5 papers
MAGICS: Adversarial RL with Minimax Actors Guided by Implicit Critic Stackelberg for Convergent Neural Synthesis of Robot Safety
Justin Wang, Haimin Hu, Duy Phuong Nguyen +1
While robust optimal control theory provides a rigorous framework to compute robot control policies that are provably safe, it struggles to scale to high-dimensional problems, lead…
AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents
Maksym Andriushchenko, Alexandra Souly, Mateusz Dziemian +11
The robustness of LLMs to jailbreak attacks, where users design prompts to circumvent safety measures and misuse model capabilities, has been studied primarily for LLMs acting as s…
GRASP: Municipal Budget AI Chatbots for Enhancing Civic Engagement
Jerry Xu, Justin Wang, Joley Leung +1
There are a growing number of AI applications, but none tailored specifically to help residents answer their questions about municipal budget, a topic most are interested in but fe…
Tamper-Resistant Safeguards for Open-Weight LLMs
Rishub Tamirisa, Bhrugu Bharathi, Long Phan +12
Rapid advances in the capabilities of large language models (LLMs) have raised widespread concerns regarding their potential for malicious use. Open-weight LLMs present unique chal…
Exploring Parent-Child Perceptions on Safety in Generative AI: Concerns, Mitigation Strategies, and Design Implications
Yaman Yu, Tanusree Sharma, Melinda Hu +2
The widespread use of Generative Artificial Intelligence (GAI) among teenagers has led to significant misuse and safety concerns. To identify risks and understand parental controls…