Related papers: Secret-Keeping in Question Answering
Thousands of complex natural language questions are submitted to community question answering websites on a daily basis, rendering them as one of the most important information sources these days. However, oftentimes submitted questions are…
How does the extent to which a model is open or closed impact the scientific inferences that can be drawn from research that involves it? In this paper, we analyze how restrictions on information about model construction and deployment…
Question answering (QA) systems provide a way of querying the information available in various formats including, but not limited to, unstructured and structured data in natural languages. It constitutes a considerable part of…
Question generation has recently gained a lot of research interest, especially with the advent of large language models. In and of itself, question generation can be considered 'AI-hard', as there is a lack of unanimously agreed sense of…
Fact verification systems assess a claim's veracity based on evidence. An important consideration in designing them is faithfulness, i.e. generating explanations that accurately reflect the reasoning of the model. Recent works have focused…
Covert communication allows us to transmit messages in such a way that it is not possible to detect that the communication is occurring. This provides protection in situations where knowledge that people are talking to each other may be…
Interest in the field of Explainable Artificial Intelligence has been growing for decades and has accelerated recently. As Artificial Intelligence models have become more complex, and often more opaque, with the incorporation of complex…
We propose here to look at how abstract a model of a usable system can be, but still say something useful and interesting, so this paper is an exercise in abstraction and formalisation, with usability-of-design as an example target use. We…
Recent pretrained language models "solved" many reading comprehension benchmarks, where questions are written with access to the evidence document. However, datasets containing information-seeking queries where evidence documents are…
In this thesis we consider the problem of information hiding in the scenarios of interactive systems, statistical disclosure control, and refinement of specifications. We apply quantitative approaches to information flow in the first two…
Secrecy in communication systems is measured herein by the distortion that an adversary incurs. The transmitter and receiver share secret key, which they use to encrypt communication and ensure distortion at an adversary. A model is…
Information or data is very crucial resource to us. Thus securing the information becomes all the more necessary. The communication media through which we send data does not provide data security, so other methods of securing data are…
Inspired by privacy problems where the behavior of a system should not be revealed to an external curious observer, we investigate event concealment and concealability enforcement in discrete event systems modeled as non-deterministic…
In this paper, we study a security problem of protecting secrets in distributed systems. Specifically, we employ discrete-event systems to describe the structure and behaviour of distributed systems, in which global secret information is…
A hallmark of human intelligence is the ability to ask rich, creative, and revealing questions. Here we introduce a cognitive model capable of constructing human-like questions. Our approach treats questions as formal programs that, when…
"What Should be Hidden and Open in Computer Security: Lessons from Deception, the Art of War, Law, and Economic Theory" Peter P. Swire, George Washington University. Imagine a military base. It is defended against possible attack. Do we…
Machine learning systems can help humans to make decisions by providing decision suggestions (i.e., a label for a datapoint). However, individual datapoints do not always provide enough clear evidence to make confident suggestions. Although…
Question Answering (QA) is not a new research field in Natural Language Processing (NLP). However in recent years, QA has been a subject of growing study. Nowadays, most of the QA systems have a similar pipelined architecture and each…
Our goal is a question-answering (QA) system that can show how its answers are implied by its own internal beliefs via a systematic chain of reasoning. Such a capability would allow better understanding of why a model produced the answer it…
The opaque nature of many intelligent systems violates established usability principles and thus presents a challenge for human-computer interaction. Research in the field therefore highlights the need for transparency, scrutability,…