16 papers
Security and Privacy in Agentic AI: Grand Challenges and Future Directions
Adam Jenkins, Agnieszka Kitkowska, Caterina Maidhof +22
We present key challenges and future research directions in the security and privacy of agentic AI, based on a horizon-scanning exercise that brought together thirty leading intern…
CASE-Bench: Context-Aware SafEty Benchmark for Large Language Models
Guangzhi Sun, Xiao Zhan, Shutong Feng +2
Aligning large language models (LLMs) with human values is essential for their safe deployment and widespread adoption. Current LLM safety benchmarks often focus solely on the refu…
Beliefs and Misconceptions around Integrated Conversational AI
William Seymour, Adam Jenkins, Mark Cote +1
LLM-driven conversational AI is beginning to disappear into the background, shifting from something used directly towards something increasingly integrated into existing workflows.…
Unweighted ranking for value-based decision making with uncertainty
Aarón López GarcÃa, Natalia Criado, Jose Such
As intelligent systems are increasingly implemented in our society to make autonomous decisions, their commitment to human values raises serious concerns. Their alignment with huma…
Protecting Bystander Privacy via Selective Hearing in Audio LLMs
Xiao Zhan, Guangzhi Sun, Jose Such +1
Audio Large language models (LLMs) are increasingly deployed in the real world, where they inevitably capture speech from unintended nearby bystanders, raising privacy risks that e…
Privacy and Safety Experiences and Concerns of U.S. Women Using Generative AI for Seeking Sexual and Reproductive Health Information
Ina Kaleva, Xiao Zhan, Ruba Abu-Salma +1
The rapid adoption of generative AI (GenAI) chatbots has reshaped access to sexual and reproductive health (SRH) information, particularly following the overturning of Roe v. Wade,…