Multimodal deepfake technologies have emerged rapidly in recent years, with wide application prospects in various fields. The conventional single-training paradigm with inherent limited generalization illustrates inadequate for addressing the continuous evolution of multimodal deepfakes. However, fine-tuning a model with new deepfake data faces past forgery patterns loss and the significant domain shift in diverse novel multimodal deepfake technologies. To address these issues, we propose a novel Quantum State Analytic Incremental Adaptability Learning method (Qsaint) for multimodal deepfake detection. To stabilize prior deepfake memory, Qsaint recursively learns detection-label mapping relations for the new deepfakes artifact with a closed-form solution, preserving the distribution memory from the historical deepfake domains without accessing previous videos. During incremental learning stages, we propose a deepfake quantum state adaptability module inspired by quantum information science. It adapts to the new forgery states and aligns them with the historical deepfake knowledge through cooling and evolution operations, eliminating deepfake domain shift issues. Comprehensive experiments demonstrate that Qsaint significantly mitigates the memory interference of historical deepfakes, effectively balancing the adaptability for new forgery tasks with the memorization of known deepfake patterns.

Biometric authentication is up-and-coming to replace the traditional identity authentication method (e.g., passwords, PIN, identification cards) for its convenience and intelligence. With more and more users using this method, the database becomes more extensive, and the functions are seriously challenged. Data outsourcing has advantages in terms of convenience and cost savings, so it has attracted much research effort. However, due to the biometric's immutability of the whole life, it is extremely sensitive, and disclosing it to a third party is undesirable. In this paper, we address the issue of securely outsourcing biometric database. We propose a novel boolean searchable symmetric encryption (SSE) to construct a secure interactive protocol when outsourcing. A new encrypted database construction method was proposed, using the more efficient boolean vectors. Based on this, We suggest three kinds of expressive SSE, supporting disjunctive query, boolean query, and lightweight settings. We prove the schemes' correctness and security theoretically. Our constructions use simple cryptographic tools, such as symmetric cryptography and pseudo-random functions. They are straightforward to understand and easy to implement. The experiments show that all our schemes are practical and more efficient than the existing methods.

Virtual machine monitor (VMM)-based anti-malware systems have recently become a popular research topic in finding ways of overcoming the fundamental limitations of traditional host-based anti-malware systems, which are likely to be deceived and attacked by malicious codes. This paper analyzes existing VMM-based models of malware detection. "Out-of-the-box" detection, active defense model, or In-VM models have the same defects: (1) on top of the VMM, two virtual machines are used, one by the user (Guest OS) and the other as monitor (Host OS), and (2) users cannot directly view the detection results nor configure detection system in the Guest OS. A layered detection model is proposed to overcome these issues, the bottom layer is responsible for security for the layers above it. Detection results can be directly displayed in the Guest OS, and users can view and configure the detection system. Furthermore, the detection model can isolate malware attacks to the detection system in the Guest OS. Experiment results show the validity of the proposed detection model.

The extensive use of Online Social Networks (OSNs) has attracted such wide attention of academia that OSNs have become a hot topic. Based on the interaction simulation, we have designed and implemented a Facebook crawler, which can obtain the complete friend list of a Facebook user and overcome the drawback in [7] that the crawler can get at most 400 friends. We make an analysis and visualization of the crawled dataset, and find that 36.5% of Facebook users have changed the default privacy setting, compared to 26.6% and 16% in [7, 20] respectively, implying that the awareness of privacy protection of Facebook users has been greatly improved.

Network routers play a key role in modern network communications and are attractive targets to attackers. By mistakenly forwarding, dropping, eavesdropping or modifying packets, malicious routers are great threat to network communications. Most papers emphasize particularly on securing routing protocols. In this paper, we present a protocol providing securely data packet forwarding with Byzantine robustness. The protocol has low overhead, low processing requirements and can detect misbehavior quickly. Through the simulation, our protocol increases throughput by 10% in the presence of 10% malicious nodes, and by 19% in the presence of 20% malicious nodes. Also, due to the authentication method, our protocol is suitable for wireless Ad Hoc networks.

Many P2P software have the similar communication patterns with computer worms, thus they will bring in false positives for behaviour based worm detection. Up to now, little work is done on the research of the similarities between communication patterns of worm and P2P software as well as how to eliminate the worm-like P2P traffic. Based on the analysis of popular P2P software used nowadays and the host process information, this paper presents ASG, which is a novel host based algorithm to generate signatures for worm-like P2P communication patterns. The contribution of our work lies in three aspects: a) Analyzing communication pattern similarities between P2P traffic and worm traffic through examples. b) Designing one practical and simple signature format for worm-like P2P traffic based on the host process information, c) Presenting Automated Signature Generation (ASG) method to extract the signature of worm-like P2P traffic. Experiments with the popular used P2P software show that ASG can effectively extract the signature and reduce the false positives.