In industrial control systems (ICSs), safeguarding system security is vital, and intrusion detection is an effective protective measure. In real-world ICS environments, however, the training data for intrusion-detection models are dominated by normal traffic, with very few abnormal samples. This scarcity prevents the model from fully learning abnormal characteristics, thereby limiting anomaly-detection performance. ICS traffic is also noisy and often captured incompletely, which is especially problematic because it possesses strong temporal dependencies. Moreover, ICS operations tend to be highly regular and follow a strict logical order, causing data to cluster densely in certain regions while edge regions remain sparsely populated—an imbalance that easily leads to misclassification. To tackle data imbalance, missing temporal features, and edge-sample scarcity, we propose the DualCGAN-AE approach. It employs two conditional generative adversarial networks to perform dynamic learning on global and edge features and to enrich samples with temporal information; a multimodel discriminator is incorporated to enhance training stability. We validated the method on two datasets, assessing both the quality of the generated samples and their impact on intrusion detection performance. Experimental results show that the samples produced by DualCGAN-AE significantly boost detection accuracy.

Computer vision (CV) applications empower various Internet of Things (IoT) scenarios. However, their advancements in image generation and manipulation tools make it increasingly easy to produce highly deceptive forged images, escalating the risk of image forgery. Cryptography-based methods can secure images but cannot support direct CV applications with compromised visual legibility. Existing generative adversarial network (GAN)-based steganography methods can effectively facilitate CV applications and image forgery prevention with high indistinguishability between stego and cover images. However, they are inefficient in resource-constrained IoT scenarios. Therefore, we propose a lightweight image forgery prevention scheme for IoT using GAN-based steganography. Our scheme embeds identity data within images. If forged, it fails to recover, triggering alerts. Our scheme can significantly improve efficiency with a lightweight generator designed by incorporating blueprint separable convolutions, sum connections and discrete wavelet transform while ensuring high effectiveness. Real-world IoT experimental results demonstrate this.

Smart contracts play a pivotal role in Ethereum by providing autonomous control functions and eliminating risks from third parties. However, there exists a current dearth of a universal automated solution to ensure contract security. In this paper, we propose EtherEditor, a bytecode-based framework to enhance smart contract security. EtherEditor operates independently of the source code, directly analyzing bytecode to automate the reconstruction of Control Flow Graphs (CFGs), vulnerability detection, and patching processes. The paper initiates with the development of a virtual execution engine for symbolic execution of bytecode, dynamically interpreting the effects of various opcodes on the stack. This approach culminates in the creation of a high-precision CFG at the bytecode level, capturing nuanced semantic information. This method lays a solid foundation for subsequent work. The paper then collects sensitive semantic information from the constructed CFG, including data flow and control flow characteristics, aiming to detect vulnerabilities by identifying risk instructions that contribute to vulnerabilities. Finally, the paper generates patch instances using preset patch templates based on the current contract’s context. These instances are then infused into the original bytecode via an advanced trampoline patch injection technique, ensuring the seamless operation of the amended contract. Extensive experiments demonstrate that our method achieves significant improvements in existing smart contract vulnerability detection and patch rewriting.

The escalating complexity of networks due to advancements in cloud computing, IoT, and data centers necessitates a shift towards more adaptable and scalable network architectures. Software Defined Networking (SDN) has risen as a prominent solution, offering a separation of control and data planes to bolster flexibility and manageability. However, network failures remain an inherent risk, undermining the reliability of both traditional and SDN environments. This paper presents BioWarp, a novel SDN failure recovery scheme that integrates bio-mimetic optimization with a Weighted-Cost Multi-Path (WCMP) routing approach. BioWarp confronts the unique challenges of SDN, such as TCAM overflow and controller computation stress, by proposing a hybrid strategy that merges the strengths of proactive and reactive recovery methods. We introduce a flow label based aggregation method to alleviate the burden on flow tables and controller resources. The Coati Optimization Algorithm (COA), inspired by the behaviors of coatis, is adapted to optimize weight update in real-time, facilitating rapid and efficient recovery from network faults. Simulation experiments are conducted to substantiate the scheme’s efficacy, demonstrating improved recovery times and resource management without compromising network stability.

With the rapid advancement of information technology, the issue of software security is increasingly gaining attention. Heap memory, as a key component of memory management in open-source software, presents particularly prominent security concerns. Heap-related vulnerabilities such as heap memory overflow, use after free, and memory leaks can pose serious security threats. To effectively detect and prevent such vulnerabilities, in this paper we introduce a new multi-phase and heap-related operations guided fuzzer called MHFuzz. This method focuses on heap-related operations, and through static instrumentation and dynamic runtime feedback, it prioritizes the mutation of seeds that trigger more heap-related operations and allocates more energy to them, thereby enhancing the capability and efficiency of vulnerability mining.The innovation of MHFuzz lies in its phased fuzzing strategy: the first phase focuses on extensively mining heap-related vulnerabilities, while the second phase, to avoid the situation of local optima, concentrates on testing low-frequency paths to improve testing efficiency. Furthermore, MHFuzz employs non-dominated sorting and the simulated annealing algorithm to optimize the processes of seed selection and energy distribution, ensuring that superior seeds have more opportunities for mutation. Experimental assessments have shown that MHFuzz outperforms four advanced fuzzing tools in tests across eight real-world programs, not only increasing code coverage but also successfully discovering five unknown heap memory vulnerabilities, which three of them were subsequently assigned CVE numbers.

With the growing emphasis on data privacy, Federated Learning (FL) has emerged as a novel distributed machine learning approach. It allows multiple participants to collaboratively train models without sharing their local data. However, ongoing research has shown that even without direct data exchange, sharing model parameters can still lead to privacy breaches. Differential Privacy (DP) helps mitigate this by adding noise to model parameters, ensuring privacy. While effective, this noise can degrade model performance. Therefore, finding a balance between noise injection and model accuracy remains a key challenge.To address this issue, we propose a dynamic noise addition method for hierarchical federated learning. Our method stratifies the model and injects different levels of noise based on each parameter’s contribution to the global model. We introduce a layer-wise asynchronous noise addition strategy. In this strategy, Deep Neural Networks (DNNs) are divided into shallow and deep layers. Deeper layers receive a larger privacy budget to enhance their protection. Additionally, we prioritize important features in the input layer, applying stricter noise to parameters with higher significance.We validated our algorithm on DNNs using two distinct datasets. The results confirm the effectiveness of our method in balancing privacy and model performance.

Fuzzing is widely used in vulnerability mining because of its simplicity and efficiency. The fuzzing tool generates numerous testcases according to the mutation of the initial seed and inputs them into the program to be tested. At the same time, it monitors exceptions of the running program to find possible software bugs. In order to improve the performance of fuzzing, many researchers are committed to generating various initial testcases. However, at present, fuzzing testcase generation does not make full use of the information of testcases, the generation process is uncontrollable, and the generation effect is general. In view of the problems mentioned above, this paper proposes a testcase generation method based on conditional generative adversarial networks. The CWGAN-GP (Conditional Wasserstein Generic Adversarial Network-Gradient Penalty) learns the format features of testcases, and generates testcases covering corresponding branches according to the input branch information. This paper conducted experiments on 6 common programs, and the experiments showed that compared to the initial training set, testcases generated by (C)WGAN-GP can extend the exploration of the program, and thus find more vulnerabilities. The CWGAN-GP model uses the branch vector in the training set as the condition to generate testcases, which can find more crashes and hangs, and improve the final fuzzing performance.

In fuzzing, the generative adversarial network learns from the training set and generates test-cases with similar formats, so as to provide inputs conforming to the input format for programs tested. However, problems of the unstable training process, single generation method, and monotonic sample types generated exist in general generative adversarial networks. This paper proposes a fuzzing input generation technique based on VAE-GAN, which introduces the representation learning process of variational auto-encoder for traditional generative adversarial networks, so that it can learn and utilize the character information of testcases, improving the stability of training and generate various testcases. It is shown that testcases generated by VAE-GAN trigger more unique tuples than other existing generative adversarial networks on 3 among 4 selected target programs. Moreover, compared with the AFL mutation training set, testcases generated by VAE-GAN can improve code coverage by up to 11.87%, and the discovery rate of 15.74% and 5.36% in the unique crashes and hangs respectively.

With the development of IoT technology, smart grid has gradually replaced the traditional grid. Smart grid is convenient and fast. It can provide real-time residential electricity monitoring and forecasting, give users better electricity guidance and save a lot of labor costs. Smart meters send customers’ electricity consumption data to the gateway, which aggregates the data and then sends it to the electricity consumption control center. But in this process, there will be a security problem of leakage of customer’s electricity consumption data. Most of the current user data privacy protection collection schemes use homomorphic encryption and randomization techniques. However, some of these schemes require a trusted third-party entity, and some may cause significant computational overhead. Due to the limited computational resources of smart meters, these techniques may be impractical. In this paper, we propose a local differential privacy data aggregation protection scheme based on the idea of grouping perturbation of electricity consumption data according to data domains. Experiments show that our scheme can provide statistical estimates of electricity in the region while satisfying the privacy protection of customers’ electricity consumption data. Moreover, our scheme has small computational and communication overheads, which can meet the application requirements in practical scenarios.

In this work, we conduct an in-depth survey on recent multimedia storage security research activities in association with cloud computing. After an overview of the cloud storage system and its security problem, we focus on four hot research topics. They are data integrity, data confidentiality, access control, and data manipulation in the encrypted domain. We describe several key ideas and solutions proposed in the current literature and point out possible extensions and futuristic research opportunities. Our research objective is to offer a state-of-the-art knowledge to new researchers who would like to enter this exciting new field.

This work is about content based image database retrieval, focusing on developing a classification based methodology to address semantics-intensive image retrieval. With self organization map based image feature grouping, a visual dictionary is created for color, texture, and shape feature attributes, respectively. Labeling each training image with the keywords in the visual dictionary, a classification tree is built. Based on the statistical properties of the feature space we define a structure, called /spl alpha/-semantics graph, to discover the hidden semantic relationships among the semantic repositories embodied in the image database. With the /spl alpha/-semantics graph, each semantic repository is modeled as a unique fuzzy set to explicitly address the semantic uncertainty and the semantic overlap existing among the repositories in the feature space. A retrieval algorithm combining the classification tree with the fuzzy set models to deliver semantically relevant image retrieval is provided. The experimental evaluations have demonstrated that the proposed approach models the semantic relationships effectively and outperforms a state-of-the-art content based image retrieval system in the literature both in effectiveness and efficiency.

This paper proposes an integrative approach that facilitates physicians to semi automatically obtain a 3-D symbolic representation of cerebral vasculature from 3-D magnetic resonance angiography (MRA) datasets. In this approach, firstly vessels are segmented by morphology method followed by 3-D parallel thinning to obtain the one voxel wide skeleton. Then a novel method employing general tree and its combinations is introduced to depict the 3-D geometrical structure of the vasculature. With the generated tree, post processing, such as traversal and visualization, is implemented. The method has been tested on both synthetic images and real images; the results are promising. A system based on this approach provides a useful visualization tool of the intracerebral vasculature for clinic applications.