Digital Security Research Collaboratory Neu-Ulm
@dsrc.bsky.social
Research collaboratory at HNU, Germany, studying digital tech abuse to create safer online spaces. Views are our own, not the university’s.
Beyond hate speech, MAXplain enables rapid prototyping for other multimodal tasks — from misinformation detection to broader classification and evaluation tasks.
A step toward transparent, human-centered, and collaborative AI. 6/6
A step toward transparent, human-centered, and collaborative AI. 6/6
November 4, 2025 at 12:22 PM
Beyond hate speech, MAXplain enables rapid prototyping for other multimodal tasks — from misinformation detection to broader classification and evaluation tasks.
A step toward transparent, human-centered, and collaborative AI. 6/6
A step toward transparent, human-centered, and collaborative AI. 6/6
On the Hateful Memes benchmark, the multi-agent setup outperformed single-model baselines — showing higher F1 scores and how structured collaboration improves transparency and control. 5/6
November 4, 2025 at 12:22 PM
On the Hateful Memes benchmark, the multi-agent setup outperformed single-model baselines — showing higher F1 scores and how structured collaboration improves transparency and control. 5/6
The web interface (see diagram 👇) visualizes agent conversations, lets users create new agents, control workflows, and configure a shared rulebook.
A Chrome plugin enables one-click inspection of online posts. 4/6
A Chrome plugin enables one-click inspection of online posts. 4/6
November 4, 2025 at 12:22 PM
The web interface (see diagram 👇) visualizes agent conversations, lets users create new agents, control workflows, and configure a shared rulebook.
A Chrome plugin enables one-click inspection of online posts. 4/6
A Chrome plugin enables one-click inspection of online posts. 4/6
It splits the task into expert agents — e.g. a TargetingAgent for group detection, a CriticAgent to challenge outputs, and a central JudgeAgent that integrates all perspectives — explainable by design. 3/6
November 4, 2025 at 12:22 PM
It splits the task into expert agents — e.g. a TargetingAgent for group detection, a CriticAgent to challenge outputs, and a central JudgeAgent that integrates all perspectives — explainable by design. 3/6
Social media platforms face an overload of hateful memes and other multimodal content — combining text and images that challenge automated detection. MAXplain coordinates several specialized AI agents instead of one black box. 2/6
November 4, 2025 at 12:22 PM
Social media platforms face an overload of hateful memes and other multimodal content — combining text and images that challenge automated detection. MAXplain coordinates several specialized AI agents instead of one black box. 2/6
If effective, attitude inoculation could complement moderation — scalable, preventive, and psychologically grounded. A step toward prebunking social harms before they spread. 6/6
October 23, 2025 at 9:58 AM
If effective, attitude inoculation could complement moderation — scalable, preventive, and psychologically grounded. A step toward prebunking social harms before they spread. 6/6
The proposed 3×2 experiment compares:
- Basic rule reminders
- Netiquette education
- Future-oriented inoculation
… each in generic vs. specific forms. 5/6
- Basic rule reminders
- Netiquette education
- Future-oriented inoculation
… each in generic vs. specific forms. 5/6
October 23, 2025 at 9:58 AM
The proposed 3×2 experiment compares:
- Basic rule reminders
- Netiquette education
- Future-oriented inoculation
… each in generic vs. specific forms. 5/6
- Basic rule reminders
- Netiquette education
- Future-oriented inoculation
… each in generic vs. specific forms. 5/6
The study tests future-oriented inoculation by encouraging users to think long-term, reducing susceptibility to authoritarian and anti-democratic attitudes. 4/6
October 23, 2025 at 9:58 AM
The study tests future-oriented inoculation by encouraging users to think long-term, reducing susceptibility to authoritarian and anti-democratic attitudes. 4/6
Enter attitude inoculation: expose users to weak versions of manipulative content + refutations. Like a cognitive vaccine, it builds mental immunity against harmful ideas. 3/6
October 23, 2025 at 9:58 AM
Enter attitude inoculation: expose users to weak versions of manipulative content + refutations. Like a cognitive vaccine, it builds mental immunity against harmful ideas. 3/6
Social media moderation removes millions of posts — but harmful content persist. Platforms can’t catch them all, and deletion alone doesn’t change minds. 2/6
October 23, 2025 at 9:58 AM
Social media moderation removes millions of posts — but harmful content persist. Platforms can’t catch them all, and deletion alone doesn’t change minds. 2/6
If effective, attitude inoculation could complement moderation — scalable, preventive, and psychologically grounded. A step toward prebunking social harms before they spread. 6/6
October 23, 2025 at 9:40 AM
If effective, attitude inoculation could complement moderation — scalable, preventive, and psychologically grounded. A step toward prebunking social harms before they spread. 6/6
The proposed 3×2 experiment compares:
- Basic rule reminders
- Netiquette education
- Future-oriented inoculation
… each in generic vs. specific forms. 5/6
- Basic rule reminders
- Netiquette education
- Future-oriented inoculation
… each in generic vs. specific forms. 5/6
October 23, 2025 at 9:40 AM
The proposed 3×2 experiment compares:
- Basic rule reminders
- Netiquette education
- Future-oriented inoculation
… each in generic vs. specific forms. 5/6
- Basic rule reminders
- Netiquette education
- Future-oriented inoculation
… each in generic vs. specific forms. 5/6
The study tests future-oriented inoculation by encouraging users to think long-term, reducing susceptibility to authoritarian and anti-democratic attitudes. 4/6
October 23, 2025 at 9:40 AM
The study tests future-oriented inoculation by encouraging users to think long-term, reducing susceptibility to authoritarian and anti-democratic attitudes. 4/6
Enter attitude inoculation: expose users to weak versions of manipulative content + refutations. Like a cognitive vaccine, it builds mental immunity against harmful ideas. 3/6
October 23, 2025 at 9:40 AM
Enter attitude inoculation: expose users to weak versions of manipulative content + refutations. Like a cognitive vaccine, it builds mental immunity against harmful ideas. 3/6
Social media moderation removes millions of posts — but harmful content persist. Platforms can’t catch them all, and deletion alone doesn’t change minds. 2/6
October 23, 2025 at 9:40 AM
Social media moderation removes millions of posts — but harmful content persist. Platforms can’t catch them all, and deletion alone doesn’t change minds. 2/6
The full paper provides a unified framework grounded in homophily, distinguishing the two constructs and mapping their interdependence.
It also sets out a research agenda for future interdisciplinary work on measurement, mechanisms, and interventions. 6/6
It also sets out a research agenda for future interdisciplinary work on measurement, mechanisms, and interventions. 6/6
October 14, 2025 at 7:45 AM
The full paper provides a unified framework grounded in homophily, distinguishing the two constructs and mapping their interdependence.
It also sets out a research agenda for future interdisciplinary work on measurement, mechanisms, and interventions. 6/6
It also sets out a research agenda for future interdisciplinary work on measurement, mechanisms, and interventions. 6/6
Since both phenomena reinforce polarization and fragment democratic discourse, it is also on us to actively seek diverse perspectives and challenge our own biases. 5/6
October 14, 2025 at 7:45 AM
Since both phenomena reinforce polarization and fragment democratic discourse, it is also on us to actively seek diverse perspectives and challenge our own biases. 5/6
So while cocoons are about individual choice and self-selection, chambers are about group reinforcement and social dynamics.
The transition from individual-level cocoons to group-level chambers is a key unresolved question. 4/6
The transition from individual-level cocoons to group-level chambers is a key unresolved question. 4/6
October 14, 2025 at 7:45 AM
So while cocoons are about individual choice and self-selection, chambers are about group reinforcement and social dynamics.
The transition from individual-level cocoons to group-level chambers is a key unresolved question. 4/6
The transition from individual-level cocoons to group-level chambers is a key unresolved question. 4/6
While information cocoons are an individual-level phenomenon, echo chambers are a group-level phenomenon.
Through network homophily, members repeatedly reinforce shared beliefs and actively discredit opposing views. 3/6
Through network homophily, members repeatedly reinforce shared beliefs and actively discredit opposing views. 3/6
October 14, 2025 at 7:45 AM
While information cocoons are an individual-level phenomenon, echo chambers are a group-level phenomenon.
Through network homophily, members repeatedly reinforce shared beliefs and actively discredit opposing views. 3/6
Through network homophily, members repeatedly reinforce shared beliefs and actively discredit opposing views. 3/6
We tend to isolate ourselves from alternative perspectives by choosing information sources that match our personal beliefs (selective homophily).
This is called an information cocoon. Often it’s reinforced by algorithms. 2/6
This is called an information cocoon. Often it’s reinforced by algorithms. 2/6
October 14, 2025 at 7:45 AM
We tend to isolate ourselves from alternative perspectives by choosing information sources that match our personal beliefs (selective homophily).
This is called an information cocoon. Often it’s reinforced by algorithms. 2/6
This is called an information cocoon. Often it’s reinforced by algorithms. 2/6
We study these dynamics as an interdisciplinary team from a sociotechnical perspective working to create safer online spaces.
Here, we will share insights from our team and provide updates on what we are working on. 3/3
Here, we will share insights from our team and provide updates on what we are working on. 3/3
October 8, 2025 at 9:37 AM
We study these dynamics as an interdisciplinary team from a sociotechnical perspective working to create safer online spaces.
Here, we will share insights from our team and provide updates on what we are working on. 3/3
Here, we will share insights from our team and provide updates on what we are working on. 3/3
Our work focuses on some of the most pressing issues of digital technologies, including phenomena such as disinformation, online extremism, hate speech, information warfare and digital vigilantism. 2/3
October 8, 2025 at 9:37 AM
Our work focuses on some of the most pressing issues of digital technologies, including phenomena such as disinformation, online extremism, hate speech, information warfare and digital vigilantism. 2/3