Unsupervised Domain Adaptation (UDA) intends to achieve excellent results by transferring knowledge from labeled source domains to unlabeled target domains in which the data or label distribution changes. Previous UDA methods have acquired great success when labels in the source domain are pure. However, even the acquisition of scare clean labels in the source domain needs plenty of costs as well. In the presence of label noise in the source domain, the traditional UDA methods will be seriously degraded as they do not deal with the label noise. In this paper, we propose an approach named Robust Self-training with Label Refinement (RSLR) to address the above issue. RSLR adopts the self-training framework by maintaining a Labeling Network (LNet) on the source domain, which is used to provide confident pseudo-labels to target samples, and a Target-specific Network (TNet) trained by using the pseudo-labeled samples. To combat the effect of label noise, LNet progressively distinguishes and refines the mislabeled source samples. In combination with class re-balancing to combat the label distribution shift issue, RSLR achieves effective performance on extensive benchmark datasets.
Reinforcement Learning (RL) is gaining importance in automating penetration testing as it reduces human effort and increases reliability. Nonetheless, given the rapidly expanding scale of modern network infrastructure, the limited testing scale and monotonous strategies of existing RL-based automated penetration testing methods make them less effective in practical application. In this paper, we present CLAP (Coverage-Based Reinforcement Learning to Automate Penetration Testing), an RL penetration testing agent that provides comprehensive network security assessments with diverse adversary testing behaviours on a massive scale. CLAP employs a novel neural network, namely the coverage mechanism, to address the enormous and growing action spaces in large networks. It also utilizes a Chebyshev decomposition critic to identify various adversary strategies and strike a balance between them. Experimental results across various scenarios demonstrate that CLAP outperforms state-of-the-art methods, by further reducing attack operations by nearly 35%. CLAP also provides enhanced training efficiency and stability and can effectively perform pen-testing over large-scale networks with up to 500 hosts. Additionally, the proposed agent is also able to discover pareto-dominant strategies that are both diverse and effective in achieving multiple objectives.
In Weighted Model Counting (WMC), we assign weights to literals and compute the sum of the weights of the models of a given propositional formula where the weight of an assignment is the product of the weights of its literals. The current WMC solvers work on Conjunctive Normal Form (CNF) formulas. However, CNF is not a natural representation for human-being in many applications. Motivated by the stronger expressive power of Pseudo-Boolean (PB) formulas than CNF, we propose to perform WMC on PB formulas. Based on a recent dynamic programming algorithm framework called ADDMC for WMC, we implement a weighted PB counting tool
It plays a central role in intelligent agent systems to model agents’ epistemic states and their changes. Asynchrony plays a key role in distributed systems, in which the messages transmitted may not be received instantly by the agents. To characterize asynchronous communications, Asynchronous Announcement Logic (AAL) has been presented, which focuses on the logic laws of the change of epistemic state after receiving information. However AAL does not involve the interactive behaviours between an agent and its environment. Epistemic interactions can change agents’ epistemic states, while the latter will affect the former. Through enriching the well-known
Sharding is a promising technique to tackle the critical weakness of scalability in blockchain-based unmanned aerial vehicle (UAV) search and rescue (SAR) systems. By breaking up the blockchain network into smaller partitions called shards that run independently and in parallel, sharding-based UAV systems can support a large number of search and rescue UAVs with improved scalability, thereby enhancing the rescue potential. However, the lack of adaptability and interoperability still hinder the application of sharded blockchain in UAV SAR systems. Adaptability refers to making adjustments to the blockchain towards real-time surrounding situations, while interoperability refers to making cross-shard interactions at the mission level. To address the above challenges, we propose a blockchain UAV system for SAR missions based on dynamic sharding mechanism. Apart from the benefits in scalability brought by sharding, our system improves adaptability by dynamically creating configurable and mission-exclusive shards, and improves interoperability by supporting calls between smart contracts that are deployed on different shards. We implement a prototype of our system based on Quorum, give an analysis of the improved adaptability and interoperability, and conduct experiments to evaluate the performance. The results show our system can achieve the above goals and overcome the weakness of blockchain-based UAV systems in SAR scenarios.
Data outsourcing has become an industry trend with the popularity of cloud computing. How to search data securely and efficiently has received unprecedented attention. Dynamic Searchable Symmetric Encryption (DSSE) is an effective method to solve this problem, which supports file updates and keyword-based searches over encrypted data. Unfortunately, most existing DSSE schemes have privacy leakages during the addition and deletion phases, thus proposing the concepts of forward and backward privacy. At present, some secure DSSE schemes with forward and backward privacy have been proposed, but most of these DSSE schemes only achieve single-keyword query in the single-client setting, which seriously limits the application in practice. To solve this problem, we propose a multi-client and multi-keyword searchable symmetric encryption scheme with forward and backward privacy (MMKFB). Our scheme focuses on the multi-keyword threshold queries in the multi-client setting, which is a new pattern of multi-keyword search realized with the help of additive homomorphism. And performance analysis and experiments demonstrate that our scheme is more practical for use in small and medium size databases. Especially when a large number of files are updated at once, our scheme has advantages over some existing DSSE schemes in terms of computational efficiency and client storage overhead.
Adversarial training has been widely considered the most effective defense against adversarial attacks. However, recent studies have demonstrated that a large discrepancy exists in the class-wise robustness of adversarial training, leading to two potential issues: firstly, the overall robustness of a model is compromised due to the weakest class; and secondly, ethical concerns arising from unequal protection and biases, where certain societal demographic groups receive less robustness in defense mechanisms. Despite these issues, solutions to address the discrepancy remain largely underexplored. In this paper, we advance beyond existing methods that focus on class-level solutions. Our investigation reveals that hard examples, identified by higher cross-entropy values, can provide more fine-grained information about the discrepancy. Furthermore, we find that enhancing the diversity of hard examples can effectively reduce the robustness gap between classes. Motivated by these observations, we propose Fair Adversarial Training (FairAT) to mitigate the discrepancy of class-wise robustness. Extensive experiments on various benchmark datasets and adversarial attacks demonstrate that FairAT outperforms state-of-the-art methods in terms of both overall robustness and fairness. For a WRN-28-10 model trained on CIFAR10, FairAT improves the average and worst-class robustness by 2.13% and 4.50%, respectively.
Edge-assisted mobile crowdsensing (EMCS) has gained significant attention as a data collection paradigm. However, existing incentive mechanisms in EMCS systems rely on centralized platforms, making them impractical for the decentralized nature of EMCS systems. To address this limitation, we propose CHASER, an incentive mechanism designed for blockchain-based EMCS (BEMCS) systems. In fact, CHASER can attract more participants by satisfying the incentive requirements of budget balance, double-side truthfulness, double-side individual rationality and also high social welfare. Furthermore, the proposed BEMCS system with CHASER in smart contracts guarantees the data confidentiality by utilizing an asymmetric encryption scheme, and the anonymity of participants by applying the zero-knowledge succinct non-interactive argument of knowledge (zk-SNARK). This also restrains the malicious behaviors of participants. Finally, most simulations show that the social welfare of CHASER is increased by approximately
