arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2204.02494cs.CVcs.CR
收藏

利用解纠缠表示改进低数据量下基于视觉的击键推理攻击

Leveraging Disentangled Representations to Improve Vision-Based Keystroke Inference Attacks Under Low Data

UNC Chapel Hill(北卡罗来纳大学教堂山分校)

John Lim, Jan-Michael Frahm, Fabian Monrose

摘要:

击键推断攻击是侧信道攻击的一种形式,其中攻击者利用各种技术来在用户将信息输入到某个显示器(例如,同时发送文本消息或输入她的PIN)。通常,这些攻击利用机器学习方法,但评估威胁空间的真实性已经落后于机器学习进步的步伐,部分原因是管理大型现实生活数据集的挑战。我们的目标是通过引入视频领域自适应技术,能够利用合成数据,通过监督分离学习,以克服具有有限数量的实际数据的挑战。具体来说,对于一个给定的域,我们将观察到的数据分解为两个变化因素:风格和内容。这样做提供了四种学习表示:现实生活风格,合成风格,现实生活内容和合成内容。然后,我们将它们组合成来自跨域的样式-内容配对的所有组合的特征表示,并在这些组合表示上训练模型以对内容进行分类(即,标签)的一个给定的数据点在另一个域的风格。我们使用各种指标来量化攻击者能够恢复的信息量,从而评估我们在现实数据上的方法。我们表明,我们的方法可以防止我们的模型过度拟合到一个小的真实训练集,这表明我们的方法是一种有效的数据增强形式,从而使反推理攻击更实用。

英文摘要:

Keystroke inference attacks are a form of side-channel attacks in which an attacker leverages various techniques to recover a user's keystrokes as she inputs information into some display (e.g., while sending a text message or entering her pin). Typically, these attacks leverage machine learning approaches, but assessing the realism of the threat space has lagged behind the pace of machine learning advancements, due in-part, to the challenges in curating large real-life datasets. We aim to overcome the challenge of having limited number of real data by introducing a video domain adaptation technique that is able to leverage synthetic data through supervised disentangled learning. Specifically, for a given domain, we decompose the observed data into two factors of variation: Style and Content. Doing so provides four learned representations: real-life style, synthetic style, real-life content and synthetic content. Then, we combine them into feature representations from all combinations of style-content pairings across domains, and train a model on these combined representations to classify the content (i.e., labels) of a given datapoint in the style of another domain. We evaluate our method on real-life data using a variety of metrics to quantify the amount of information an attacker is able to recover. We show that our method prevents our model from overfitting to a small real-life training set, indicating that our method is an effective form of data augmentation, thereby making keystroke inference attacks more practical.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑