In this paper, we propose a novel directed fuzzing solution named AFLRun, which features target path-diversity metric and unbiased energy assignment. Firstly, we develop a new coverage metric by maintaining extra virgin map for each covered target to track the coverage status of seeds that hit the target. This approach enables the storage of waypoints into the corpus that hit a target through interesting path, thus enriching the path diversity for each target. Additionally, we propose a corpus-level energy assignment strategy that guarantees fairness for each target. AFLRun starts with uniform target weight and propagates this weight to seeds to get a desired seed weight distribution. By assigning energy to each seed in the corpus according to such desired distribution, a precise and unbiased energy assignment can be achieved. We built a prototype system and assessed its performance using a standard benchmark and several extensively fuzzed real-world applications. The evaluation results demonstrate that AFLRun outperforms state-of-the-art fuzzers in terms of vulnerability detection, both in quantity and speed. Moreover, AFLRun uncovers 29 previously unidentified vulnerabilities, including 8 CVEs, across four distinct programs.
相關內容
In this research paper, we introduce a novel classification method aimed at improving the performance of the K-Nearest Neighbors (KNN) algorithm. Our approach leverages Mutual Information (MI) to enhance the significance of weights and draw inspiration from Shapley values, a concept originating from cooperative game theory, to refine value allocation. The fundamental concept underlying KNN is the classification of samples based on the majority thorough their k-nearest neighbors. While both the distances and labels of these neighbors are crucial, traditional KNN assigns equal weight to all samples and prevance considering the varying importance of each neighbor based on their distances and labels. In the proposed method, known as Information-Modified KNN (IMKNN), we address this issue by introducing a straightforward algorithm. To evaluate the effectiveness of our approach, it is compared with 7 contemporary variants of KNN, as well as the traditional KNN. Each of these variants exhibits its unique advantages and limitations. We conduct experiments on 12 widely-used datasets, assessing the methods' performance in terms of accuracy, precision and recall. Our study demonstrates that IMKNN consistently outperforms other methods across different datasets and criteria by highlighting its superior performance in various classification tasks. These findings underscore the potential of IMKNN as a valuable tool for enhancing the capabilities of the KNN algorithm in diverse applications.
In this paper, we introduce a novel fine-tuning technique for language models, which involves incorporating symmetric noise into the embedding process. This method aims to enhance the model's function by more stringently regulating its local curvature, demonstrating superior performance over the current method, NEFTune. When fine-tuning the LLaMA-2-7B model using Alpaca, standard techniques yield a 29.79% score on AlpacaEval. However, our approach, SymNoise, increases this score significantly to 69.04%, using symmetric noisy embeddings. This is a 6.7% improvement over the state-of-the-art method, NEFTune~(64.69%). Furthermore, when tested on various models and stronger baseline instruction datasets, such as Evol-Instruct, ShareGPT, OpenPlatypus, SymNoise consistently outperforms NEFTune. The current literature, including NEFTune, has underscored the importance of more in-depth research into the application of noise-based strategies in the fine-tuning of language models. Our approach, SymNoise, is another significant step towards this direction, showing notable improvement over the existing state-of-the-art method.
In this paper, we consider the problem of recovering random graph signals from nonlinear measurements. We formulate the maximum a-posteriori probability (MAP) estimator, which results in a nonconvex optimization problem. Conventional iterative methods for minimizing nonconvex problems are sensitive to the initialization, have high computational complexity, and do not utilize the underlying graph structure behind the data. In this paper we propose two new estimators that are both based on the Gauss-Newton method: 1) the elementwise graph-frequency-domain MAP (eGFD-MAP) estimator; and 2) the graph signal processing MAP (GSP-MAP) estimator. At each iteration, these estimators are updated by the outputs of two graph filters, with the previous state estimator and the residual as the input graph signals. The eGFD-MAP estimator is an ad-hoc method that minimizes the MAP objective function in the graph frequency domain and neglects mixed-derivatives of different graph frequencies in the Jacobian matrix as well as off-diagonal elements in the covariance matrices. Consequently, it updates the elements of the graph signal independently, which reduces the computational complexity compared to the conventional MAP estimator. The GSP-MAP estimator is based on optimizing the graph filters at each iteration of the Gauss-Newton algorithm. We state conditions under which the eGFD-MAP and GSP- MAP estimators coincide with the MAP estimator, in the case of an observation model with orthogonal graph frequencies. We evaluate the performance of the estimators for nonlinear graph signal recovery tasks with synthetic data and with the real-world problem of state estimation in power systems. These simulations show the advantages of the proposed estimators in terms of computational complexity, mean-squared-error, and robustness to the initialization of the iterative algorithms.
We propose a novel Neural Radiance Field (NeRF) representation for non-opaque scenes that allows fast inference by utilizing textured polygons. Despite the high-quality novel view rendering that NeRF provides, a critical limitation is that it relies on volume rendering that can be computationally expensive and does not utilize the advancements in modern graphics hardware. Existing methods for this problem fall short when it comes to modelling volumetric effects as they rely purely on surface rendering. We thus propose to model the scene with polygons, which can then be used to obtain the quadrature points required to model volumetric effects, and also their opacity and colour from the texture. To obtain such polygonal mesh, we train a specialized field whose zero-crossings would correspond to the quadrature points when volume rendering, and perform marching cubes on this field. We then rasterize the polygons and utilize the fragment shaders to obtain the final colour image. Our method allows rendering on various devices and easy integration with existing graphics frameworks while keeping the benefits of volume rendering alive.
Motivated by Tucker tensor decomposition, this paper imposes low-rank structures to the column and row spaces of coefficient matrices in a multivariate infinite-order vector autoregression (VAR), which leads to a supervised factor model with two factor modelings being conducted to responses and predictors simultaneously. Interestingly, the stationarity condition implies an intrinsic weak group sparsity mechanism of infinite-order VAR, and hence a rank-constrained group Lasso estimation is considered for high-dimensional linear time series. Its non-asymptotic properties are discussed thoughtfully by balancing the estimation, approximation and truncation errors. Moreover, an alternating gradient descent algorithm with thresholding is designed to search for high-dimensional estimates, and its theoretical justifications, including statistical and convergence analysis, are also provided. Theoretical and computational properties of the proposed methodology are verified by simulation experiments, and the advantages over existing methods are demonstrated by two real examples.
In this paper, we propose a novel Feature Decomposition and Reconstruction Learning (FDRL) method for effective facial expression recognition. We view the expression information as the combination of the shared information (expression similarities) across different expressions and the unique information (expression-specific variations) for each expression. More specifically, FDRL mainly consists of two crucial networks: a Feature Decomposition Network (FDN) and a Feature Reconstruction Network (FRN). In particular, FDN first decomposes the basic features extracted from a backbone network into a set of facial action-aware latent features to model expression similarities. Then, FRN captures the intra-feature and inter-feature relationships for latent features to characterize expression-specific variations, and reconstructs the expression feature. To this end, two modules including an intra-feature relation modeling module and an inter-feature relation modeling module are developed in FRN. Experimental results on both the in-the-lab databases (including CK+, MMI, and Oulu-CASIA) and the in-the-wild databases (including RAF-DB and SFEW) show that the proposed FDRL method consistently achieves higher recognition accuracy than several state-of-the-art methods. This clearly highlights the benefit of feature decomposition and reconstruction for classifying expressions.
Knowledge graph embedding, which aims to represent entities and relations as low dimensional vectors (or matrices, tensors, etc.), has been shown to be a powerful technique for predicting missing links in knowledge graphs. Existing knowledge graph embedding models mainly focus on modeling relation patterns such as symmetry/antisymmetry, inversion, and composition. However, many existing approaches fail to model semantic hierarchies, which are common in real-world applications. To address this challenge, we propose a novel knowledge graph embedding model---namely, Hierarchy-Aware Knowledge Graph Embedding (HAKE)---which maps entities into the polar coordinate system. HAKE is inspired by the fact that concentric circles in the polar coordinate system can naturally reflect the hierarchy. Specifically, the radial coordinate aims to model entities at different levels of the hierarchy, and entities with smaller radii are expected to be at higher levels; the angular coordinate aims to distinguish entities at the same level of the hierarchy, and these entities are expected to have roughly the same radii but different angles. Experiments demonstrate that HAKE can effectively model the semantic hierarchies in knowledge graphs, and significantly outperforms existing state-of-the-art methods on benchmark datasets for the link prediction task.
In this paper, we proposed to apply meta learning approach for low-resource automatic speech recognition (ASR). We formulated ASR for different languages as different tasks, and meta-learned the initialization parameters from many pretraining languages to achieve fast adaptation on unseen target language, via recently proposed model-agnostic meta learning algorithm (MAML). We evaluated the proposed approach using six languages as pretraining tasks and four languages as target tasks. Preliminary results showed that the proposed method, MetaASR, significantly outperforms the state-of-the-art multitask pretraining approach on all target languages with different combinations of pretraining languages. In addition, since MAML's model-agnostic property, this paper also opens new research direction of applying meta learning to more speech-related applications.
In this paper, we introduce the Reinforced Mnemonic Reader for machine reading comprehension tasks, which enhances previous attentive readers in two aspects. First, a reattention mechanism is proposed to refine current attentions by directly accessing to past attentions that are temporally memorized in a multi-round alignment architecture, so as to avoid the problems of attention redundancy and attention deficiency. Second, a new optimization approach, called dynamic-critical reinforcement learning, is introduced to extend the standard supervised method. It always encourages to predict a more acceptable answer so as to address the convergence suppression problem occurred in traditional reinforcement learning algorithms. Extensive experiments on the Stanford Question Answering Dataset (SQuAD) show that our model achieves state-of-the-art results. Meanwhile, our model outperforms previous systems by over 6% in terms of both Exact Match and F1 metrics on two adversarial SQuAD datasets.
In this paper, we propose a conceptually simple and geometrically interpretable objective function, i.e. additive margin Softmax (AM-Softmax), for deep face verification. In general, the face verification task can be viewed as a metric learning problem, so learning large-margin face features whose intra-class variation is small and inter-class difference is large is of great importance in order to achieve good performance. Recently, Large-margin Softmax and Angular Softmax have been proposed to incorporate the angular margin in a multiplicative manner. In this work, we introduce a novel additive angular margin for the Softmax loss, which is intuitively appealing and more interpretable than the existing works. We also emphasize and discuss the importance of feature normalization in the paper. Most importantly, our experiments on LFW BLUFR and MegaFace show that our additive margin softmax loss consistently performs better than the current state-of-the-art methods using the same network architecture and training dataset. Our code has also been made available at //github.com/happynear/AMSoftmax
小貼士
登錄享
相關主題
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191