While anonymity networks like Tor aim to protect the privacy of their users, they are vulnerable to traffic analysis attacks such as Website Fingerprinting (WF) and Flow Correlation (FC). Recent implementations of WF and FC attacks, such as Tik-Tok and DeepCoFFEA, have shown that the attacks can be effectively carried out, threatening user privacy. Consequently, there is a need for effective traffic analysis defense. There are a variety of existing defenses, but most are either ineffective, incur high latency and bandwidth overhead, or require additional infrastructure. As a result, we aim to design a traffic analysis defense that is efficient and highly resistant to both WF and FC attacks. We propose DeTorrent, which uses competing neural networks to generate and evaluate traffic analysis defenses that insert 'dummy' traffic into real traffic flows. DeTorrent operates with moderate overhead and without delaying traffic. In a closed-world WF setting, it reduces an attacker's accuracy by 61.5%, a reduction 10.5% better than the next-best padding-only defense. Against the state-of-the-art FC attacker, DeTorrent reduces the true positive rate for a $10^{-5}$ false positive rate to about .12, which is less than half that of the next-best defense. We also demonstrate DeTorrent's practicality by deploying it alongside the Tor network and find that it maintains its performance when applied to live traffic.
相關內容
Sharing knowledge between information extraction tasks has always been a challenge due to the diverse data formats and task variations. Meanwhile, this divergence leads to information waste and increases difficulties in building complex applications in real scenarios. Recent studies often formulate IE tasks as a triplet extraction problem. However, such a paradigm does not support multi-span and n-ary extraction, leading to weak versatility. To this end, we reorganize IE problems into unified multi-slot tuples and propose a universal framework for various IE tasks, namely Mirror. Specifically, we recast existing IE tasks as a multi-span cyclic graph extraction problem and devise a non-autoregressive graph decoding algorithm to extract all spans in a single step. It is worth noting that this graph structure is incredibly versatile, and it supports not only complex IE tasks, but also machine reading comprehension and classification tasks. We manually construct a corpus containing 57 datasets for model pretraining, and conduct experiments on 30 datasets across 8 downstream tasks. The experimental results demonstrate that our model has decent compatibility and outperforms or reaches competitive performance with SOTA systems under few-shot and zero-shot settings. The code, model weights, and pretraining corpus are available at //github.com/Spico197/Mirror .
Storing network traffic data is key to efficient network management; however, it is becoming more challenging and costly due to the ever-increasing data transmission rates, traffic volumes, and connected devices. In this paper, we explore the use of neural architectures for network traffic compression. Specifically, we consider a network scenario with multiple measurement points in a network topology. Such measurements can be interpreted as multiple time series that exhibit spatial and temporal correlations induced by network topology, routing, or user behavior. We present \textit{Atom}, a neural traffic compression method that leverages spatial and temporal correlations present in network traffic. \textit{Atom} implements a customized spatio-temporal graph neural network design that effectively exploits both types of correlations simultaneously. The experimental results show that \textit{Atom} can outperform GZIP's compression ratios by 50\%-65\% on three real-world networks.
Large Language Models (LLMs) with a billion or more parameters are prime targets for network pruning, which aims to reduce a portion of the network weights without compromising performance. Prior approaches such as Weights Magnitude, SparseGPT, and Wanda, either concentrated solely on weights or integrated weights with activations for sparsity. However, they overlooked the informative gradients derived from pretrained large language models. In this paper, we present a novel sparsity-centric pruning method for pretrained LLMs, termed Gradient-based Language Model Pruner (GBLM-Pruner). GBLM-Pruner leverages the first-order term of the Taylor expansion, operating in a training-free manner by harnessing properly normalized gradients from a few calibration samples to determine the importance pruning score, and substantially outperforms competitive counterparts like SparseGPT and Wanda in multiple benchmarks. Intriguing, after incorporating gradients, the unstructured pruning method tends to reveal some structural patterns post-pruning, which mirrors the geometric interdependence inherent in the LLMs' parameter structure. Additionally, GBLM-Pruner functions without any subsequent retraining or weight updates to maintain its simplicity as other counterparts. Extensive evaluations on LLaMA-1 and LLaMA-2 across various language benchmarks and perplexity show that GBLM-Pruner surpasses magnitude pruning, Wanda (weights+activations) and SparseGPT (weights+activations+weight update) by significant margins. Our code and models are available at //github.com/RocktimJyotiDas/GBLM-Pruner.
Large graphs are present in a variety of domains, including social networks, civil infrastructure, and the physical sciences to name a few. Graph generation is similarly widespread, with applications in drug discovery, network analysis and synthetic datasets among others. While GNN (Graph Neural Network) models have been applied in these domains their high in-memory costs restrict them to small graphs. Conversely less costly rule-based methods struggle to reproduce complex structures. We propose HIGGS (Hierarchical Generation of Graphs) as a model-agnostic framework of producing large graphs with realistic local structures. HIGGS uses GNN models with conditional generation capabilities to sample graphs in hierarchies of resolution. As a result HIGGS has the capacity to extend the scale of generated graphs from a given GNN model by quadratic order. As a demonstration we implement HIGGS using DiGress, a recent graph-diffusion model, including a novel edge-predictive-diffusion variant edge-DiGress. We use this implementation to generate categorically attributed graphs with tens of thousands of nodes. These HIGGS generated graphs are far larger than any previously produced using GNNs. Despite this jump in scale we demonstrate that the graphs produced by HIGGS are, on the local scale, more realistic than those from the rule-based model BTER.
Attackers can exploit known vulnerabilities to infiltrate a device's firmware and the communication between firmware binaries, in order to pass between them. To improve cybersecurity, organizations must identify and mitigate the risks of the firmware they use. An attack graph (AG) can be used to assess and visually display firmware's risks by organizing the identified vulnerabilities into attack paths composed of sequences of actions attackers may perform to compromise firmware images. In this paper, we utilize AGs for firmware risk assessment. We propose MIRAGE (Multi-binary Image Risk Assessment with Attack Graph Employment), a framework for identifying potential attack vectors and vulnerable interactions between firmware binaries; MIRAGE accomplishes this by generating AGs for firmware inter-binary communication. The use cases of the proposed firmware AG generation framework include the identification of risky external interactions, supply chain risk assessment, and security analysis with digital twins. To evaluate the MIRAGE framework, we collected a dataset of 703 firmware images. We also propose a model for examining the risks of firmware binaries, demonstrate the model's implementation on the dataset of firmware images, and list the riskiest binaries.
Fully Homomorphic Encryption (FHE) has the potential to substantially improve privacy and security by enabling computation on encrypted data. This is especially true with deep learning, as today many popular user services are powered by neural networks. One of the major challenges facing wide-scale deployment of FHE-secured neural inference is effectively mapping them to the FHE domain. FHE poses many programming challenges including packing large vectors, handling expensive rotations, and correctly implementing complex strided convolutions. This makes programming FHE inferences prone to poor performance and errors. In this paper we overcome these challenges with Orion, an automated optimizing FHE compiler for neural inference. Orion automatically maps PyTorch-specified networks to FHE, handling common layer types and arbitrary tensor shapes and strides. Moreover, we develop novel optimizations that balance dense FHE vector packing, efficient rotations, and minimize operations to improve performance. We have implemented Orion, which will be open sourced, and evaluated it on common benchmarks used by the FHE deep learning community. We compare Orion to multiple state-of-the-art solutions and report iso-accuracy speedups ranging from 2.7$\times$ to 20.5$\times$.
More than one hundred benchmarks have been developed to test the commonsense knowledge and commonsense reasoning abilities of artificial intelligence (AI) systems. However, these benchmarks are often flawed and many aspects of common sense remain untested. Consequently, we do not currently have any reliable way of measuring to what extent existing AI systems have achieved these abilities. This paper surveys the development and uses of AI commonsense benchmarks. We discuss the nature of common sense; the role of common sense in AI; the goals served by constructing commonsense benchmarks; and desirable features of commonsense benchmarks. We analyze the common flaws in benchmarks, and we argue that it is worthwhile to invest the work needed ensure that benchmark examples are consistently high quality. We survey the various methods of constructing commonsense benchmarks. We enumerate 139 commonsense benchmarks that have been developed: 102 text-based, 18 image-based, 12 video based, and 7 simulated physical environments. We discuss the gaps in the existing benchmarks and aspects of commonsense reasoning that are not addressed in any existing benchmark. We conclude with a number of recommendations for future development of commonsense AI benchmarks.
Graph convolutional networks (GCNs) have recently become one of the most powerful tools for graph analytics tasks in numerous applications, ranging from social networks and natural language processing to bioinformatics and chemoinformatics, thanks to their ability to capture the complex relationships between concepts. At present, the vast majority of GCNs use a neighborhood aggregation framework to learn a continuous and compact vector, then performing a pooling operation to generalize graph embedding for the classification task. These approaches have two disadvantages in the graph classification task: (1)when only the largest sub-graph structure ($k$-hop neighbor) is used for neighborhood aggregation, a large amount of early-stage information is lost during the graph convolution step; (2) simple average/sum pooling or max pooling utilized, which loses the characteristics of each node and the topology between nodes. In this paper, we propose a novel framework called, dual attention graph convolutional networks (DAGCN) to address these problems. DAGCN automatically learns the importance of neighbors at different hops using a novel attention graph convolution layer, and then employs a second attention component, a self-attention pooling layer, to generalize the graph representation from the various aspects of a matrix graph embedding. The dual attention network is trained in an end-to-end manner for the graph classification task. We compare our model with state-of-the-art graph kernels and other deep learning methods. The experimental results show that our framework not only outperforms other baselines but also achieves a better rate of convergence.
Sentiment analysis is a widely studied NLP task where the goal is to determine opinions, emotions, and evaluations of users towards a product, an entity or a service that they are reviewing. One of the biggest challenges for sentiment analysis is that it is highly language dependent. Word embeddings, sentiment lexicons, and even annotated data are language specific. Further, optimizing models for each language is very time consuming and labor intensive especially for recurrent neural network models. From a resource perspective, it is very challenging to collect data for different languages. In this paper, we look for an answer to the following research question: can a sentiment analysis model trained on a language be reused for sentiment analysis in other languages, Russian, Spanish, Turkish, and Dutch, where the data is more limited? Our goal is to build a single model in the language with the largest dataset available for the task, and reuse it for languages that have limited resources. For this purpose, we train a sentiment analysis model using recurrent neural networks with reviews in English. We then translate reviews in other languages and reuse this model to evaluate the sentiments. Experimental results show that our robust approach of single model trained on English reviews statistically significantly outperforms the baselines in several different languages.
Recurrent neural nets (RNN) and convolutional neural nets (CNN) are widely used on NLP tasks to capture the long-term and local dependencies, respectively. Attention mechanisms have recently attracted enormous interest due to their highly parallelizable computation, significantly less training time, and flexibility in modeling dependencies. We propose a novel attention mechanism in which the attention between elements from input sequence(s) is directional and multi-dimensional (i.e., feature-wise). A light-weight neural net, "Directional Self-Attention Network (DiSAN)", is then proposed to learn sentence embedding, based solely on the proposed attention without any RNN/CNN structure. DiSAN is only composed of a directional self-attention with temporal order encoded, followed by a multi-dimensional attention that compresses the sequence into a vector representation. Despite its simple form, DiSAN outperforms complicated RNN models on both prediction quality and time efficiency. It achieves the best test accuracy among all sentence encoding methods and improves the most recent best result by 1.02% on the Stanford Natural Language Inference (SNLI) dataset, and shows state-of-the-art test accuracy on the Stanford Sentiment Treebank (SST), Multi-Genre natural language inference (MultiNLI), Sentences Involving Compositional Knowledge (SICK), Customer Review, MPQA, TREC question-type classification and Subjectivity (SUBJ) datasets.
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