Layer-4 load balancers are a popular solution to high tail latencies but perform poorly under unpredictable skewed workloads because they statically assign connections to servers. We present Capybara, a new load balancer architecture that enables dynamic rebalancing of established connections. Capybara divides load balancing responsibility into a fast L4 load balancer, a host-switch co-designed connection migration protocol, and a transport interface for application-level connection state migration. Capybara leverages two trends - programmable switches and kernel-bypass - to efficiently implement connection migration without disruption, while maintaining transparency to clients. Under realistic workloads, Capybara achieves up to 149× lower tail latency and more than 2× higher throughput for scale-out services compared to state-of-the-art load balancing approaches.

Remote Direct Memory Access (RDMA) is widely used in high-performance computing (HPC) and data center networks. In this paper, we first show that RDMA does not work well with existing load balancing algorithms because of its traffic flow characteristics and assumption of in-order packet delivery. We then propose ConWeave, a load balancing framework designed for RDMA. The key idea of ConWeave is that with the right design, it is possible to perform fine granularity rerouting and mask the effect of out-of-order packet arrivals transparently in the network datapath using a programmable switch. We have implemented ConWeave on a Tofino2 switch. Evaluations show that ConWeave can achieve up to 42.3% and 66.8% improvement for average and 99-percentile FCT, respectively compared to the state-of-the-art load balancing algorithms.

Network adversaries, such as malicious transit autonomous systems (ASes), have been shown to be capable of partitioning the Bitcoin's peer-to-peer network via routing-level attacks; e.g., a network adversary exploits a BGP vulnerability and performs a prefix hijacking attack (viz. Apostolaki et al. [3]). Due to the nature of BGP operation, such a hijacking is globally observable and thus enables immediate detection of the attack and the identification of the perpetrator. In this paper, we present a stealthier attack, which we call the EREBUS attack, that partitions the Bitcoin network without any routing manipulations, which makes the attack undetectable to control-plane and even to data-plane detectors. The novel aspect of EREBUS is that it makes the adversary AS a natural man-in-the-middle network of all the peer connections of one or more targeted Bitcoin nodes by patiently influencing the targeted nodes' peering decision. We show that affecting the peering decision of a Bitcoin node, which is believed to be infeasible after a series of bug patches against the earlier Eclipse attack [29], is possible for the network adversary that can use abundant network address resources (e.g., spoofing millions of IP addresses in many other ASes) reliably for an extended period of time at a negligible cost. The EREBUS attack is readily available for large ASes, such as Tier-1 and large Tier-2 ASes, against the vast majority of 10K public Bitcoin nodes with only about 520 bit/s of attack traffic rate per targeted Bitcoin node and a modest (e.g., 5-6 weeks) attack execution period. The EREBUS attack can be mounted by nation-state adversaries who would be willing to execute sophisticated attack strategies patiently to compromise cryptocurrencies (e.g., control the consensus, take down a cryptocurrency, censor transactions). As the attack exploits the topological advantage of being a network adversary but not the specific vulnerabilities of Bitcoin core, no quick patches seem to be available. We discuss that some naive solutions (e.g., whitelisting, rate-limiting) are ineffective and third-party proxy solutions may worsen the Bitcoin's centralization problem. We provide some suggested modifications to the Bitcoin core and show that they effectively make the EREBUS attack significantly harder; yet, their non-trivial changes to the Bitcoin's network operation (e.g., peering dynamics, propagation delays) should be examined thoroughly before their wide deployment.

This paper proposes the eye detection using generalized binary pattern (GBP). The GBP can generate all possible patterns of ordered comparisons within a 3 × 3 neighborhood. Since existing local structure patterns consider all neighboring pixels around a given pixel, the number of possible patterns is fixed and limited to 2n. However, since the GBP takes the ordered comparisons of some partial neighboring pixels around a given pixel, a total of 502 different types can be generated in 3 × 3 block. So, our proposed GBP generates 19,162 binary patterns at the given pixel. Among the possible binary patterns, we take an effective set of pattern and position by the AdaBoost feature selection algorithm. Experimental results shows that the GBP provides higher eye detection accuracy on the BioID and FERET databases than other existing local structure patterns such as LBP and MCT.

We propose two novel local transform features: local gradient patterns (LGP) and binary histograms of oriented gradients (BHOG). LGP assigns one if the neighboring gradient of a given pixel is greater than its average of eight neighboring gradients and zero otherwise, which makes the local intensity variations along the edge components robust. BHOG assigns one if the histogram bin has a higher value than the average value of the total histogram bins, and zero otherwise, which makes the computation time fast due to no further postprocessing and SVM classification. We also propose a hybrid feature that combines several local transform features by means of the AdaBoost method, where the best feature having the lowest classification error is sequentially selected until we obtain the required classification performance. This hybridization makes face and human detection robust to global illumination changes by LBP, local intensity changes by LGP, and local pose changes by BHOG, which considerably improves detection performance. We apply the proposed features to face detection using the MIT+CMU and FDDB databases and human detection using the INRIA and Caltech databases. Our experimental results indicate that the proposed LGP and BHOG feature attain accurate detection performance and fast computation time, respectively, and the hybrid feature improves face and human detection performance considerably.

This letter proposes a novel local structure pattern, the generalized binary pattern (GBP), which can represent all possible binary patterns of ordered comparisons within a 3 × 3 neighborhood. Since most existing local structure patterns consider ordered comparisons of all neighboring pixels (8 or 9 pixels) around a given pixel, the number of possible binary patterns is fixed and limited to 256 (or 511). In contrast, our proposed GBP takes the ordered comparisons of some partial neighboring pixels (2 to 9 pixels) around a given pixel, which generates a total of 502 different structure types and thus extends the number of possible binary patterns to 19,162. Among these possible binary patterns, we choose an effective set of binary patterns for a given problem by means of the AdaBoost feature selection method. Experimental results show that our proposed GBP provides higher eye detection accuracy on the BioID and LFW face databases than other existing local structure patterns.

This paper proposes a precise eye detection and eye blink detection algorithm. Eye detection combines and separates scanning results based on an MCT-based AdaBoost detector. The algorithm detects eyes by applying the eye detector to eye candidate regions of a face. To eliminate outliers, we select an eye candidate group by grouping eye candidates. A refinement process using the average position of eye candidates in the selected eye candidate group obtains reliable detection results. Eye blink detection uses an MCT-based AdaBoost classifier, which discriminates between opened and closed eyes. The eye detection rate is 99.34% at the 0.1 normalized error on the BioID database. The eye blink detection accuracy is 96% at the 0.03 FAR on our blink database, which contains 400 images. The average processing time is 1 ms and 30 ms in a PC (Core2Duo 3.2GHz) and smart phone (PXA312), respectively.

This paper proposes a 3D face fitting algorithm based on the 3D Morphable Face Model. This algorithm updates parameters at each stage in the fitting process. To simplify measurement of parameters, this algorithm updates the parameters in cylindrical coordinates. The parameters are updated using a cost function which is the difference between the input 3D face data and the fitted 3D face model. This proposed algorithm shows good results when shape, texture and extrinsic variations occur in the 3D domain. The average correlation of the fitted shape and texture parameters to the test values are 0.72 and 0.99, respectively. This 3D face fitting algorithm can be widely used for 3D face analysis and 3D face recognition.