Zobrazeno 1 - 10
of 9 477
pro vyhledávání: '"Aylin, P."'
This paper considers an information theoretic model of secure integrated sensing and communication, represented as a wiretap channel with action dependent states. This model allows securing part of a transmitted message against a sensed target that e
Externí odkaz:
http://arxiv.org/abs/2409.04619
We consider a secure integrated sensing and communication (ISAC) scenario, in which a signal is transmitted through a state-dependent wiretap channel with one legitimate receiver with which the transmitter communicates and one honest-but-curious targ
Externí odkaz:
http://arxiv.org/abs/2408.17050
Publikováno v:
2024 IEEE International Symposium on Information Theory (ISIT), Athens, Greece, 2024, pp. 2580-2585
This work models a secure integrated sensing and communication (ISAC) system as a wiretap channel with action-dependent channel states and channel output feedback, e.g., obtained through reflections. The transmitted message is split into a common and
Externí odkaz:
http://arxiv.org/abs/2408.13635
Though research into text-to-image generators (T2Is) such as Stable Diffusion has demonstrated their amplification of societal biases and potentials to cause harm, such research has primarily relied on computational methods instead of seeking informa
Externí odkaz:
http://arxiv.org/abs/2408.01594
Autor:
Nicolas, Gandalf, Caliskan, Aylin
This study introduces a taxonomy of stereotype content in contemporary large language models (LLMs). We prompt ChatGPT 3.5, Llama 3, and Mixtral 8x7B, three powerful and widely used LLMs, for the characteristics associated with 87 social categories (
Externí odkaz:
http://arxiv.org/abs/2408.00162
Autor:
Wilson, Kyra, Caliskan, Aylin
Artificial intelligence (AI) hiring tools have revolutionized resume screening, and large language models (LLMs) have the potential to do the same. However, given the biases which are embedded within LLMs, it is unclear whether they can be used in th
Externí odkaz:
http://arxiv.org/abs/2407.20371
Our research investigates the impact of Generative Artificial Intelligence (GAI) models, specifically text-to-image generators (T2Is), on the representation of non-Western cultures, with a focus on Indian contexts. Despite the transformative potentia
Externí odkaz:
http://arxiv.org/abs/2407.14779
Existing works examining Vision-Language Models (VLMs) for social biases predominantly focus on a limited set of documented bias associations, such as gender:profession or race:crime. This narrow scope often overlooks a vast range of unexamined impli
Externí odkaz:
http://arxiv.org/abs/2407.02066
Large Language Models (LLMs) perpetuate social biases, reflecting prejudices in their training data and reinforcing societal stereotypes and inequalities. Our work explores the potential of the Contact Hypothesis, a concept from social psychology for
Externí odkaz:
http://arxiv.org/abs/2407.02030
How good a research scientist is ChatGPT? We systematically probed the capabilities of GPT-3.5 and GPT-4 across four central components of the scientific process: as a Research Librarian, Research Ethicist, Data Generator, and Novel Data Predictor, u
Externí odkaz:
http://arxiv.org/abs/2406.14765