Bryan A. Liang
YOU?
Author Swipe
View article: SECA: Semantically Equivalent and Coherent Attacks for Eliciting LLM Hallucinations
SECA: Semantically Equivalent and Coherent Attacks for Eliciting LLM Hallucinations Open
Large Language Models (LLMs) are increasingly deployed in high-risk domains. However, state-of-the-art LLMs often produce hallucinations, raising serious concerns about their reliability. Prior work has explored adversarial attacks for hal…
View article: KDA: A Knowledge-Distilled Attacker for Generating Diverse Prompts to Jailbreak LLMs
KDA: A Knowledge-Distilled Attacker for Generating Diverse Prompts to Jailbreak LLMs Open
Jailbreak attacks exploit specific prompts to bypass LLM safeguards, causing the LLM to generate harmful, inappropriate, and misaligned content. Current jailbreaking methods rely heavily on carefully designed system prompts and numerous qu…
View article: Combinatorial Wnt signaling determines wing margin color patterns of the swallowtail butterfly ground plan
Combinatorial Wnt signaling determines wing margin color patterns of the swallowtail butterfly ground plan Open
The intricate wing patterns of butterflies are thought to derive from a morphological ground plan that anchors homology relationships between individual color pattern elements and serves as an archetype for comparative analysis. These patt…
View article: Assessing Characteristics and Compliance of Online Delta-8 Tetrahydrocannabinol Product Sellers
Assessing Characteristics and Compliance of Online Delta-8 Tetrahydrocannabinol Product Sellers Open
Introduction: The debate over the legal status of many cannabis- and hemp-derived products, including delta-8 tetrahydrocannabinol (THC), is in question. Although low concentrations of delta-8 THC are legal at the Federal level, many state…
View article: Big Data, Natural Language Processing, and Deep Learning to Detect and Characterize Illicit COVID-19 Product Sales: Infoveillance Study on Twitter and Instagram
Big Data, Natural Language Processing, and Deep Learning to Detect and Characterize Illicit COVID-19 Product Sales: Infoveillance Study on Twitter and Instagram Open
Background The coronavirus disease (COVID-19) pandemic is perhaps the greatest global health challenge of the last century. Accompanying this pandemic is a parallel “infodemic,” including the online marketing and sale of unapproved, illega…
View article: Machine Learning to Detect Self-Reporting of Symptoms, Testing Access, and Recovery Associated With COVID-19 on Twitter: Retrospective Big Data Infoveillance Study
Machine Learning to Detect Self-Reporting of Symptoms, Testing Access, and Recovery Associated With COVID-19 on Twitter: Retrospective Big Data Infoveillance Study Open
Background The coronavirus disease (COVID-19) pandemic is a global health emergency with over 6 million cases worldwide as of the beginning of June 2020. The pandemic is historic in scope and precedent given its emergence in an increasingl…
View article: Big Data, Natural Language Processing, and Deep Learning to Detect and Characterize Illicit COVID-19 Product Sales: Infoveillance Study on Twitter and Instagram (Preprint)
Big Data, Natural Language Processing, and Deep Learning to Detect and Characterize Illicit COVID-19 Product Sales: Infoveillance Study on Twitter and Instagram (Preprint) Open
BACKGROUND The coronavirus disease (COVID-19) pandemic is perhaps the greatest global health challenge of the last century. Accompanying this pandemic is a parallel “infodemic,” including the online marketing and sale of unapproved, illeg…
View article: Machine Learning to Detect Self-Reporting of Symptoms, Testing Access, and Recovery Associated With COVID-19 on Twitter: Retrospective Big Data Infoveillance Study (Preprint)
Machine Learning to Detect Self-Reporting of Symptoms, Testing Access, and Recovery Associated With COVID-19 on Twitter: Retrospective Big Data Infoveillance Study (Preprint) Open
BACKGROUND The coronavirus disease (COVID-19) pandemic is a global health emergency with over 6 million cases worldwide as of the beginning of June 2020. The pandemic is historic in scope and precedent given its emergence in an increasing…