对象检测是各种关键计算机视觉任务的基础,例如分割,对象跟踪和事件检测。要以令人满意的精度训练对象探测器,需要大量数据。但是,由于注释大型数据集涉及大量劳动力,这种数据策展任务通常被外包给第三方或依靠志愿者。这项工作揭示了此类数据策展管道的严重脆弱性。我们提出MACAB,即使数据策展人可以手动审核图像,也可以将干净的图像制作清洁的图像将后门浸入对象探测器中。我们观察到,当后门被不明确的天然物理触发器激活时,在野外实现了错误分类和披肩的后门效应。与带有清洁标签的现有图像分类任务相比,带有清洁通道的非分类对象检测具有挑战性,这是由于每个帧内有多个对象的复杂性,包括受害者和非视野性对象。通过建设性地滥用深度学习框架使用的图像尺度函数,II结合了所提出的对抗性清洁图像复制技术,以及在考虑到毒品数据选择标准的情况下,通过建设性地滥用图像尺度尺度,可以确保MACAB的功效。广泛的实验表明,在各种现实世界中,MacAB在90%的攻击成功率中表现出超过90%的攻击成功率。这包括披肩和错误分类后门效应,甚至限制了较小的攻击预算。最先进的检测技术无法有效地识别中毒样品。全面的视频演示位于https://youtu.be/ma7l_lpxkp4上,该演示基于yolov4倒置的毒药率为0.14%,yolov4 clokaking后门和更快的速度R-CNN错误分类后门。
translated by 谷歌翻译
Split学习(SL)通过允许客户在不共享原始数据的情况下协作培训深度学习模型来实现数据隐私保护。但是,SL仍然有限制,例如潜在的数据隐私泄漏和客户端的高计算。在这项研究中,我们建议将SL局部层进行二线以进行更快的计算(在移动设备上的培训和推理阶段的前进时间少17.5倍)和减少内存使用情况(最多减少32倍的内存和带宽要求) 。更重要的是,二进制的SL(B-SL)模型可以减少SL污染数据中的隐私泄漏,而模型精度的降解仅小。为了进一步增强隐私保护,我们还提出了两种新颖的方法:1)培训额外的局部泄漏损失,2)应用差异隐私,可以单独或同时集成到B-SL模型中。与多种基准模型相比,使用不同数据集的实验结果肯定了B-SL模型的优势。还说明了B-SL模型针对功能空间劫持攻击(FSHA)的有效性。我们的结果表明,B-SL模型对于具有高隐私保护要求(例如移动医疗保健应用程序)的轻巧的物联网/移动应用程序很有希望。
translated by 谷歌翻译
As a critical threat to deep neural networks (DNNs), backdoor attacks can be categorized into two types, i.e., source-agnostic backdoor attacks (SABAs) and source-specific backdoor attacks (SSBAs). Compared to traditional SABAs, SSBAs are more advanced in that they have superior stealthier in bypassing mainstream countermeasures that are effective against SABAs. Nonetheless, existing SSBAs suffer from two major limitations. First, they can hardly achieve a good trade-off between ASR (attack success rate) and FPR (false positive rate). Besides, they can be effectively detected by the state-of-the-art (SOTA) countermeasures (e.g., SCAn). To address the limitations above, we propose a new class of viable source-specific backdoor attacks, coined as CASSOCK. Our key insight is that trigger designs when creating poisoned data and cover data in SSBAs play a crucial role in demonstrating a viable source-specific attack, which has not been considered by existing SSBAs. With this insight, we focus on trigger transparency and content when crafting triggers for poisoned dataset where a sample has an attacker-targeted label and cover dataset where a sample has a ground-truth label. Specifically, we implement $CASSOCK_{Trans}$ and $CASSOCK_{Cont}$. While both they are orthogonal, they are complementary to each other, generating a more powerful attack, called $CASSOCK_{Comp}$, with further improved attack performance and stealthiness. We perform a comprehensive evaluation of the three $CASSOCK$-based attacks on four popular datasets and three SOTA defenses. Compared with a representative SSBA as a baseline ($SSBA_{Base}$), $CASSOCK$-based attacks have significantly advanced the attack performance, i.e., higher ASR and lower FPR with comparable CDA (clean data accuracy). Besides, $CASSOCK$-based attacks have effectively bypassed the SOTA defenses, and $SSBA_{Base}$ cannot.
translated by 谷歌翻译
联合学习(FL)在许多分散的用户中训练全球模型,每个用户都有本地数据集。与传统的集中学习相比,FL不需要直接访问本地数据集,因此旨在减轻数据隐私问题。但是,由于推理攻击,包括成员推理,属性推理和数据反演,FL中的数据隐私泄漏仍然存在。在这项工作中,我们提出了一种新型的隐私推理攻击,创造的偏好分析攻击(PPA),它准确地介绍了本地用户的私人偏好,例如,最喜欢(不喜欢)来自客户的在线购物中的(不喜欢)项目和最常见的表达式从用户的自拍照中。通常,PPA可以在本地客户端(用户)的特征上介绍top-k(即,尤其是k = 1、2、3和k = 1)的偏好。我们的关键见解是,本地用户模型的梯度变化对给定类别的样本比例(尤其是大多数(少数)类别的样本比例具有明显的敏感性。通过观察用户模型对类的梯度敏感性,PPA可以介绍用户本地数据集中类的样本比例,从而公开用户对类的偏好。 FL的固有统计异质性进一步促进了PPA。我们使用四个数据集(MNIST,CIFAR10,RAF-DB和PRODUCTS-10K)广泛评估了PPA的有效性。我们的结果表明,PPA分别达到了MNIST和CIFAR10的90%和98%的TOP-1攻击精度。更重要的是,在实际的购物商业商业场景(即产品-10k)和社交网络(即RAF-DB)中,PPA在前一种情况下,PPA获得了78%的TOP-1攻击精度,以推断出最有序的物品(即作为商业竞争对手),在后一种情况下,有88%来推断受害者用户最常见的面部表情,例如恶心。
translated by 谷歌翻译
利用额外数据的最佳方法(无论是从同一任务中未标记的数据还是从相关任务标记的数据)学习给定任务的最佳方法是什么?本文使用参考研究理论对问题进行正式化。参考先验是客观的,非信息性的贝叶斯先验,可最大程度地提高任务和模型权重之间的相互信息。这样的先验使该任务能够最大程度地影响贝叶斯后部,例如,参考先知取决于可用于学习任务的样本数量,并且对于非常小的样本量,先前的概率质量更大,在假设空间中的低复杂模型上有更多的概率质量。本文介绍了中等尺度深网和基于图像的数据的参考先验的首次演示。我们开发了参考先验的概括,并向两个问题展示了应用。首先,通过使用未标记的数据来计算参考之前,我们开发了新的贝叶斯半监督学习方法,即使每个类别的样本很少,它们仍然有效。其次,通过使用来自源任务的标记数据来计算参考之前,我们开发了一种新的转移学习方法,该方法允许从目标任务进行数据以最大程度地影响贝叶斯后验。这些方法的经验验证是在图像分类数据集上进行的。代码可从https://github.com/grasp-lyrl/deep_reference_priors获得。
translated by 谷歌翻译
后门深度学习(DL)模型的行为通常在清洁输入上,但在触发器输入时不端行为,因为后门攻击者希望为DL模型部署构成严重后果。最先进的防御是限于特定的后门攻击(源无关攻击)或在该机器学习(ML)专业知识或昂贵的计算资源中不适用于源友好的攻击。这项工作观察到所有现有的后门攻击都具有不可避免的内在弱点,不可转换性,即触发器输入劫持劫持模型,但不能对另一个尚未植入同一后门的模型有效。通过此密钥观察,我们提出了不可转换性的反向检测(NTD)来识别运行时在运行时的模型欠测试(MUT)的触发输入。特定,NTD允许潜在的回溯静电预测输入的类别。同时,NTD利用特征提取器(FE)来提取输入的特征向量,并且从其预测类随机拾取的一组样本,然后比较FE潜在空间中的输入和样本之间的相似性。如果相似性低,则输入是对逆势触发输入;否则,良性。 FE是一个免费的预训练模型,私下从开放平台保留。随着FE和MUT来自不同来源,攻击者非常不可能将相同的后门插入其中两者。由于不可转换性,不能将突变处工作的触发效果转移到FE,使NTD对不同类型的后门攻击有效。我们在三个流行的定制任务中评估NTD,如面部识别,交通标志识别和一般动物分类,结果确认NDT具有高效率(低假验收率)和具有低检测延迟的可用性(低误报率)。
translated by 谷歌翻译
尽管深度神经网络模型在各种应用程序中表现出出色的性能,但它们的较大模型大小和广泛的浮点操作使移动计算平台上的部署成为主要挑战,尤其是在物联网设备上。一种吸引人的解决方案是模型量化,可降低模型大小并使用微控制器通常支持的整数操作。为此,1位量化的DNN模型或深二进制神经网络可最大化存储效率,其中BNN模型中的每个参数仅具有1位。在本文中,我们提出了一个可重构的BNN(RBNN),以进一步扩大资源约束的物联网设备的内存效率。通常,可以根据需要重新配置RBNN,以实现具有相同参数集的M(m> 1)不同的任务,因此只有一个任务决定了内存要求。换句话说,通过时间M改善了内存利用率。我们的广泛实验证实了多达七个常用的任务可以共存(M的值更大)。这些具有不同类别的任务在三个二氧化流行的DNN体系结构(包括VGG,Resnet和ReactNet)上没有准确性或微不足道的准确性下降。这些任务跨越了不同域,例如本文验证的计算机视觉和音频域,并以模型体系结构可以服务于这些跨域任务的先决条件。为了保护RBNN模型的知识属性,可以通过用户密钥和由固有硬件指纹生成的设备唯一的根键来控制重新配置。通过这样做,RBNN模型只能使用每个授权设备的每个付费用户使用,从而使用户和模型提供商受益。
translated by 谷歌翻译
A recent trojan attack on deep neural network (DNN) models is one insidious variant of data poisoning attacks. Trojan attacks exploit an effective backdoor created in a DNN model by leveraging the difficulty in interpretability of the learned model to misclassify any inputs signed with the attacker's chosen trojan trigger. Since the trojan trigger is a secret guarded and exploited by the attacker, detecting such trojan inputs is a challenge, especially at run-time when models are in active operation. This work builds STRong Intentional Perturbation (STRIP) based run-time trojan attack detection system and focuses on vision system. We intentionally perturb the incoming input, for instance by superimposing various image patterns, and observe the randomness of predicted classes for perturbed inputs from a given deployed model-malicious or benign. A low entropy in predicted classes violates the input-dependence property of a benign model and implies the presence of a malicious input-a characteristic of a trojaned input. The high efficacy of our method is validated through case studies on three popular and contrasting datasets: MNIST, CIFAR10 and GTSRB. We achieve an overall false acceptance rate (FAR) of less than 1%, given a preset false rejection rate (FRR) of 1%, for different types of triggers. Using CIFAR10 and GTSRB, we have empirically achieved result of 0% for both FRR and FAR. We have also evaluated STRIP robustness against a number of trojan attack variants and adaptive attacks.
translated by 谷歌翻译
In this paper, we study the problem of knowledge-intensive text-to-SQL, in which domain knowledge is necessary to parse expert questions into SQL queries over domain-specific tables. We formalize this scenario by building a new Chinese benchmark KnowSQL consisting of domain-specific questions covering various domains. We then address this problem by presenting formulaic knowledge, rather than by annotating additional data examples. More concretely, we construct a formulaic knowledge bank as a domain knowledge base and propose a framework (ReGrouP) to leverage this formulaic knowledge during parsing. Experiments using ReGrouP demonstrate a significant 28.2% improvement overall on KnowSQL.
translated by 谷歌翻译
Weakly-supervised object localization aims to indicate the category as well as the scope of an object in an image given only the image-level labels. Most of the existing works are based on Class Activation Mapping (CAM) and endeavor to enlarge the discriminative area inside the activation map to perceive the whole object, yet ignore the co-occurrence confounder of the object and context (e.g., fish and water), which makes the model inspection hard to distinguish object boundaries. Besides, the use of CAM also brings a dilemma problem that the classification and localization always suffer from a performance gap and can not reach their highest accuracy simultaneously. In this paper, we propose a casual knowledge distillation method, dubbed KD-CI-CAM, to address these two under-explored issues in one go. More specifically, we tackle the co-occurrence context confounder problem via causal intervention (CI), which explores the causalities among image features, contexts, and categories to eliminate the biased object-context entanglement in the class activation maps. Based on the de-biased object feature, we additionally propose a multi-teacher causal distillation framework to balance the absorption of classification knowledge and localization knowledge during model training. Extensive experiments on several benchmarks demonstrate the effectiveness of KD-CI-CAM in learning clear object boundaries from confounding contexts and addressing the dilemma problem between classification and localization performance.
translated by 谷歌翻译