Self-supervised learning usually uses a large amount of unlabeled data to pre-train an encoder which can be used as a general-purpose feature extractor, such that downstream users only need to perform fine-tuning oper...
Self-supervised learning usually uses a large amount of unlabeled data to pre-train an encoder which can be used as a general-purpose feature extractor, such that downstream users only need to perform fine-tuning operations to enjoy the benefit of "large model". Despite this promising prospect, the security of pre-trained encoder has not been thoroughly investigated yet, especially when the pre-trained encoder is publicly available for commercial *** this paper, we propose AdvEncoder, the first framework for generating downstream-agnostic universal adversarial examples based on the pre-trained encoder. AdvEncoder aims to construct a universal adversarial perturbation or patch for a set of natural images that can fool all the downstream tasks inheriting the victim pre-trained encoder. Unlike traditional adversarial example works, the pre-trained encoder only outputs feature vectors rather than classification labels. Therefore, we first exploit the high frequency component information of the image to guide the generation of adversarial examples. Then we design a generative attack framework to construct adversarial perturbations/patches by learning the distribution of the attack surrogate dataset to improve their attack success rates and transferability. Our results show that an attacker can successfully attack downstream tasks without knowing either the pre-training dataset or the downstream dataset. We also tailor four defenses for pre-trained encoders, the results of which further prove the attack ability of AdvEncoder. Our codes are available at: https://***/CGCL-codes/AdvEncoder.
The natural bijection between a proposed circuit design and its graph representation shall allow any graph optimization algorithm deploying into many-core systems efficiently. However, this process suffers from the ex...
The natural bijection between a proposed circuit design and its graph representation shall allow any graph optimization algorithm deploying into many-core systems efficiently. However, this process suffers from the exponentially growing overhead and heavy memory footprint with the signal propagation. To conquer the unique challenge, we systematically study the simulation with millions of gates, and identify that the processing complexity could grow exponentially from the signal inputs, the skewness of the computational graph stays. Thus, we present ZhouBi, a fast and scalable gate-level simulation framework to fully exploit the parallelism from many-core systems. ZhouBi contributes in threefolds, (I) a graph representation that colors gate-level netlists and identifies skew partitions based on the graph skewness; (II) A set of heuristic algorithms that picks opportunistic and conservative algorithms to accelerate the simulation; (III) A system facility that supports selective mapping between simulation and many-core, providing a tradeoff between the risk of concurrent simulation fail and performance gain. We have prototyped ZhouBi and evaluated it with practical baselines. ZhouBi can achieve a 27.6× performance gain, as compared to the state-of-the-practice Veriwell without compromising any correctness. Our framework supports large graphs enabling scale-out gate-level simulations for chip design.
With the advantages of zero emission and comfortable riding experience, battery-electric buses (BEBs) are widely adopted in public transit agencies as a green alternative to conventional diesel buses. Battery swapping...
详细信息
ISBN:
(数字)9798350314212
ISBN:
(纸本)9798350314229
With the advantages of zero emission and comfortable riding experience, battery-electric buses (BEBs) are widely adopted in public transit agencies as a green alternative to conventional diesel buses. Battery swapping technology is an efficient and promising charging technology to address the issues of battery range anxiety and long battery charging time. This study developed a two-stage optimization model to optimize the single-line battery-electric bus scheduling problem considering battery swapping. At the first stage, a bi-objective integer programming model is established to determine the minimum BEB fleet size, together with the BEB-to-trip assignment and battery swapping schedule. At the second stage, an integer linear programming model is formulated to determine the required minimum number of batteries. An
$\epsilon$
-constraint method is designed to investigate the trade-off between the required minimum fleet size and the number of back-up batteries. Finally, a real-world case study of a BEB line in Chengdu, China, is conducted to demonstrate the effectiveness of the optimization model and solution method. Sensitivity analyses are further conducted to understand the impacts of some key parameters, including battery capacity, number of trips, cycle time, and battery swapping time. The results show that battery capacity and cycle time have significant influences on BEB-to-trip assignment results and battery swapping schedule.
For efficient and high-fidelity local facial attribute editing, most existing editing methods either require additional finetuning for different editing effects or tend to affect beyond the editing regions. Alternativ...
Accurately synthesizing talking face videos and capturing fine facial features for individuals with long hair presents a significant challenge. To tackle these challenges in existing methods, we propose a decomposed p...
详细信息
Hair editing is a critical image synthesis task that aims to edit hair color and hairstyle using text descriptions or reference images, while preserving irrelevant attributes (e.g., identity, background, cloth). Many ...
详细信息
The Natural Language to Visualization (NL2Vis) task aims to transform natural-language descriptions into visual representations for a grounded table, enabling users to gain insights from vast amounts of data. Recently...
详细信息
Existing streaming graph processing systems typically adopt two phases of refinement and recomputation to ensure the correctness of the incremental computation. However, severe redundant memory accesses exist due to t...
详细信息
ISBN:
(纸本)9781665454452
Existing streaming graph processing systems typically adopt two phases of refinement and recomputation to ensure the correctness of the incremental computation. However, severe redundant memory accesses exist due to the unnecessary synchronization among independent edge updates. In this paper, we present GraphFly, a high-performance asynchronous streaming graph processing system based on dependency-flows. GraphFly features three key designs: 1) Dependency trees (D-trees), which helps quickly identify independent graph updates with low cost; 2) Dependency-flow based processing model, which exploits the space-time dependent co-scheduling for cache efficiency; 3) Specialized graph data layout, which further reduces memory accesses. We evaluate GraphFly, and the results show that GraphFly significantly outperforms state-of-the-art systems KickStarter and GraphBolt by 5.81× and 1.78× on average, respectively. Also, GraphFly scales well with different sizes of update batch and compute resources.
Student cognitive modeling (SCM) is a fundamental task in intelligent education, with applications ranging from personalized learning to educational resource allocation. By exploiting students' response logs, SCM ...
ISBN:
(纸本)9798331314385
Student cognitive modeling (SCM) is a fundamental task in intelligent education, with applications ranging from personalized learning to educational resource allocation. By exploiting students' response logs, SCM aims to predict their exercise performance as well as estimate knowledge proficiency in a subject. data mining approaches such as matrix factorization can obtain high accuracy in predicting student performance on exercises, but the knowledge proficiency is unknown or poorly estimated. The situation is further exacerbated if only sparse interactions exist between exercises and students (or knowledge concepts). To solve this dilemma, we root monotonicity (a fundamental psychometric theory on educational assessments) in a co-factorization framework and present an autoencoder-like nonnegative matrix co-factorization (AE-NMCF), which improves the accuracy of estimating the student's knowledge proficiency via an encoder-decoder learning pipeline. The resulting estimation problem is nonconvex with nonnegative constraints. We introduce a projected gradient method based on block coordinate descent with Lipschitz constants and guarantee the method's theoretical convergence. Experiments on several real-world data sets demonstrate the efficacy of our approach in terms of both performance prediction accuracy and knowledge estimation ability, when compared with existing student cognitive models.
The data-centric machine learning aims to find effective ways to build appropriate datasets which can improve the performance of AI models. In this paper, we mainly focus on designing an efficient data-centric scheme ...
详细信息
暂无评论