1 citations · 1 across the 7 of their papers we have counts for
7 papers
Beyond Aggregate Scores: Behavioral Correctness Assumptions for Assessing Reference-Based Automatic Evaluation Methods
Maria Mahbub, Ashley Rice, Michael R. Munroe +2
Automated reference-based evaluation methods play a critical role in assessing natural language generation systems. Existing meta-evaluation primarily measures agreement with human…
Reducing Catastrophic Risk from AI with Systematic Monitoring and Evaluation of Rogue AI Progression
T. Bauer, W. P. Kegelmeyer, E. Begoli +15
This article presents a structured framework of behavioral indicators that may signal progression toward potentially catastrophic threats from artificial intelligence systems. We a…
Signal-based Model Access Risk Analysis for AI System Operations Security
Maria Mahbub, Steven Young, Amir Sadovnik +4
Artificial intelligence (AI) systems are now ubiquitous across domains such as security, finance, healthcare, consumer technology, and large-scale cloud services, where they proces…
The Black Tuesday Attack: how to crash the stock market with adversarial examples to financial forecasting models
Thomas Hofweber, Jefrey Bergl, Ian Reyes +1
We investigate and defend the possibility of causing a stock market crash via small manipulations of individual stock values that together realize an adversarial example to financi…
AI-generated Image Detection: Passive or Watermark?
Moyang Guo, Yuepeng Hu, Zhengyuan Jiang +4
While text-to-image models offer numerous benefits, they also pose significant societal risks. Detecting AI-generated images is crucial for mitigating these risks. Detection method…
Advancing NLP Security by Leveraging LLMs as Adversarial Engines
Sudarshan Srinivasan, Maria Mahbub, Amir Sadovnik
This position paper proposes a novel approach to advancing NLP security by leveraging Large Language Models (LLMs) as engines for generating diverse adversarial attacks. Building u…
Hiding-in-Plain-Sight (HiPS) Attack on CLIP for Targetted Object Removal from Images
Arka Daw, Megan Hong-Thanh Chung, Maria Mahbub +1
Machine learning models are known to be vulnerable to adversarial attacks, but traditional attacks have mostly focused on single-modalities. With the rise of large multi-modal mode…