5 papers
Stylometric Defenses Against Author Impersonation in Software Repositories
Leonid Ravich, Michael Fire
Software supply-chain attacks increasingly exploit an identity gap where compromised maintainer accounts authorize malicious changes. This work evaluates patch-level authorship ver…
Sympathetic Framing: Evaluating AI Alignment across Sociodemographic Groups
Haran Shani-Narkiss, Michael Fire, Oren Tsur
Large Language Models (LLMs) are increasingly shaping how we consume information and form our worldview. This raises concerns beyond bias in AI: do LLMs grasp the emotional nuances…
Gender Gap Analysis in News and Talk Online Radio Broadcast
Gregory Koushnir, Michael Fire, Dima Kagan +1
Radio broadcasting remains a dominant medium of communication, reaching 82% of Americans ages 12 and older weekly. Given its broad media impact, gender representation on radio news…
Dark LLMs: The Growing Threat of Unaligned AI Models
Michael Fire, Yitzhak Elbazis, Adi Wasenstein +1
Large Language Models (LLMs) rapidly reshape modern life, advancing fields from healthcare to education and beyond. However, alongside their remarkable capabilities lies a signific…
VANPY: Voice Analysis Framework
Gregory Koushnir, Michael Fire, Galit Fuhrmann Alpert +1
Voice data is increasingly being used in modern digital communications, yet there is still a lack of comprehensive tools for automated voice analysis and characterization. To this…