Retrieval-Augmented Generation (RAG) mitigates hallucinations in large language models (LLMs) by incorporating external knowledge in open-domain question answering. However, for complex multi-hop questions, mainstream iterative retrieval methods struggle with conflicts between internal and retrieved knowledge and noisy external documents. Achieving flexible and effective integration of internal and external knowledge continues to be a research challenge. In this paper, we propose a dynamic knowledge fusion-based RAG framework (DKF-RAG), which can adaptively adjust the knowledge fusion strategy during the iterative reasoning process. Specifically, DKF-RAG iteratively decomposes complex multi-hop questions into simpler sub-questions, forming a reasoning chain. At each iteration, it assesses the relevance and consistency of external knowledge in real time, based on which adaptive fusion actions are triggered to integrate internal and external information. We conduct experiments on four multi-hop QA datasets and compare DKF-RAG against multiple iterative retrieval-augmented baselines, demonstrating its superiority and effectiveness.

Secret image sharing (SIS) schemes have undergone significant development. However, to the best of our knowledge, none of the existing schemes has considered the deniable property during secret sharing. This presents a problem when we need to share secret images through an untrusted and supervised channel, where we may be coerced to reveal the secret to adversary. Here we propose a deniable SIS (DSIS) scheme. Before sharing the secret image, we manipulate the secret area of the image to create a forged image that possesses deniability. Then we employ SIS to distribute the forged image, while generating an auxiliary matrix derived from secret key. This matrix governs rules for sharing secret area. In the event of coercion to reveal the secret, we have the capability to present the adversary with the forged image instead, thereby retaining control over the disclosure of the secret area at our discretion. In DSIS, we can obtain a secret image with the small-sized secret key losslessly, while we can recover another visually-meaningful fake image to safeguard the secrecy and protect ourselves when facing coercion.

Secret image sharing (SIS) has made significant progress in research and has found wide applications. However, we note that shadows of traditional SIS contain a large amount of redundancy. A novel Shadow-Embeddable Secret Image Sharing scheme (SE-SIS) leveraging the redundancy in the shadows is proposed in this paper. SE-SIS utilizes the random values in Lagrange polynomials of traditional secret image sharing (SIS) scheme, and modifies a shadow to embed another secret image with a secret key. Then other shadows are modified simultaneously according to the properties of Lagrange polynomials to ensure the accurate recovery of the previously shared image. It is worth noting that embedding process does not impact the recovery of the shared image, and the embedded shadow is indistinguishable from the others. SE-SIS modifies noise-liked shadows into other noise-liked ones without affecting the recovery process, thereby achieving a high embedding rate. Meanwhile, SE-SIS realizes lossless recovery for both the shared image and the secret image. Experimental results indicate SE-SIS constructs randomized shadows and exhibits excellent performance in terms of Peak Signal to Noise Ratio (PSNR) and embedding rate.

Online hashing has gained significant interest for its tremendous promise in handling large-scale streaming image data. However, there are still several problems to be solved. Firstly, many existing methods struggle to fully utilize previous knowledge and fail to effectively mitigate catastrophic forgetting. Secondly, current online hashing methods lack targeted guidance for hash function learning, resulting in weak discriminative ability. Thirdly, many current methods adopt ineffective optimization methods to learn hash code. This paper proposes a Discriminative Visual-semantic Collaborative Online Decomposition Hashing method, abbreviated as DVsCODH. It includes two steps: hash code learning and hash function learning. In the first step, DVsCODH adopts an online pairwise similarity supervision to guide hash code learning, and simultaneously introduces a visual-semantic collaborative online decomposition strategy to adaptively fuse visual and semantic information. Through incremental online learning, DVsCODH is capable of extracting complete similarity, visual and high-level semantic information of the database. In the second step, DVsCODH leverages database-wide similarity to supervise hash function online learning. Furthermore, we propose an effective online discrete optimization algorithm that directly generate hash code, thereby enhancing model training efficiency. Experimental results on three public image datasets demonstrate the excellent retrieval performance of DVsCODH.

Image steganography aims to conceal secret messages within an image without detection and has a long development history. With the rapid development of generative artificial intelligence, generative image steganography is also thriving. However, existing generative steganography methods struggle to balance steganographic capacity, extraction accuracy, and security. This paper proposes a high-capacity generative steganography method based on the first-order DPM-Solver, called StegaFDS. By utilizing our efficiently designed mapping function, which connects secret messages to the noise space of the diffusion probabilistic model (DPM), we achieve a significant increase in hiding capacity and detection resistance, while maintaining distribution-preserving. To improve message extraction accuracy further, we also optimize the existing first-order DPM-Solver inversion. Additionally, based on pre-trained diffusion models, StegaFDS can generate high-quality stego images without training. Experimental results show that StegaFDS performs exceptionally better than other generative steganography methods in the abovementioned metrics and demonstrates strong potential and availability.

With the rapid development of general cloud services, more and more individuals or collectives use cloud platforms to store data. Assured data deletion deserves investigation in cloud storage. In time-sensitive data storage scenarios, it is necessary for cloud platforms to automatically destroy data after the data owner-specified expiration time. Therefore, assured time-sensitive data deletion should be sought. In this paper, a fine-grained assured time-sensitive data deletion (ATDD) scheme in cloud storage is proposed by embedding the time trapdoor in Ciphertext-Policy Attribute-Based Encryption (CP-ABE). Time-sensitive data is self-destructed after the data owner-specified expiration time so that the authorized users cannot get access to the related data. In addition, a credential is returned to the data owner for data deletion verification. This proposed scheme provides solutions for fine-grained access control and verifiable data self-destruction. Detailed security and performance analysis demonstrate the security and the practicability of the proposed scheme.

Due to the increasing popularity of cloud computing and privacy preservation concerns, sensitive data should be encrypted before outsourcing to the cloud and data utilization becomes a challenging issue. Searchable encryption (SE) is a promising technique to address this problem. Most existing searchable encryption schemes only support accurate keyword but fuzzy keyword search schemes are appreciated in practice. Moreover, in some application scenarios like the video on demand systems, data owners only hope to give the access of their data to those who have payed but authenticated user identity may often change. Therefore, dynamic user attribute updating should be considered. To solve about issues, we propose a fuzzy secure keyword search scheme over encrypted cloud data with dynamic fine-grained access control. We design a novel fuzzy keyword index to retrieve corresponding documents. To reduce the computation cost, the cloud server selects most relevant top-k documents and return them to the data users. The ciphertext-policy attribute based encryption (CP-ABE) technique is introduced to implement fine-grained access control. Meanwhile, the basic CP-ABE is improved to meet the practical need of user attribute updating. Extensive security and performance analysis demonstrates that our proposed scheme is highly efficient and can satisfy the security requirements for fuzzy keyword search over encrypted cloud data.

Over the past several years, to solve the problem of malicious abuse of facial manipulation technology, face manipulation detection technology has obtained considerable attention and achieved remarkable progress. However, most existing methods have very impoverished generalization ability and robustness. In this paper, we propose a novel method for face manipulation detection, which can improve the generalization ability and ro-bustness by bag-of-feature. Specifically, we extend Transformers using bag-of-feature approach to encode inter-patch relation-ships, allowing it to learn forgery features without any additional mask supervision. Extensive experiments demonstrate that our method can outperform competing for state-of-the-art methods on FaceForensics++, Celeb-DF and DeeperForensics-l.0 datasets.

Many of the recent methods for semi-supervised video object segmentation are still far from being applicable for real time applications due to their slow inference speed. Therefore, we explore a propagation based segmentation method in compressed domain to accelerate inference speed in this paper. In particular, we only extract the features of I-frames by traditional deep convolutional neural network and produce the features of P-frames through information flow propagation. In the process of feature propagation, we propose two effective components to enhance the representation ability of simply warped features in terms of appearance and location. Specifically, we propose a residual supplement module to supplement appearance information which is lost in direct warping and a spatial attention module that can mine extra spatial saliency to provide the location information of the specified object. Besides, we propose a metric based decoder module which consists of a feature match module and a multi-level refinement module to transform information from semantic representation to shape segmentation mask. Extensive experiments on several video datasets demonstrate that the proposed method can achieve comparable accuracy while much faster inference speed when compared to the state-of-the-art algorithms.

Video object detection is a challenging problem in computer vision. In this paper, we propose a novel spatial-temporal feature aggregation network to deal with this issue. Specifically, we present a novel instance-level feature aggregation module as complementary to traditional pixel-level feature aggregation, in which we build a new movement estimation module to learn instance movements across frames. Then the Graph Convolutional Networks (GCNs) is applied to obtain temporal relation among instances over frames to implement instance-level feature aggregation. At last, we combine pixel-level and instance-level features by learnable soft weights to make use of their complementary information. Our framework is simple to implement and enables end-to-end training, which achieves state-of-art performance on the ImageNet VID dataset by extensive experiments.

Person Search plays the role of the ultimate destination of person re-identification (re-ID) in real applications. It has many challenges that person re-ID doesn't need to handle, such as mis-detections, false alarms and multi-scale matching. In contrast to previous works, we show that a strong multi-scale person matching system can result in a good person search performance with a common deep object detector (e.g. Faster-RCNN). In this work, we provide a robust person search method called Dynamic Hierarchical Feature Fusion (DHFF) which is based on multi-level feature fusion to tackle with multi-scale matching. In addition, A Multi-Metric loss is proposed to train the model effectively and stably with numerous identities. We evaluate our method on two large person search benchmark data sets: CUHK-SYSU and PRW. Experiments show that the proposed algorithm outperforms other state-of-the-art person search methods.

Crowd counting is a challenging task due to the issues such as scale variation and perspective variation in real crowd scenes. In this paper, we propose a novel Cascaded Residual Density Network (CRDNet) in a coarse-to-fine approach to generate the high-quality density map for crowd counting more accurately. (1) We estimate the residual density maps by multi-scale pyramidal features through cascaded residual density modules. It can improve the quality of density map layer by layer effectively. (2) A novel additional local count loss is presented to refine the accuracy of crowd counting, which reduces the errors of pixel-wise Euclidean loss by restricting the number of people in the local crowd areas. Experiments on two public benchmark datasets show that the proposed method achieves effective improvement compared with the state-of-the-art methods.

Video object segmentation is a challenging task with wide variety of applications. Although recent CNN based methods have achieved great performance, they are far from being applicable for real time applications. In this paper, we propose a propagation based video object segmentation method in compressed domain to accelerate inference speed. We only extract features from I-frames by the traditional deep segmentation network. And the features of P-frames are propagated from I-frames. Apart from feature warping, we propose two effective modules in the process of feature propagation to ensure the representation ability of propagated features in terms of appearance and location. Residual supplement module is used to supplement appearance information lost in warping, and spatial attention module mines accurate spatial saliency prior to highlight the specified object. Compared with recent state-of-the-art algorithms, the proposed method achieves comparable accuracy while much faster inference speed.

Recent approaches have achieved great success on still image object detection. Despite the high accuracy, directly applying image object detectors for video object detection is rather slow. Inspired from the fact that object tracking is much more efficient than object detection, we propose to combine object detection and tracking for fast video object detection. Computational expensive detection network is applied on sparsely arranged key frames, while proposals of non-key frames are obtained through tracking and regression of previous frame's proposals. Assisted with an adaptive key-frame arrangement module, our method can adaptively decide whether to track or to detect based on tracking quality. Extensive experiments show that the proposed method can significantly boost detection speed with a rather small drop in detection accuracy.

Video object segmentation plays an important role in computer vision and has attracted much attention. Although many recent works have removed the fine-tuning process in pursuit of fast inference speed, while achieving high segmentation accuracy, they are still far from being real-time. In this paper, we regard this task as a feature matching problem and propose a prior probability based metric learning (PPML) method for faster inference speed and higher segmentation accuracy. The proposed method consists of two ingredients: a novel template space updating strategy that improves the efficiency of segmentation by avoiding the explosion of data in template space, and a novel feature matching method which applies more potential probability information through integrating the prior of the first frame and the predicted score of previous frames. Experimental results on DAVIS datasets demonstrate that the proposed method reaches the state-of-the-art competitive performance and is more efficient in time consumption.

Detecting and localizing anomalies in surveillance videos is an ongoing challenge. Most existing methods are patch or trajectory-based, which lack semantic understanding of scenes and may split targets into pieces. To handle this problem, this paper proposes a novel and effective algorithm by incorporating deep object detection and tracking with full utilization of spatial and temporal information. We propose a new dynamic image by fusing both appearance and motion information and feed it into object detection network, which can detect and classify objects precisely even in dim and crowd scenes. Based on the detected objects, we develop an effective and scale-insensitive feature, named histogram variance of optical flow angle (HVOFA), together with motion energy to find abnormal motion patterns. In order to further discover missing anomalies and reduce false detected ones, we conduct a post-processing step with abnormal object tracking. The proposed algorithm outperforms state-of-the-art methods on standard benchmarks.

In prevalent two-stage object detectors, ROI pooling or position sensitive ROI pooling (PS ROI pooling) is usually used to extract features of proposal. But ROI pooling or PS ROI pooling ignores the local or global information of proposal respectively. It motivates us to design a kind of pooling method which can capture both global information and local information of proposal. In this paper, we propose pyramid sub-region sensitive network (PSSNet) for object detection which uses pyramid sub-region sensitive ROI pooling (PSS ROI pooling) to extract features of proposal. The PSS ROI pooling can capture the global and coarse-to-fine local information of proposal. Then, we explore different weighting strategies to utilize the PSS ROI features using self-adapting learning factors. Our PSSNet achieves the state-of-art result on PASCAL VOC 2007, PASCAL VOC 2012 datasets and competitive result on MS COCO dataset.

How to effectively utilize the temporal information in video has been an important problem in visual tracking. In this paper, we try to address this problem from two aspects. At first, we use optical flow to take advantage of the inter-frame information, when we obtain the position of the last frame, we predict the approximate location in present frame by calculating the optical flow and generate samples around it. Secondly, we use the tracked patches as reference to identify the target better. We designed a Siamese network which take image pairs consisted of exemplars and samples as inputs, the objective function is also modified by adding a priori probability. Further, we conducted experiments on the OTB benchmark and achieve competitive result both on accuracy and robustness, which demonstrate the effectiveness of our proposed algorithm.

Anomaly detection in crowded scenes is an important issue in computer vision. In this paper, we propose a novel framework which takes both appearance and motion characteristics into consideration to detect anomalies. A new foreground object localization method is put forward at first to extract object proposals. For motion representation, we present a novel local motion based descriptor named as Spatially Localized Multi-scale Histogram of Optical Flow (SL-MHOF) to capture the local motion statistics for each object proposal. For appearance representation, we apply convolutional neural networks (CNNs) because of their high visual discriminative capacities. These two features are then fed into Gaussian Mixture Model (GMM) Classifiers respectively to generate anomaly scores, which are fused with a softmax function to produce the final anomaly detection results. Experiments on UCSD datasets indicate the effectiveness of our proposed approach, which achieves state-of-the-art performance.

A variety of methods have been proposed for object level saliency detection, which is useful for many content-based computer vision applications. Unlike most previous work that integrate multiple low level cues to compute the saliency map, this paper presents a novel hierarchical optimization model. First, we compute a rough saliency map using HS method, and then, boundary and foreground seeds are extracted from it, which guide the computation of the background and foreground saliency maps, respectively. Next, a combination of the two saliency maps is performed. In the end, Cellular Automata is applied to optimize it and a threshold method is taken to make the optimized saliency map closer to the ground truth. Experiments on three large datasets demonstrate that the proposed method performs favorably against the state-of-the-art methods in terms of F-measures and MAEs.

The technology of specific target detection and recognition in Synthetic Aperture Radar (SAR) image is one of the most important issues especially in the area of remote sensing observation. Aiming at ship detection in complex scenario, this paper presents a universal framework and a novel method called Speed-up Seed point OTSU (SSOTSU) based on OTSU and invoked in the framework. Different from the classic OTSU method, SSOTSU obtains seed points and compute threshold in specific area around every seed point. The experiment results demonstrate that our method can be implemented to detect ships under complicated scenario of both SAR images and optical images fast and obtain high accuracy in detection.

An efficient three-dimensional target height extraction method via high squint airborne synthetic aperture radar(SAR) is introduced in this paper. Here we obtain two SAR images of the interested terrain from two parallel flight tracks, utilizing the geometry to calculate the height of the target. Due to the high squint angle, the spectrum of the range-azimuth is tilted. Therefore, the actual azimuth bandwidth is much lager than its effective azimuth bandwidth and a larger pulse repetition frequency(PRF) is needed to avoid azimuth ambiguities. This will increase the amount of calculation. A linear range cell migration correction(RCMC) and azimuth demodulation are taken in advance to correct the spectrum and move it to the baseband. Raw data of high squint airborne SAR in S-band is simulated and the imaging result is analyzed. Simulation results show that the target height can be acquired, and also confirm the validity and efficiency of the algorithm.

For online multi-object tracking, the appearance model of a target is essential. It has to be consistent within the track of a target and be discriminative between tracks of different targets. To satisfy these requirements, a new two-stage frame-by-frame method that takes advantage of both global and local features is proposed. In this paper, first, targets are tracked with their global feature that is more consistent than local features. Then, a discriminative local feature-MSER (maximally stable extremal regions)-based color histogram is proposed and used for targets tracking. Experiments on several public datasets shows improvement in performance over other state-of-the-art methods.

A novel approach for imaging fast ground moving targets with fast cross and along track velocities is presented in this paper, in which their moving parameters are estimated by using single-antenna synthetic aperture radar (SAR). First, the way of phase extraction is proposed. Next, fractional Fourier transform is applied to estimate the Doppler parameters for the extracted phase. According to the parameters, a matched filter is generated to correct simultaneously range walk and curvature. Finally, after azimuth compression, a focused image is obtained. By considering the general definition of the Doppler modulation rate and obtaining the shortest distance from the focused image, the estimation of fast along track velocity is precise. Simulation results validate the performance of the proposed approach.

The credibility of digital images is decreasing with the fast development of easy-to-use image manipulation tools such as Photoshop and Picasso. Although good forged images are deceptive to human eyes, the manipulation process often leaves some statistical traces in the forged images. Very often, the forged images are rotated partly or as a whole. If we can identify image rotation or even determine image rotation angle, the authenticity of images could be verified. In this paper, we propose an image rotation angle estimation algorithm based on properties of 2-D DFT of pixel variance. This algorithm is a blind one because it works in absence of any prior information such as digital watermark. We show the efficacy of this approach in our experiment.

In this paper, a redundancy based cipher-only attack is proposed to break row-column shuffle based image encryption algorithms, which are considered to be safe under cipher-only attack before although it is well known that they are fragile under known-plaintext attack. This attack is carried out on the shuffle operations itself by analyzing the redundancy remained in cipher image, and doesn't care how the shuffle tables are generated. So, no matter how the shuffling tables are generated, this attack is valid. Experimental results show high quality deciphered images from one single cipher image, and that demonstrate the validity of our attack method. This attack method is also a potential threat to shuffle-scramble combined encryptions.

Protocol plays a profound role among networked computers in security issues. With the development of computer network engineering, protocol has become increasingly intricate in both data format and interaction behavior, which means that more potential defects exist in protocol software implementations. These factors make protocol vulnerable to malicious attacks and raise the security requirements to an ever high level. After over ten-year progress, however, the vulnerability testing methods have not been unified to an agreement. Especially, the problems in automated test cases generation remain to be solved. This paper proposes a novel brute force vulnerability testing technique, generating test data by mutating captured protocol messages. And to formalize the perturbing process, regular expression is introduced into the approach for constructing test case templates. In addition, a multi-protocol test tool called PVD is developed to implement the test system architecture. Finally, the authors carry on a complete vulnerability testing campaign on Asterisk 1.4 SIP (Session Initiation Protocol) server, as the result, finding a number of protocol defects and achieving fairly efficient test results.

Copy-move tampering is a common type of image synthesizing, where a part of an image is copied and pasted to another place to add or remove an object. In this paper, an efficient algorithm based on the Fourier-Mellin Transform is proposed with features extracted along radius direction. Also, to reduce computational cost, a link processing is introduced instead of hash value counting in the counting bloom filters. Moreover, a vector erosion filter is designed to cluster distance vectors, which is usually achieved through vector counters in existed copy-move detection algorithms. Our experimental results show that the improved algorithm can detect duplicated regions efficiently. Especially, the improved algorithm is robust to duplicated regions of large rotation angle, whereas existed algorithms can only treat slight rotation.

Digital image and video forensics is to detect the authenticity of digital images/videos. So far, existing algorithms are designed by exploring one or several special features, which usually result in limited performance and applicability. With the perspective of entire procedure including image acquisition and image processing, a theory of general blind image forensics is proposed in this paper. Then a new blind image forensic method is designed based on this theory to identify camera source and processing history of cropped compressed digital images. In this method, tensor decomposition analysis is applied to extract features of nonlinear operations, which come from both algorithms embedded within camera and operations done by post-software. Then, the Support Vector Machine is utilized to classify whether the target image is captured by the claimed camera and underwent the declared processing history. Experimental results show that this method has high detection accuracy, which demonstrated that our theory is correct.

A DCT domain image encryption scheme based on chaotic shuffling table is proposed, in which the shuffling tables are generated by several logistic maps. This scheme is robust to normal image processing, such as noising, smoothing, compressing, and even print-scan processing. In this scheme, key space is easy to be adjusted by choosing the number of logistic maps. The encrypted image is still highly compressible since shuffling operation is confined in DCT equal-frequency coefficients. What is more, a random number, called nonce, is introduced to initialize initial values of logistic maps, which ensures that the proposed scheme can resist chosen-plain-text cryptanalysis.

An image encryption algorithm based on chaotic circular bit shift is proposed recently. This paper analyses the security of this algorithm and point out that the key space is not as large as they alleged and the algorithm can not resist chosen-plaintext attack or difference attack. The amount of chosen-plaintexts to carry out an attack is very few. This paper also introduces two methods to improve its security by changing chaotic sequences generators, altering orders of permutation and substitution, and applying feedback link mode. The improved algorithm has variable key space and has very good avalanche effect to resist chosen-plaintext attacks, chosen-ciphertext attacks, or difference attacks. The computation cost of improved algorithm is very low.

Nowadays, digital images can be easily modified by using software. In this paper, a new blind approach is proposed to detect copy-paste trail in a doctored JPEG image, i.e., to check whether a copied area came from the same image or not. When a copy-paste procedure is done on an image, especially adding or hiding an object, the block artifact grid contained in the copy-pasted slice is moved together. Since a slice must be placed properly in the target image to avoid obvious vision flaw, the grid in the slice mismatches to the original grid in the target image normally. Our approach utilizes the mismatch information of block artifact grid as a clue of copy-paste forgery. Experiment results demonstrate the efficiency of the proposed approach.