Related papers: Secret-Keeping in Question Answering
Communication is secret if a message is independent of the state; however, the receiver's subsequent action may still reveal that she has acted on hidden information. This paper studies when secret communication can also provide plausible…
Defensive deception is a promising approach for cyber defense. Via defensive deception, the defender can anticipate attacker actions; it can mislead or lure attacker, or hide real resources. Although defensive deception is increasingly…
Enabling open-domain dialogue systems to ask clarifying questions when appropriate is an important direction for improving the quality of the system response. Namely, for cases when a user request is not specific enough for a conversation…
Search and recommender systems that take the initiative to ask clarifying questions to better understand users' information needs are receiving increasing attention from the research community. However, to the best of our knowledge, there…
We introduce a cryptographic method to hide an arbitrary secret payload in the response of a Large Language Model (LLM). A secret key is required to extract the payload from the model's response, and without the key it is provably…
Ambiguous questions persist in open-domain question answering, because formulating a precise question with a unique answer is often challenging. Previously, Min et al. (2020) have tackled this issue by generating disambiguated questions for…
As machine learning becomes a more mainstream technology, the objective for governments and public sectors is to harness the power of machine learning to advance their mission by revolutionizing public services. Motivational government use…
We study a question answering problem on a social network, where a requester is seeking an answer from the agents on the network. The goal is to design reward mechanisms to incentivize the agents to propagate the requester's query to their…
Explainability has been an important goal since the early days of Artificial Intelligence. Several approaches for producing explanations have been developed. However, many of these approaches were tightly coupled with the capabilities of…
Although security questions are still widely adopted, they still have several limitations. Previous research found that using system-generated information to answer security questions could be more secure than users' own answers. However,…
Data for deep learning should be protected for privacy preserving. Researchers have come up with the notion of learnable image encryption to satisfy the requirement. However, existing privacy preserving approaches have never considered the…
This study investigates the relationship between resilience of control systems to attacks and the information available to malicious attackers. Specifically, it is shown that control systems are guaranteed to be secure in an asymptotic…
Why do language models trained on contradictory data prefer correct answers? In controlled experiments with small transformers (3.5M--86M parameters), we show that this preference tracks the compressibility structure of errors rather than…
Transparency and security are both central to Responsible AI, but they may conflict in adversarial settings. We investigate the strategic effect of transparency for agents through the lens of transferable adversarial example attacks. In…
Question Generation (QG) is a fundamental NLP task for many downstream applications. Recent studies on open-book QG, where supportive answer-context pairs are provided to models, have achieved promising progress. However, generating natural…
Quantum systems carry information. Quantum theory supports at least two distinct kinds of information (classical and quantum), and a variety of different ways to encode and preserve information in physical systems. A system's ability to…
Algorithms of inference in a computer system oriented to input and semantic processing of text information are presented. Such inference is necessary for logical questions when the direct comparison of objects from a question and database…
Many Question-Answering (QA) datasets contain unanswerable questions, but their treatment in QA systems remains primitive. Our analysis of the Natural Questions (Kwiatkowski et al. 2019) dataset reveals that a substantial portion of…
Modern AI systems are reaping the advantage of novel learning methods. With their increasing usage, we are realizing the limitations and shortfalls of these systems. Brittleness to minor adversarial changes in the input data, ability to…
Properties expressed as the provability of a first-order sentence can be disproved by just finding a model of the negation of the sentence. This fact, however, is meaningful in restricted cases only, depending on the shape of the sentence…