Related papers: Transparent Object Proxies for JavaScript
Anonymous messaging platforms, such as Secret and Whisper, have emerged as important social media for sharing one's thoughts without the fear of being judged by friends, family, or the public. Further, such anonymous platforms are crucial…
A key challenge in censorship-resistant web browsing is being able to direct legitimate users to redirection proxies while preventing censors, posing as insiders, from discovering their addresses and blocking them. We propose a new…
The need for transparency of predictive systems based on Machine Learning algorithms arises as a consequence of their ever-increasing proliferation in the industry. Whenever black-box algorithmic predictions influence human affairs, the…
AI systems have been known to amplify biases in real-world data. Explanations may help human-AI teams address these biases for fairer decision-making. Typically, explanations focus on salient input features. If a model is biased against…
Recent data-extraction attacks have exposed that language models can memorize some training samples verbatim. This is a vulnerability that can compromise the privacy of the model's training data. In this work, we introduce SubMix: a…
Free web proxies promise anonymity and censorship circumvention at no cost. Several websites publish lists of free proxies organized by country, anonymity level, and performance. These lists index hundreds of thousand of hosts discovered…
Object detection is a crucial task in autonomous driving. While existing research has proposed various attacks on object detection, such as those using adversarial patches or stickers, the exploration of projection attacks on 3D surfaces…
Internet censors seek ways to identify and block internet access to information they deem objectionable. Increasingly, censors deploy advanced networking tools such as deep-packet inspection (DPI) to identify such connections. In response,…
Post-hoc explanations provide transparency and are essential for guiding model optimization, such as prompt engineering and data sanitation. However, applying model-agnostic techniques to Large Language Models (LLMs) is hindered by…
Concerns for the privacy of individuals captured in public imagery have led to privacy-preserving action recognition. Existing approaches often suffer from issues arising through obfuscation being applied globally and a lack of…
Personalizing diffusion models allows users to generate new images that incorporate a given subject, allowing more control than a text prompt. These models often suffer somewhat when they end up just recreating the subject image and…
Emerging scholarship suggests that the EU legal concept of direct discrimination - where a person is given different treatment on grounds of a protected characteristic - may apply to various algorithmic decision-making contexts. This has…
Explainable Artificial Intelligence (XAI) is essential for building advanced machine learning-powered applications, especially in critical domains such as medical diagnostics or autonomous driving. Legal, business, and ethical requirements…
Parallel programs require software support to coordinate access to shared data. For this purpose, modern programming languages provide strongly-consistent shared objects. To account for their many usages, these objects offer a large API.…
Network traffic inspection, including TLS traffic, in enterprise environments is widely practiced. Reasons for doing so are primarily related to improving enterprise security (e.g., malware detection) and meeting legal requirements. To…
The benefits of utilizing spatial context in fast object detection algorithms have been studied extensively. Detectors increase inference speed by doing a single forward pass per image which means they implicitly use contextual reasoning…
Transparency - the provision of information about what personal data is collected for which purposes, how long it is stored, or to which parties it is transferred - is one of the core privacy principles underlying regulations such as the…
In order to be useful in the real world, AI agents need to plan and act in the presence of others, who may include adversarial and cooperative entities. In this paper, we consider the problem where an autonomous agent needs to act in a…
Self-supervised learning (SSL) aims to produce useful feature representations without access to any human-labeled data annotations. Due to the success of recent SSL methods based on contrastive learning, such as SimCLR, this problem has…
Transparency is an essential requirement of machine learning based decision making systems that are deployed in real world. Often, transparency of a given system is achieved by providing explanations of the behavior and predictions of the…