Domain generation algorithms (DGAs) can be categorized into three types: zero-knowledge , partial-knowledge , and full-knowledge . While prior research merely focused on zero-knowledge and full-knowledge types, we characterize their anti-detection ability and practicality and find that zero-knowledge DGAs present low anti-detection ability against detectors , and full-knowledge DGAs suffer from low practicality due to the strong assumption that they are fully detector -aware. Given these observations, we propose PKDGA , a partial knowledge-based domain generation algorithm with high anti-detection ability and high practicality. PKDGA employs the reinforcement learning architecture, which makes it evolve automatically based only on the easily-observable feedback from detectors. We evaluate PKDGA using a comprehensive set of real-world datasets, and the results demonstrate that it reduces the detection performance of existing detectors from 91.7% to 52.5%. We further apply PKDGA to the Mirai malware, and the evaluations show that the proposed method is quite lightweight and time-efficient.
29 March 2021 in IEEE Transactions on Network and Service Management
Detecting abnormal service performance is significant for Internet-based service management and operation. Recent advances in anomaly detection methods prefer unsupervised learning algorithms since they can work without manually labelled data. However, existing unsupervised methods converge into suboptimal solutions due to their heuristic-based objectives. Moreover, they frequently rely on the strong assumption that noise follows a Gaussian distribution, and their detection accuracy is also highly sensitive to threshold settings. To detect anomalies precisely and robustly, we present Adran , an unsupervised anomaly detection model that introduces adversarial learning into a reconstructive model, generating a reconstructive adversarial network with an anomaly detection-based training objective. It tolerates non-Gaussian noise by activating the discriminator with a non-smooth function. Our experimental results demonstrate that Adran achieves an improvement of $\geq 32\%$ over the state-of-the-art methods in terms of F-score . Moreover, the robustness analysis demonstrates that it is reasonably easy and straightforward to set an appropriate threshold using Adran .
Event detection by discovering frequent itemsets is very popular in sensor network communities. However, the recorded data is often a probability rather than a determined value in a really productive environment as sensed data is often affected by noise. In this paper, we study to detect events by finding frequent patterns over probabilistic sensor data under the Possible World Semantics. This is technically challenging as probabilistic records can generate an exponential number of possible worlds. Although several efficient algorithms are proposed in the literature, it is still difficult to mine probabilistic maximal frequent items (PMFIs) in large uncertain database due to the high time complexity. To address this issue, we employ approximate idea to further reduce the time complexity from O(nlogn) to O(n) and propose a two-step solution (Aproximation Probabilistic Frequent Itemset-MAX, APFI-MAX in short) including PMFI candidates generation and PMFIs confirmation. We also provide the necessary proofs of our approximation method to make APFI-MAX more solid and convincing. Finally, extensive experiments have been conducted on synthetic and real databases, demonstrating that the proposed APFI-MAX always running faster than state-of-art methods under different parameter settings.
17 June 2022 in Mathematical Problems in Engineering
Nowadays, various algorithms are widely used in the field of economy and trade, and economic and trade management laws also need to introduce scientific and effective data models for optimization. In this paper, support vector machine algorithm and logistic regression algorithm are used to analyze and process the actual economic and trade case data and bank loan user data, and a hybrid model of support vector machine and logistic regression is established. This study first introduces the basic definitions and contents of the support vector machine algorithm and logistic regression algorithm, and then constructs a hybrid model by randomly dividing the data, first using the support vector machine algorithm to calculate the results, and then inputting them into the logistic regression algorithm. The first mock exam is that the efficiency of the hybrid model is much higher than that of the single model. This study mainly optimizes and upgrades the legal system of economic and trade management from two aspects. In the prediction of economic and trade legal cases, the hybrid model is significantly better than FastText and LSTM models in accuracy and macro recall performance. In terms of credit risk prediction of economic and trade loan users, the subset most likely to default in the loan customer set is obtained.
24 August 2023 in IEEE Transactions on Network Science and Engineering
Security vendors can take down botnets by detecting the malicious domain names crafted by attackers. However, the adversarial Domain Generation Algorithms ( DGAs ) greatly challenge the existing domain detection schemes, in particular, adversarial DGAs can actively compromise arbitrarily specified domain detection systems by crafting the adversarial domain names. To resist adversarial DGAs, we propose a game theory-based defending strategy, which launches adversarial DGA and trains an incremental domain detector alternately. While we find the game-based strategy cannot achieve the expected detection accuracy due to two problems: the failure of incremental training and the problem of the catastrophic forgetting . To this end, we propose a multi-level incremental random forest model, which settles the above problems by splitting the leaf nodes of the decision trees and increasing the levels of the original random forest. The experimental results on the real-life dataset demonstrate the proposed detection method significantly outperforms the competing schemes when detecting adversarial DGAs (improves the detection AUC by 42%) and presents comparable performance when defending against non-adversarial DGAs.
28 November 2024 in IEEE Transactions on Parallel and Distributed Systems
Inter-datacenter network applications generate massive coflows for purposes, e.g., backup, synchronization, and analytics, with deadline requirements. Decentralized coflow scheduling frameworks are desirable for their scalability in cross-domain deployment but grappling with the challenge of information agnosticism for lack of cross-domain privileges. Current information-agnostic coflow scheduling methods are incompatible with decentralized frameworks for relying on centralized controllers to continuously monitor and learn from coflow global transmission states to infer global coflow information. Alternative methods propose mechanisms for decentralized global coflow information gathering and synchronization. However, they require dedicated physical hardware or control logic, which could be impractical for incremental deployment. This paper proposes Slark, a decentralized deadline-aware coflow scheduling framework, which meets coflows' soft and hard deadline requirements using only local traffic information. It eschews requiring global coflow transmission states and dedicated hardware or control logic by leveraging multiple software-implemented scheduling agents working independently on each node and integrating such information agnosticism into node-specific bandwidth allocation by modeling it as a robust optimization problem with flow information on the other nodes represented as uncertain parameters. Subsequently, we validate the performance robustness of Slark by investigating how perturbations in the optimal objective function value and the associated optimal solution are affected by uncertain parameters. Finally, we propose a firebug-swarm-optimization-based heuristic algorithm to tackle the non-convexity in our problem. Experimental results demonstrate that Slark can significantly enhance transmission revenue and increase soft and hard deadline guarantee ratios by 10.52% and 7.99% on average.