W. Kegelmeyer","doi":"10.1145/3411508.3421373","DOIUrl":"https://doi.org/10.1145/3411508.3421373","url":null,"abstract":"Machine learning (ML) techniques are being used to detect increasing amounts of malware and variants. Despite successful applications of ML, we hypothesize that the full potential of ML is not realized in malware analysis (MA) due to a semantic gap between the ML and MA communities---as demonstrated in the data that is used. Due in part to the available data, ML has primarily focused on detection whereas MA is also interested in identifying behaviors. We review existing open-source malware datasets used in ML and find a lack of behavioral information that could facilitate stronger impact by ML in MA. As a first step in bridging this gap, we label existing data with behavioral information using open-source MA reports---1) altering the analysis from identifying malware to identifying behaviors, 2)~aligning ML better with MA, and 3)~allowing ML models to generalize to novel malware in a zero/few-shot learning manner. We classify the behavior of a malware family not seen during training using transfer learning from a state-of-the-art model for malware family classification and achieve 57% - 84% accuracy on behavioral identification but fail to outperform the baseline set by a majority class predictor. This highlights opportunities for improvement on this task related to the data representation, the need for malware specific ML techniques, and a larger training set of malware samples labeled with behaviors.","PeriodicalId":132987,"journal":{"name":"Proceedings of the 13th ACM Workshop on Artificial Intelligence and Security","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121239181","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 22

Where Does the Robustness Come from?: A Study of the Transformation-based Ensemble Defence 稳健性从何而来?基于转换的集成防御研究

Proceedings of the 13th ACM Workshop on Artificial Intelligence and Security Pub Date : 2020-09-28 DOI: 10.1145/3411508.3421380

Chang Liao, Yao Cheng, Chengfang Fang, Jie Shi

引用次数: 1