DeepAID: Interpreting and Improving Deep Learning-based Anomaly Detection in Security Applications
Authors: Dongqi Han, Zhiliang Wang, Wenqi Chen, Ying Zhong, Su Wang, Han Zhang, Jiahai Yang, Xingang Shi, Xia Yin
Abstract: Unsupervised Deep Learning (DL) techniques have been widely used in various security-related anomaly detection applications, owing to the great promise of being able to detect unforeseen threats and superior performance provided by Deep Neural Networks (DNN). However, the lack of interpretability creates key barriers to the adoption of DL models in practice. Unfortunately, existing interpretation approaches are proposed for supervised learning models and/or non-security domains, which are unadaptable for unsupervised DL models and fail to satisfy special requirements in security domains. In this paper, we propose DeepAID, a general framework aiming to (1) interpret DL-based anomaly detection systems in security domains, and (2) improve the practicality of these systems based on the interpretations. We first propose a novel interpretation method for unsupervised DNNs by formulating and solving well-designed optimization problems with special constraints for security domains. Then, we provide several applications based on our Interpreter as well as a model-based extension Distiller to improve security systems by solving domain-specific problems. We apply DeepAID over three types of security-related anomaly detection systems and extensively evaluate our Interpreter with representative prior works. Experimental results show that DeepAID can provide high-quality interpretations for unsupervised DL models while meeting the special requirements of security domains. We also provide several use cases to show that DeepAID can help security operators to understand model decisions, diagnose system mistakes, give feedback to models, and reduce false positives.Comment: Accepted by 2021 ACM SIGSAC Conference on Computer and Communications Security (CCS '21)
Date: 23 Sep 2021
PDF »Main page »
An Improved Authentication & Key Exchange Protocol Based on ECDH for WSNs
Authors: Sina Baghbanijam, Hanie Sanaei
Abstract: Wide-spread use of wireless sensor networks (WSNs) that are consisted of resource-constrained sensor nodes in communication with gateways in sensitive and mission-critical industries have highlighted the need for a secure yet fast communication protocol between users, gateways and sensor nodes. Due to the properties of the network, elliptic-curve cryptography seems to be the most viable choice as it requires less resources than most other options. In this paper we analyze the protocol suggested by Moghadam et al. which is based on ECDH (elliptic-curve Diffie-Hellman) and mention some of the flaws in their proposed authentication and key exchange protocol. Some attacks are also mentioned to further explain the shortcomings of their schema. Then a modified version of the protocol is proposed, analyzed and checked against the same attacks as an informal security proof.Comment: 6 Pages, 5 figures
Date: 23 Sep 2021
PDF »Main page »
On The Vulnerability of Anti-Malware Solutions to DNS Attacks
Authors: Asaf Nadler, Ron Bitton, Oleg Brodt, Asaf Shabtai
Abstract: Anti-malware agents typically communicate with their remote services to share information about suspicious files. These remote services use their up-to-date information and global context (view) to help classify the files and instruct their agents to take a predetermined action (e.g., delete or quarantine). In this study, we provide a security analysis of a specific form of communication between anti-malware agents and their services, which takes place entirely over the insecure DNS protocol. These services, which we denote DNS anti-malware list (DNSAML) services, affect the classification of files scanned by anti-malware agents, therefore potentially putting their consumers at risk due to known integrity and confidentiality flaws of the DNS protocol. By analyzing a large-scale DNS traffic dataset made available to the authors by a well-known CDN provider, we identify anti-malware solutions that seem to make use of DNSAML services. We found that these solutions, deployed on almost three million machines worldwide, exchange hundreds of millions of DNS requests daily. These requests are carrying sensitive file scan information, oftentimes - as we demonstrate - without any additional safeguards to compensate for the insecurities of the DNS protocol. As a result, these anti-malware solutions that use DNSAML are made vulnerable to DNS attacks. For instance, an attacker capable of tampering with DNS queries, gains the ability to alter the classification of scanned files, without presence on the scanning machine. We showcase three attacks applicable to at least three anti-malware solutions that could result in the disclosure of sensitive information and improper behavior of the anti-malware agent, such as ignoring detected threats. Finally, we propose and review a set of countermeasures for anti-malware solution providers to prevent the attacks stemming from the use of DNSAML services.Date: 23 Sep 2021
PDF »Main page »
A Validated Privacy-Utility Preserving Recommendation System with Local Differential Privacy
Authors: Seryne Rahali, Maryline Laurent, Souha Masmoudi, Charles Roux, Brice Mazeau
Abstract: This paper proposes a new recommendation system preserving both privacy and utility. It relies on the local differential privacy (LDP) for the browsing user to transmit his noisy preference profile, as perturbed Bloom filters, to the service provider. The originality of the approach is multifold. First, as far as we know, the approach is the first one including at the user side two perturbation rounds - PRR (Permanent Randomized Response) and IRR (Instantaneous Randomized Response) - over a complete user profile. Second, a full validation experimentation chain is set up, with a machine learning decoding algorithm based on neural network or XGBoost for decoding the perturbed Bloom filters and the clustering Kmeans tool for clustering users. Third, extensive experiments show that our method achieves good utility-privacy trade-off, i.e. a 90$\%$ clustering success rate, resp. 80.3$\%$ for a value of LDP $\epsilon = 0.8$, resp. $\epsilon = 2$. Fourth, an experimental and theoretical analysis gives concrete results on the resistance of our approach to the plausible deniability and resistance against averaging attacks.Comment: Accepted for publication in the 15th IEEE International Conference on Big Data Science and Engineering (BigDataSE 2021)
Date: 23 Sep 2021
PDF »Main page »
FooBaR: Fault Fooling Backdoor Attack on Neural Network Training
Authors: Jakub Breier, Xiaolu Hou, Martín Ochoa, Jesus Solano
Abstract: Neural network implementations are known to be vulnerable to physical attack vectors such as fault injection attacks. As of now, these attacks were only utilized during the inference phase with the intention to cause a misclassification. In this work, we explore a novel attack paradigm by injecting faults during the training phase of a neural network in a way that the resulting network can be attacked during deployment without the necessity of further faulting. In particular, we discuss attacks against ReLU activation functions that make it possible to generate a family of malicious inputs, which are called fooling inputs, to be used at inference time to induce controlled misclassifications. Such malicious inputs are obtained by mathematically solving a system of linear equations that would cause a particular behaviour on the attacked activation functions, similar to the one induced in training through faulting. We call such attacks fooling backdoors as the fault attacks at the training phase inject backdoors into the network that allow an attacker to produce fooling inputs. We evaluate our approach against multi-layer perceptron networks and convolutional networks on a popular image classification task obtaining high attack success rates (from 60% to 100%) and high classification confidence when as little as 25 neurons are attacked while preserving high accuracy on the originally intended classification task.Date: 23 Sep 2021
PDF »Main page »