Philip Feldman
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Philip Feldman has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Aaron Dant
ASRC Federal, US
2 shared publications - Jarod Govers
School of Computing and Information Systems, University of Melbourne, Melbourne, Victoria, Australia
2 shared publications - Panos Patros
Department of Software Engineering, University of Waikato, Hamilton, New Zealand
2 shared publications - Antonio Bucchiarone
University of L'Aquila, L'Aquila, Italy
1 shared publication - James Foulds
University of Maryland Baltimore County USA
1 shared publication Sandro Battisti
Fondazione Bruno Kessler, Trento, Italy
1 shared publication
Latest Publications
- Open Access
- 8 July 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-5
The Voice: Lessons on Trustworthy Conversational Agents from 'Dune'
The potential for untrustworthy conversational agents presents a significant threat for covert social manipulation. Taking inspiration from Frank Herbert’s Dune [12], where the Bene Gesserit Sisterhood uses the Voice for influence, manipulation, and control of people, we explore how generative AI provides a way to implement individualized influence at industrial scales. Already, these models can manipulate communication across text, image, speech, and most recently video. They are rapidly becoming affordable enough for any organization of even moderate means to train and deploy. If employed by malicious actors, they risk becoming powerful tools for shaping public opinion, sowing discord, and undermining organizations from companies to governments. As researchers and developers, it is crucial to recognize the potential for such weaponization and to explore strategies for prevention, detection, and defense against these emerging forms of sociotechnical manipulation.
- 8 July 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-5
Open AccessThe Voice: Lessons on Trustworthy Conversational Agents from 'Dune'
The potential for untrustworthy conversational agents presents a significant threat for covert social manipulation. Taking inspiration from Frank Herbert’s Dune [12], where the Bene Gesserit Sisterhood uses the Voice for influence, manipulation, and control of people, we explore how generative AI provides a way to implement individualized influence at industrial scales. Already, these models can manipulate communication across text, image, speech, and most recently video. They are rapidly becoming affordable enough for any organization of even moderate means to train and deploy. If employed by malicious actors, they risk becoming powerful tools for shaping public opinion, sowing discord, and undermining organizations from companies to governments. As researchers and developers, it is crucial to recognize the potential for such weaponization and to explore strategies for prevention, detection, and defense against these emerging forms of sociotechnical manipulation.
- Open Access
- 17 July 2023
- Published by Association for Computing Machinery (ACM) in ACM Computing Surveys
- Vol. 55 (14s) , 1-35
Down the Rabbit Hole: Detecting Online Extremism, Radicalisation, and Politicised Hate Speech
Social media is a modern person’s digital voice to project and engage with new ideas and mobilise communities—a power shared with extremists. Given the societal risks of unvetted content-moderating algorithms forExtremism, Radicalisation,andHate speech(ERH)detection, responsible software engineering must understand the who, what, when, where, and why such models are necessary to protect user safetyandfree expression. Hence, we propose and examine the unique research field ofERH context miningto unify disjoint studies. Specifically, we evaluate the start-to-finish design process from socio-technical definition-building and dataset collection strategies to technical algorithm design and performance. Our 2015–2021 51-studySystematic Literature Review (SLR)provides the first cross-examination of textual, network, and visual approaches to detectingextremistaffiliation,hatefulcontent, andradicalisationtowards groups and movements. We identify consensus-driven ERH definitions and propose solutions to existing ideological and geographic biases, particularly due to the lack of research in Oceania/Australasia. Our hybridised investigation on Natural Language Processing, Community Detection, and visual-text models demonstrates the dominating performance of textual transformer-based algorithms. We conclude with vital recommendations for ERH context mining researchers and propose an uptake roadmap with guidelines for researchers, industries, and governments to enable a safer cyberspace.
- 17 July 2023
- Published by Association for Computing Machinery (ACM) in ACM Computing Surveys
- Vol. 55 (14s) , 1-35
Open AccessDown the Rabbit Hole: Detecting Online Extremism, Radicalisation, and Politicised Hate Speech
Social media is a modern person’s digital voice to project and engage with new ideas and mobilise communities—a power shared with extremists. Given the societal risks of unvetted content-moderating algorithms forExtremism, Radicalisation,andHate speech(ERH)detection, responsible software engineering must understand the who, what, when, where, and why such models are necessary to protect user safetyandfree expression. Hence, we propose and examine the unique research field ofERH context miningto unify disjoint studies. Specifically, we evaluate the start-to-finish design process from socio-technical definition-building and dataset collection strategies to technical algorithm design and performance. Our 2015–2021 51-studySystematic Literature Review (SLR)provides the first cross-examination of textual, network, and visual approaches to detectingextremistaffiliation,hatefulcontent, andradicalisationtowards groups and movements. We identify consensus-driven ERH definitions and propose solutions to existing ideological and geographic biases, particularly due to the lack of research in Oceania/Australasia. Our hybridised investigation on Natural Language Processing, Community Detection, and visual-text models demonstrates the dominating performance of textual transformer-based algorithms. We conclude with vital recommendations for ERH context mining researchers and propose an uptake roadmap with guidelines for researchers, industries, and governments to enable a safer cyberspace.
- Open Access
- 27 March 2023
- Published by Association for Computing Machinery (ACM)
- p. 21-24
The Keyword Explorer Suite: A Toolkit for Understanding Online Populations
We have developed a set of Python applications that use large language models to identify and analyze data from social media platforms relevant to a population of interest. Our pipeline begins with using OpenAI’s GPT-3 to generate potential keywords for identifying relevant text content from the target population. The keywords are then validated, and the content downloaded and analyzed using GPT-3 embedding and manifold reduction. Corpora are then created to fine-tune GPT-2 models to explore latent information via prompt-based queries. These tools allow researchers and practitioners to gain valuable insights into population subgroups online.
- 27 March 2023
- Published by Association for Computing Machinery (ACM)
- p. 21-24
Open AccessThe Keyword Explorer Suite: A Toolkit for Understanding Online Populations
We have developed a set of Python applications that use large language models to identify and analyze data from social media platforms relevant to a population of interest. Our pipeline begins with using OpenAI’s GPT-3 to generate potential keywords for identifying relevant text content from the target population. The keywords are then validated, and the content downloaded and analyzed using GPT-3 embedding and manifold reduction. Corpora are then created to fine-tune GPT-2 models to explore latent information via prompt-based queries. These tools allow researchers and practitioners to gain valuable insights into population subgroups online.
- Open Access
- 17 March 2023
- Published by Association for Computing Machinery (ACM)
- p. 515-522
Prompt-GAN–Customisable Hate Speech and Extremist Datasets via Radicalised Neural Language Models
Online hate speech and violent extremism knows no borders, no political boundaries, no remorse. Researchers face an uphill battle to collect hate speech data in volumes and topical diversity suitable for training state-of-the-art content-moderation systems. Neural language models ushered in a new era of synthetic data generation in use across various businesses, all despite calls for research to protect against unintended toxic output. We present a method for radicalising pre-trained neural language models to identify real hate speech and highlight the risks of AI which could undermine our trust in social media. We present Prompt-GAN, a prompt-tuning adversarial approach with three achievements. Namely, we demonstrate prompt-tuning’s ability to generate realistic types of hate and non-hate speech which mimics political extremist discourse. Prompt-GAN’s architecture offers a twofold reduction in memory and runtime requirements compared to fine-tuning. Prompt-GAN improves hate speech classification F1-scores by up to 10.1% and sets a new record in neural language simulation compared to the current state-of-the-art across three benchmark social media datasets.
- 17 March 2023
- Published by Association for Computing Machinery (ACM)
- p. 515-522
Open AccessPrompt-GAN–Customisable Hate Speech and Extremist Datasets via Radicalised Neural Language Models
Online hate speech and violent extremism knows no borders, no political boundaries, no remorse. Researchers face an uphill battle to collect hate speech data in volumes and topical diversity suitable for training state-of-the-art content-moderation systems. Neural language models ushered in a new era of synthetic data generation in use across various businesses, all despite calls for research to protect against unintended toxic output. We present a method for radicalising pre-trained neural language models to identify real hate speech and highlight the risks of AI which could undermine our trust in social media. We present Prompt-GAN, a prompt-tuning adversarial approach with three achievements. Namely, we demonstrate prompt-tuning’s ability to generate realistic types of hate and non-hate speech which mimics political extremist discourse. Prompt-GAN’s architecture offers a twofold reduction in memory and runtime requirements compared to fine-tuning. Prompt-GAN improves hate speech classification F1-scores by up to 10.1% and sets a new record in neural language simulation compared to the current state-of-the-art across three benchmark social media datasets.
- 30 March 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 22 (4) , 2008-2012
Guest Editorial Diversification in Urban Transportation Systems and Beyond: Integrating People and Goods for the Future of Mobility
The increasing growing need for optimization of transportation in a sustainable and green environment is fundamental for the future of mobility. Companies, governments, and non-governmental institutions are trying to find new ways to contribute to this challenge. In particular, the approach is to improve the efficiency and the quality of the movement of diversification of an integrated way of transportation of people and goods. Many people may need to be at some location at some point in time, or many goods may need to be transported to nearby destinations with the same packaging conditions. The main goal of this Special Issue was to integrate the most recent advances in transportation that connect the hybrid point of view. In particular, key contributions integrate several interesting topics related to earning algorithms for the integration of passengers and goods, gamification techniques, semantic data, blockchain, and edge computing. Other topics in urban mobility, railway, and highways were considered, and hot topics on shared autonomous vehicles (SAVs) brought huge value. Moreover, the Internet of Things (IoT) opens the doors for new development in Vehicle to Everything (V2X), which are crucial for the development of new services that generate business and social impact in the future of a diversified way of the integration of passengers and goods mobility.
- 30 March 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 22 (4) , 2008-2012
Guest Editorial Diversification in Urban Transportation Systems and Beyond: Integrating People and Goods for the Future of Mobility
The increasing growing need for optimization of transportation in a sustainable and green environment is fundamental for the future of mobility. Companies, governments, and non-governmental institutions are trying to find new ways to contribute to this challenge. In particular, the approach is to improve the efficiency and the quality of the movement of diversification of an integrated way of transportation of people and goods. Many people may need to be at some location at some point in time, or many goods may need to be transported to nearby destinations with the same packaging conditions. The main goal of this Special Issue was to integrate the most recent advances in transportation that connect the hybrid point of view. In particular, key contributions integrate several interesting topics related to earning algorithms for the integration of passengers and goods, gamification techniques, semantic data, blockchain, and edge computing. Other topics in urban mobility, railway, and highways were considered, and hot topics on shared autonomous vehicles (SAVs) brought huge value. Moreover, the Internet of Things (IoT) opens the doors for new development in Vehicle to Everything (V2X), which are crucial for the development of new services that generate business and social impact in the future of a diversified way of the integration of passengers and goods mobility.
- Open Access
- 1 January 2018
- Published by Association for Computing Machinery (ACM)
- p. 351-353
With Maps and Mobs
- 1 January 2018
- Published by Association for Computing Machinery (ACM)
- p. 351-353
Open AccessWith Maps and Mobs
- 25 June 1993
- Published by Cambridge University Press (CUP)
- p. 410-424
Crime prevention
The Psychology of Crime - June 1993
- 25 June 1993
- Published by Cambridge University Press (CUP)
- p. 410-424
Crime prevention
The Psychology of Crime - June 1993