3 citations · 3 across the 6 of their papers we have counts for
6 papers
Safety Monitoring for Learning-Enabled Cyber-Physical Systems in Out-of-Distribution Scenarios
Vivian Lin, Ramneet Kaur, Yahan Yang +6
The safety of learning-enabled cyber-physical systems is compromised by the well-known vulnerabilities of deep neural networks to out-of-distribution (OOD) inputs. Existing literat…
MrGuard: A Multilingual Reasoning Guardrail for Universal LLM Safety
Yahan Yang, Soham Dan, Shuo Li +2
Large Language Models (LLMs) are susceptible to adversarial attacks such as jailbreaking, which can elicit harmful or unsafe behaviors. This vulnerability is exacerbated in multili…
Benchmarking LLM Guardrails in Handling Multilingual Toxicity
Yahan Yang, Soham Dan, Dan Roth +1
With the ubiquity of Large Language Models (LLMs), guardrails have become crucial to detect and defend against toxic content. However, with the increasing pervasiveness of LLMs in…
On the Calibration of Multilingual Question Answering LLMs
Yahan Yang, Soham Dan, Dan Roth +1
Multilingual pre-trained Large Language Models (LLMs) are incredibly effective at Question Answering (QA), a core task in Natural Language Understanding, achieving high accuracies…
In and Out-of-Domain Text Adversarial Robustness via Label Smoothing
Yahan Yang, Soham Dan, Dan Roth +1
Recently it has been shown that state-of-the-art NLP models are vulnerable to adversarial attacks, where the predictions of a model can be drastically altered by slight modificatio…
Real-Time Detectors for Digital and Physical Adversarial Inputs to Perception Systems
Yiannis Kantaros, Taylor Carpenter, Kaustubh Sridhar +3
Deep neural network (DNN) models have proven to be vulnerable to adversarial digital and physical attacks. In this paper, we propose a novel attack- and dataset-agnostic and real-t…