As semantic communication (SemCom) attracts growing attention as a novel communication paradigm, ensuring the security of transmitted semantic information over open wireless channels has become a critical issue. However, traditional encryption methods often introduce significant additional communication overhead to maintain stability, and conventional learning-based secure SemCom methods typically rely on a channel capacity advantage for the legitimate receiver, which is challenging to guarantee in real-world scenarios. In this paper, we propose a coding-enhanced jamming method that eliminates the need to transmit a secret key by utilizing shared knowledge–potentially part of the training set of the SemCom system–between the legitimate receiver and the transmitter. Specifically, we leverage the shared private knowledge base to generate a set of private digital codebooks in advance using neural network (NN)-based encoders. For each transmission, we encode the transmitted data into digital sequence Y1and associate Y1with a sequence randomly picked from the private codebook, denoted as Y2, through superposition coding. Here, Y1serves as the outer code and Y2as the inner code. By optimizing the power allocation between the inner and outer codes, the legitimate receiver can reconstruct the transmitted data using successive decoding with the index of Y2shared, while the eavesdropper’s decoding performance is severely degraded, potentially to the point of random guessing. Experimental results demonstrate that our method achieves security comparable to state-of-the-art approaches while significantly improving the reconstruction performance of the legitimate receiver by more than 1 dB across varying channel signal-to-noise ratios (SNRs) and compression ratios.

Asymmetric numeral systems (ANS) is a widely used entropy coding method in commercial compressors due to its high performance. Joint compression and encryption techniques can offer reliability and cost-effectiveness for secure Big Data storage. However, existing joint compression-encryption schemes for ANS coding often suffer from either increased storage space requirements or limited security. To address these issues, this paper proposes two ANS-based joint compression-encryption algorithms that provide considerable security with almost no compression loss. The first scheme, based on interval swapping, employs a cryptographically secure ChaCha20 generator to perturb the order of contiguous intervals, thereby introducing controlled randomness into the encoding process. The second scheme, based on interval splitting, discards the conventional assumption of representing each symbol with a single contiguous interval, instead assigning multiple sub-intervals to enhance both security and flexibility. In addition, a sequence of output permutations is applied to further strengthen resistance against attacks. Experimental results show that the proposed methods reduce compression loss by approximately 3.83% compared with existing schemes, while the interval swapping scheme achieves a 46.9% reduction in time cost. Security analysis confirms that the enlarged key space significantly increases robustness against brute-force attacks. These results demonstrate that the proposed approaches effectively balance compression efficiency and encryption strength, offering a lightweight and secure solution for Big Data storage.

This paper addresses the challenge of achieving security in semantic communication (SemCom) over a wiretap channel, where a legitimate receiver coexists with an eavesdropper experiencing a poorer channel condition. Despite previous efforts to secure SemCom against eavesdroppers, guarantee of approximately zero information leakage remains an open issue. In this work, we propose a secure SemCom approach based on superposition code, aiming to provide quantifiable and controllable security for digital SemCom systems. The proposed method employs a double-layered constellation map, where semantic information is associated with satellite constellation points and cloud center constellation points are randomly selected. By carefully allocating power between these two layers of constellation, we ensure that the symbol error probability (SEP) of the eavesdropper when decoding satellite constellation points is nearly equivalent to random guessing, while maintaining a low SEP for the legitimate receiver to successfully decode the semantic information. Simulation results demonstrate that the peak signal-to-noise ratio (PSNR) and mean squared error (MSE) of the eavesdropper's reconstructed data, under the proposed method, can range from decoding Gaussian-distributed random noise to approaching the variance of the data. This validates the effectiveness of our method in nearly achieving the experimental upper bound of security for digital SemCom systems when both eavesdroppers and legitimate users utilize identical decoding schemes. Furthermore, the proposed method consistently outperforms benchmark techniques, showcasing superior data security and robustness against eavesdropping. The implementation code is publicly available at:https://github.com/1weixuanchen/A-Superposition-Code-Based-Semantic-Communication.

In this paper, we propose a new decoding algorithm for extremely skewed distribution, so that it can omit reading unnecessary bits and thus improve decoding performance. In particular, the proposed method does not require additional space to store the encoded stream. Specifically, we first reorder the compressed bit sequence as in [1], so that to support direct access without extra space. Then, we propose a labeling method to generate a temporary label corresponding to the encountered block, in order to indicate whether the length of the codeword stored in that block is determined. If it is determined, we can identify where to read the necessary bits for decoding the desired symbol. Otherwise, we read bits from the later blocks to update the labels until the codeword lengths are determined.

Range coding is a type of entropy coding widely used in modern data compressors. However, its compression and decompression processes involve multiple range adjustments, and the bitstream can only be read sequentially during decoding, resulting in quite high latency. In addition, existing input-interleaved fast implementations demand additional computational and memory overhead for the post-compression byte-swizzling step, which leads to increased compression time. In this paper, we propose a parallel range coding method that employs multiple encoders and decoders without the need for the swizzling step. It is achieved by designing a sliding window mechanism to interleave the outputs of multiple encoders, so that the positions of each encoder's outputs in the bitstream follow a predictable and ordered pattern. This design reduces encoding latency and enables each decoder to pre-locate the data it needs to read during decoding, thereby improving both compression and decompression performance. The simulation results indicate that compared to the traditional range coding and existing multi-way input-interleaved implementations (which require a large amount of memory overhead during encoding), our proposal achieves an average throughput increase of 48.03%/81.08% and 74.01%/9.14% during encoding/decoding, respectively, with almost the same compression ratios.

Digital media's rapid expansion has made copying, sharing, and tampering with images trivial, posing serious challenges for copyright protection and forensic analysis. Current deep learning-based watermarking techniques rely on irreversible embedding or heavy cryptographic checks, leaving them vulnerable to noise and attacks and undermining their effectiveness. To overcome these limitations, we propose an end-toend image watermarking framework by integrating three key components: a reversible linear payload transform to stabilize bit embedding, a neural network to fuse image and payload features, and an authenticity verification module to ensure reliable tamper detection. Specifically, a binary watermark is first projected into a highdimensional continuous vector using a session-specific matrix, achieving invertible obfuscation of the payload to enhance security. This vector is then fused with multiscale image features via a Swin-Tiny Transformer, and decoder reconstructs image and watermark, ensuring high visual quality. Finally, a shallow belief-propagation style neural decoder validates the extracted payload by outputting a distance metric to the nearest valid codeword; extraction is accepted as authentic only if this distance falls below a preset threshold, indicating a legitimate payload. Additionally, a compact SimHash fingerprint is employed for a fast supplementary integrity check. Experiments on the Mini-ImageNet dataset demonstrate that the proposed framework achieves a peak signal-to-noise ratio (PSNR) of 42.1 dB and over 95% of the authentication accuracy, while reducing an adversary's authentication success rate to nearly zero when the secret transform matrix is unknown. These results demonstrate marked improvements in imperceptibility, robustness, and security over existing methods.

We introduce the hybrid ageing problem in gossip networks, where each node has different ageing processes. This generalization brings two new issues: i) the traditional subset recursion method in [1] fails; ii) the existence of stationary average age penalty needs to be re-examined. To resolve issue i) and ii), we leverage a node-by-node SHSs analysis by introducing splitting Poisson processes to evaluate the average age penalty. We first analyze the hybrid ageing problem in two types of line networks, i.e., one-way and two-way gossip lines. In one-way gossip lines, we derive the closed-form expression of average age penalty in two different cases, where the ageing process of each node can be ordered or disordered (Definition 1). The closedform expressions of average age penalty are also derived in the two-way gossip line. Moreover, we show that the growth rate of age penalty is bounded by the arrival rates between gossip nodes in the one-way line to ensure the existence of average age penalty.

In this paper, a novel learning-based Wyner-Ziv coding framework is considered under a distributed image transmission scenario, where the correlated source is only available at the receiver. Unlike other learnable frameworks, our approach demonstrates robustness to non-stationary source correlation, where the overlapping information between image pairs varies. Specifically, we first model the affine relationship between correlated images and leverage this model for learnable mask generation and rate-adaptive joint source-channel coding. Moreover, we also provide a warping-prediction network to remove the distortion from channel interference and affine transform. Intuitively, the observed performance improvement is largely due to focusing on the simple geometric relationship, rather than the complex joint distribution between the sources. Numerical results show that our framework achieves a 1.5 dB gain in PSNR and a 0.2 improvement in MS-SSIM, along with a significant superiority in perceptual metric, compared to state-of-the-art methods when applied to real-world samples with non-stationary correlations.

We consider multi-user semantic communications over broadcast channels. While most existing works consider that each receiver requires either the same or independent semantic information, this paper explores the scenario where the semantic information desired by different receivers is different but correlated. In particular, we investigate semantic communications over Gaussian broadcast channels where the transmitter has a common observable source but the receivers wish to recover hierarchical semantic information in adaptation to their channel conditions. Inspired by the capacity achieving property of superposition coding, we propose a deep learning-based superposition coded modulation (DeepSCM) scheme. Specifically, the hierarchical semantic information is first extracted and encoded into basic and enhanced feature vectors. A linear minimum mean square error (LMMSE) decorrelator is then developed to obtain a refinement from the enhanced features that is uncorrelated with the basic features. Finally, the basic features and their refinement are superposed for broadcasting after probabilistic modulation. Extensive experiments are conducted for two-receiver image semantic broadcasting with coarse and fine classification as hierarchical semantic tasks. DeepSCM outperforms the benchmarking coded-modulation scheme without a superposition structure as well as the classic separate source-channel coding baselines, especially with large channel disparity and high order modulation. It also approaches the performance upperbound as if there were only one receiver.

We consider a general point-to-point fading multiple-input multiple-output (MIMO) Gaussian channel. The channel suffers block fading and is with finite channel states, among which there is no degraded order due to the multi-antenna deployment. To guarantee reliable transmissions under the arbitrary unpredictable fading state, we generalize the layered broadcast approach in the channel by inducing the general rate splitting scheme. It assigns the specific sub-message layers for every possible state set and splits the transmission rate by allocating power to each layer. Under this scheme, a generalized broadcast approach is designed to be suitable for multi-antenna transmission. The maximum average rate subject to a transmit power constraint can be determined by a non-convex optimization problem over power allocation and rate tuple. We propose an iterative algorithm based on certain properties that the optimal solution would meet under some necessary conditions. It can output one local optimum for the optimization and thus assist in obtaining a scheme with a decent performance.

This paper considers the joint compression of a pair of correlated sources, where the encoder is allowed to access only one of the sources. The objective is to recover both sources under separate distortion constraints for each source while minimizing the rate. This problem generalizes the indirect lossy source coding problem by also requiring the recovery of the observed source. In this paper, we aim to study the nonasymptotic and second-order asymptotic properties of this problem. Specifically, we begin by deriving nonasymptotic achievability and converse bounds valid for general sources and distortion measures. The source dispersion (Gaussian approximation) is then determined through asymptotic analysis of the nonasymptotic bounds. We further examine the case of erased fair coin flips (EFCF) and provide its specific nonasymptotic achievability and converse bounds. Numerical results under the EFCF case demonstrate that our second-order asymptotic approximation closely approximates the optimum rate at appropriately large blocklengths.

For deep learning-enabled semantic communication, existing privacy protection methods only take into account the presence of eavesdropper while ignoring malicious receiver aiming to detect confidential information. Only informationtheoretical security can transmitter defend against malicious receiver. However, private information are always entangled with pragmatic information in feature space, which leads global perturbation to degrade communication performance. To handle these difficulties, in this paper a privacy preserving semantic communication system is proposed. Different from traditional paradigm, a novel privacy preserving semantic encoder is designed to realize targeted privacy protection while remaining useful information unaffected. Within proposed privacy preserving semantic encoder, feature decoupling module aims to disentangle semantic information by learning two sets of basis vectors which can express private and pragmatic information of data, respectively. Accordingly differential privacy mechanism is employed to provide information-theoretical security. Experimental results demonstrate that proposed method not only achieves better communication performance in both data recovery and pragmatic task, but also more effectively degrades the accuracy of malicious receiver to infer sensitive information than global perturbation does.

Semantic communications have emerged as a new paradigm for improving communication efficiency by transmitting the semantic information of a source message that is most relevant to a desired task at the receiver. Most existing approaches typically utilize neural networks (NNs) to design end-to-end semantic communication systems, where NN-based semantic encoders output continuously distributed signals to be sent directly to the channel in an analog fashion. In this work, we propose a joint coding-modulation (JCM) framework for digital semantic communications by using variational autoencoder (VAE). Our approach learns the transition probability from source data to discrete constellation symbols, thereby avoiding the non-differentiability problem of digital modulation. Meanwhile, by jointly designing the coding and modulation process together, we can match the obtained modulation strategy with the operating channel condition. We also derive a matching loss function with information-theoretic meaning for end-to-end training. Experiments on image semantic communication validate the superiority of our proposed JCM framework over the state-of-the-art quantization-based digital semantic coding-modulation methods across a wide range of channel conditions, transmission rates, and modulation orders. Furthermore, its performance gap to analog semantic communication reduces as the modulation order increases while enjoying the hardware implementation convenience.

Reversible data hiding (RDH) has been extensively studied in the field of multimedia security. Embedding capacity is an important metric for RDH performance evaluation. However, the embedding capacity of existing methods for independent and identically distributed (i.i.d.) gray-scale signals is still not good enough. In this paper, we propose a high-capacity RDH code construction method that employs asymmetric numeral systems (ANS) coding as the underlying coding framework. Based on the proposed framework, two RDH methods are presented. First, we propose a static RDH method that takes the constant host probability mass function (PMF) as input parameters and offers high embedding performance. Then, we give a dynamic RDH method that can eliminate the need for transmitting the host PMF in advance by designing a reversible dynamic probability calculator. The simulation results on discrete normally distributed signals demonstrate that the performance of the proposed static method is very close to the expected rate-distortion bound, and the proposed dynamic method can achieve satisfactory embedding capacity without prior knowledge of host PMF at the cost of slightly sacrificing steganographic data quality. Moreover, the experimental results on gray-scale images show that the proposed static method provides higher peak signal-to-noise ratio (PSNR) values and larger embedding capacities than some state-of-the-art methods, e.g., the embedding capacity of image Lena is as high as 3.571 bits per pixel.

This paper investigates digital semantic communications over broadcast channels, where the transmitter has a common observable source to transmit, but the receivers desire to recover different levels of semantic information in adaptation to their respective channel conditions. Inspired by the capacity-achieving superposition coding structure for degraded broadcast channel, we propose a superposition coded modulation (SCM) scheme for semantic information transmission over a two-receiver Gaussian broadcast channel. In specific, the transmitter consists of two separate neural network (NN)-based semantic encoders, one NN-based linear minimum mean square error (LMMSE) decorrelator, and one superposition-based digital modulator. The SCM scheme enables the receiver with lower signal-to-noise ratio (SNR) to decode basic semantic information while the receiver with larger SNR can decode enhanced semantic information. Experiments are conducted on image transmission with coarse and fine classifications as semantics. Results show that our proposed SCM scheme outperforms the basic coded-modulation scheme without a superposition structure for both receivers, especially when channel conditions of the two receivers differ significantly. It also approaches the performance upperbound as if there were only one receiver.

User-tag profiling is an effective way of mining user attributes in modern recommender systems. However, prior researches fail to extract users' precise preferences for tags in the items due to their incomplete feature-input patterns. To convert user-item interactions to user-tag preferences, we propose a novel feature-based framework named Coalition Tag Multi-View Mapping (CTMVM), which identifies and investigates two special features, Coalition Feature and Privileged Feature. The former indicates decisive tags in each click where relationships between tags in one item are treated as a coalition game. The latter represents highly informative features that only occur during training. For the coalition feature, we adopt Shapley Value based Empowerment (SVE) to model the tags in items with a game-theoretic paradigm and charge the network to straight master user preferences for essential tags. For the privileged feature, we present Privileged Knowledge Mapping (PKM) to explicitly distill privileged feature knowledge for each tag into one single embedding, which assists the model in predicting user-tag preferences at a more fine-grained level. However, the barren capacity of single embeddings limits the diverse relations between each tag and different privileged features. Therefore, we further propose Adaptive Multi-View Mapping (AMVM) model to enhance effect by handling multiple mapping networks. Excellent offline experiment results on two public and one private datasets show the out-standing performance of CTMVM. After the deployment on Alibaba large-scale recommendation systems, CTMVM achieved improvement by 10.81% and 6.74% in terms of Theme-CTR and Item-CTR respectively, which validates the effectiveness of taking in the two particular features for training.

Existing deep learning-enabled semantic communication systems often rely on shared background knowledge between the transmitter and receiver that includes empirical data and their associated semantic information. In practice, the semantic information is defined by the pragmatic task of the receiver and cannot be known to the transmitter. The actual observable data at the transmitter can also have non-identical distribution with the empirical data in the shared background knowledge library. To address these practical issues, this paper proposes a new neural network-based semantic communication system for image transmission, where the task is unaware at the transmitter and the data environment is dynamic. The system consists of two main parts, namely the semantic coding (SC) network and the data adaptation (DA) network. The SC network learns how to extract and transmit the semantic information using a receiver-leading training process. By using the domain adaptation technique from transfer learning, the DA network learns how to convert the data observed into a similar form of the empirical data that the SC network can process without re-training. Numerical experiments show that the proposed method can be adaptive to observable datasets while keeping high performance in terms of both data recovery and task execution.

This paper considers the massive random access problem in multiple-input multiple-output (MIMO) quasi-static Rayleigh fading channels. Specifically, we derive achievability and converse bounds on the minimum energy-per-bit required for each active user to transmit$J$bits with blocklength$n$, power$P$, and$L$receive antennas under a per-user probability of error (PUPE) constraint, in the cases with and without a priori channel state information at the receiver (CSIR and no-CSI). In the case of no-CSI, we consider both the settings with and without the knowledge of the number$K_{a}$of active users at the receiver. Numerical evaluation shows that the gap between achievability and converse bounds is less than 2.5 dB for the CSIR case and less than 4 dB for the no-CSI case in most considered regimes. Under the condition that the distribution of$K_{a}$is known in advance, the uncertainty of the exact value of$K_{a}$entails only a small penalty in terms of energy efficiency. Our results show the significance of MIMO for the massive random access problem. As an example, we show that the spectral efficiency grows approximately linearly with the number of receive antennas in the case of CSIR, whereas the growth rate decreases in the case of no-CSI. Moreover, in the case of no-CSI, we demonstrate the suboptimality of the pilot-assisted scheme, especially when the number of active users is large. Building on non-asymptotic results, assuming all users are active and$J=\Theta (1)$, we obtain scaling laws of the number of supported users as follows: when$L = \Theta \left ({n^{2}}\right)$and$P=\Theta \left ({\frac {1}{n^{2}}}\right)$, one can reliably serve$K = \mathcal {O}(n^{2})$users in the case of no-CSI; under mild conditions in the case of CSIR, the PUPE requirement is satisfied if and only if$\frac {nL\ln KP}{K}=\Omega \left ({1}\right)$.

In this paper, the analysis of excess distortion exponent for joint source-channel coding (JSCC) in semantic-aware communication systems is presented. By introducing an unobservable semantic source, we extend the classical results by Csiszar to semantic-aware communication systems. Both upper and lower bounds of the exponent for the discrete memoryless source-channel pair are established. Moreover, an extended achievable bound of the excess distortion exponent for MIMO systems is derived. Further analysis explores how the block fading and numbers of antennas influence the exponent of semantic-aware MIMO systems. Our results offer some theoretical bounds of error decay performance and can be used to guide future semantic communications with joint source-channel coding scheme.

We consider a general point-to-point fading multiple-input multiple-output (MIMO) Gaussian channel. The channel suffers block fading and with finite channel states, among which there is no degraded order on state information due to multi-antenna deployment. To guarantee reliable transmissions under arbitrary unpredictable fading states, we generalize the layered broadcast approach in the channel by inducing a rate splitting scheme. It assigns a specific sub-message layer for every possible state set and splits the transmission rate by allocating power to each layer. Under this scheme, a generalized broadcast approach is designed to be suitable for multi-antenna transmission. The maximum average rate under total power constraint can be characterized by an optimization problem. Numerical examples are provided to show the optimality of our transmission scheme within degradedness among different channel state information. Meanwhile, such generalization can also provide a decent performance under the general non-degraded case.

This paper studies the secure source coding for distributed function computation with a functional privacy constraint. In particular, two distributed encoders, named Alice and Bob, observe two correlated sources and independently compress and transmit their observations to a fusion center who wants to compute a function of the two sources. A passive eavesdropper named Eve, with access to the side information, is able to listen the link between Alice and the fusion center. Two privacy constraints are considered. The first one is a functional privacy constraint for Eve, who is interested in a given function of the two sources rather than original sources. The second requirement is that the fusion center is not allowed to learn too much information about the original sources. For the proposed problem, an inner bound on the achievable rate-distortion-leakage region is characterized for the discrete memoryless setting. When the function of interest at Eve degenerates to the source X and the fusion center has access to uncoded source Y , our inner bound is tight.

A new source model, which consists of an intrinsic state part and an extrinsic observation part, is proposed and its information-theoretic characterization, namely its rate-distortion function, is defined and analyzed. Such a source model is motivated by the recent surge of interest in the semantic aspect of information: the intrinsic state corresponds to the semantic feature of the source, which in general is not observable but can only be inferred from the extrinsic observation. There are two distortion measures, one between the intrinsic state and its reproduction, and the other between the extrinsic observation and its reproduction. Under a given code rate, the tradeoff between these two distortion measures is characterized by the rate-distortion function, which is solved via the indirect rate-distortion theory and is termed the semantic rate-distortion function of the source. As an application of the general model and its analysis, the case of Gaussian extrinsic observation is studied, assuming a linear relationship between the intrinsic state and the extrinsic observation, under a quadratic distortion structure. The semantic rate-distortion function is shown to be the solution of a convex programming problem with respect to an error covariance matrix, and a reverse water-filling type of solution is provided when the model further satisfies a diagonalizability condition.

Caching is a technique to reduce the communication load in peak hours by prefetching contents during off-peak hours. An information theoretic framework for coded caching was introduced by Maddah-Ali and Niesen in a recent work, where it was shown that significant improvement can be obtained compared to uncoded caching. Considerable efforts have been devoted to identify the precise information theoretic fundamental limits of the coded caching systems, however the difficulty of this task has also become clear. One of the reasons for this difficulty is that the original coded caching setting allows all possible multiple demand types during delivery, which in fact introduces tension in the coding strategy. In this paper, we seek to develop a better understanding of the fundamental limits of coded caching by investigating systems with certain demand type restrictions. We first consider the canonical three-user three-file system, and show that, contrary to popular beliefs, the worst demand type is not the one in which all three files are requested. Motivated by these findings, we focus on coded caching systems where every file must be requested by at least one user. A novel coding scheme is proposed, which can provide new operating points that are not covered by any previously known schemes.

Coded distributed computing (CDC) can alleviate the communication load in distributed computing systems by leveraging coding opportunities via redundant computation. While the optimal computation-communication tradeoff has been well studied for homogeneous systems, it remains largely unknown for heterogeneous systems where workers have different computation capabilities. This paper characterizes the upper and lower bounds of the optimal communication load as two linear programming problems for a general heterogeneous CDC system using the MapReduce framework. Our achievable scheme first designs a parametric data shuffling strategy for any given mapping strategy, and then jointly optimizes the mapping strategy and the data shuffling strategy to obtain the upper bound. The parametric data shuffling strategy allows adjusting the size of the multicast message intended for each worker set, so that it can largely decrease the number of unicast messages and hence increase the communication efficiency. Numerical results show that our achievable communication load is lower than those achieved in existing works. Our lower bound is established by unifying an improved cut-set bound and a peeling method. The obtained upper and lower bounds degenerate to the existing result in homogeneous systems, and coincide with each other when the system is approximately homogeneous or grouped homogeneous.

Although Shannon theory states that it is asymptotically optimal to separate the source and channel coding as two independent processes, in many practical communication scenarios this decomposition is limited by the finite bit-length and computational power for decoding. Recently, neural joint source-channel coding (NECST) (Choi et al. 2018) is proposed to sidestep this problem. While it leverages the advancements of amortized inference and deep learning (Kingma and Welling 2013; Grover and Ermon 2018) to improve the encoding and decoding process, it still cannot always achieve compelling results in terms of compression and error correction performance due to the limited robustness of its learned coding networks. In this paper, motivated by the inherent connections between neural joint source-channel coding and discrete representation learning, we propose a novel regularization method called Infomax Adversarial-Bit-Flip (IABF) to improve the stability and robustness of the neural joint source-channel coding scheme. More specifically, on the encoder side, we propose to explicitly maximize the mutual information between the codeword and data; while on the decoder side, the amortized reconstruction is regularized within an adversarial framework. Extensive experiments conducted on various real-world datasets evidence that our IABF can achieve state-of-the-art performances on both compression and error correction benchmarks and outperform the baselines by a significant margin.

Domain adaptation aims to leverage the supervision signal of source domain to obtain an accurate model for target domain, where the labels are not available. To leverage and adapt the label information from source domain, most existing methods employ a feature extracting function and match the marginal distributions of source and target domains in a shared feature space. In this paper, from the perspective of information theory, we show that representation matching is actually an insufficient constraint on the feature space for obtaining a model with good generalization performance in target domain. We then propose variational bottleneck domain adaptation (VBDA), a new domain adaptation method which improves feature transferability by explicitly enforcing the feature extractor to ignore the task-irrelevant factors and focus on the information that is essential to the task of interest for both source and target domains. Extensive experimental results demonstrate that VBDA significantly outperforms state-of-the-art methods across three domain adaptation benchmark datasets.

In this paper, we propose a new image classifier based on the incorporation of the nearest neighbor algorithm and the activation space of convolutional neural network. The classifier has been successfully implemented on some state-of-the-art models and further improve their performance. The main technique tool we use is convex hull based classification and its acceleration. We find several phenomena which we believe are of both theoretical and application interest: 1) in several cases, the new classifier outperforms original CNN by reaching higher accuracy; 2) the classifier can work more efficiently by combining with sampling strategy; 3) centroid of each convex hull shows surprising ability in classification. Most of the work have strong geometric meanings, which helps us have a new understanding about convolutional layers.

Caching is a technique to reduce the communication load in peak hours by prefetching contents during off-peak hours. Recently Maddah-Ali and Niesen introduced an information theoretic framework for coded caching, and showed that significant improvement can be obtained compared to uncoded caching. Considerable efforts have been devoted to identify the precise information theoretic fundamental limit of such systems, however the difficulty of this task has also become clear. One of the reasons for this difficulty is that the original coded caching setting allows multiple demand types during delivery, which in fact introduces tension in the coding strategy to accommodate all of them. In this paper, we seek to develop a better understanding of the fundamental limit of coded caching by investigating single demand type systems. We first show that in the canonical three-user three-file systems, such single demand type systems already provide important insights. Motivated by these findings, we focus on systems where the number of users and the number of files are the same, and the demand type is when all files are being requested. A novel coding scheme is proposed, which provides several optimal memory-transmission operating points. Outer bounds for this class of systems are also considered, and their relation with existing bounds is discussed.

The problem of multilevel diversity coding with secure regeneration is revisited. Under the assumption that the eavesdropper can access the repair data for all compromised storage nodes, Shao el al. provided a precise characterization of the minimum-bandwidth-regeneration (MBR) point of the achievable normalized storage-capacity repair-bandwidth tradeoff region. In this paper, it is shown that the MBR point of the achievable normalized storage-capacity repair-bandwidth tradeoff region remains the same even if we assume that the eavesdropper can access the repair data for some compromised storage nodes (type II compromised nodes) but only the data contents of the remaining compromised nodes (type I compromised nodes), as long as the number of type I compromised nodes is no greater than that of type II compromised nodes.

We consider the {n, k, d, l) secure exact-repair regenerating code problem, which generalizes the {n, k, d) exact-repair regenerating code problem with the additional constraint that the stored file needs to be kept information-theoretically secure against an eavesdropper, who can access the data transmitted to regenerate a total of l different failed nodes. For all known results on this problem, the achievable tradeoff regions between the normalized storage capacity and repair bandwidth have a single corner point, achieved by a scheme proposed by Shah, Rashmi and Kumar (the SRK point). Since the achievable tradeoff regions of the exact-repair regenerating code problem without any secrecy constraints are known to have multiple corner points in general, these existing results suggest a phase-change-like behavior, i.e., enforcing a secrecy constraint (l ≥ 1) immediately reduces the tradeoff region to one with a single corner point. In this work, we first show that when the secrecy parameter l is sufficiently large, the SRK point is indeed the only corner point of the tradeoff region. However, when £ is small, we show that the tradeoff region can in fact have multiple corner points. In particular, we establish a precise characterization of the tradeoff region for the (7, 6, 6,1) problem, which has exactly two corner points. Thus, a smooth transition, instead of a phase-change-type of transition, should be expected as the secrecy constraint is gradually strengthened.

We consider the (n, k, d, ℓ) secure exact-repair regenerating code problem, which generalizes the (n, k, d) exact-repair regenerating code problem with the additional constraint that the stored file needs to be kept information-theoretically secure against an eavesdropper, who can access the data transmitted to regenerate a total of ℓ different failed nodes. For all known results on this problem, the achievable tradeoff regions between the normalized storage capacity and repair bandwidth have a single corner point, achieved by a scheme proposed by Shah, Rashmi, and Kumar (the SRK point). Since the achievable tradeoff regions of the exact-repair regenerating code problem without any secrecy constraints are known to have multiple corner points in general, these existing results suggest a phasechange-like behavior, i.e., enforcing a secrecy constraint (ℓ ≥ 1) immediately reduces the tradeoff region to one with a single corner point. In this paper, we first show that when the secrecy parameter ℓ is sufficiently large, the SRK point is indeed the only corner point of the tradeoff region. However, when ℓ is small, we show that the tradeoff region can in fact have multiple corner points. In particular, we establish a precise characterization of the tradeoff region for the (7, 6, 6, 1) problem, which has exactly two corner points. Thus, a smooth transition, instead of a phase-change-type of transition, should be expected as the secrecy constraint is gradually strengthened.