337 citations · 492 across the 9 of their papers we have counts for
11 papers
Security--Fidelity Tradeoffs: The Hidden Cost of Prompt Injection Defense
Mitchell Hermon, Rahul Gupta, Weitong Ruan +2
We identify a security-fidelity tradeoff in defending LLMs against indirect prompt injection: defenses resist injected instructions largely by suppressing untrusted text, which cor…
The Amazon Nova Family of Models: Technical Report and Model Card
Amazon AGI, Aaron Langford, Aayush Shah +783
We present Amazon Nova, a new generation of state-of-the-art foundation models that deliver frontier intelligence and industry-leading price performance. Amazon Nova Pro is a highl…
MONet: Multi-scale Overlap Network for Duplication Detection in Biomedical Images
Ekraam Sabir, Soumyaroop Nandi, Wael AbdAlmageed +1
Manipulation of biomedical images to misrepresent experimental results has plagued the biomedical community for a while. Recent interest in the problem led to the curation of a dat…
BioFors: A Large Biomedical Image Forensics Dataset
Ekraam Sabir, Soumyaroop Nandi, Wael AbdAlmageed +1
Research in media forensics has gained traction to combat the spread of misinformation. However, most of this research has been directed towards content generated on social media.…
MEG: Multi-Evidence GNN for Multimodal Semantic Forensics
Ekraam Sabir, Ayush Jaiswal, Wael AbdAlmageed +1
Fake news often involves semantic manipulations across modalities such as image, text, location etc and requires the development of multimodal semantic forensics for its detection.…
CORD19STS: COVID-19 Semantic Textual Similarity Dataset
Xiao Guo, Hengameh Mirzaalian, Ekraam Sabir +2
In order to combat the COVID-19 pandemic, society can benefit from various natural language processing applications, such as dialog medical diagnosis systems and information retrie…
Recurrent Convolutional Strategies for Face Manipulation Detection in Videos
Ekraam Sabir, Jiaxin Cheng, Ayush Jaiswal +3
The spread of misinformation through synthetically generated yet realistic images and videos has become a significant problem, calling for robust manipulation detection methods. De…
Policy Design for Active Sequential Hypothesis Testing using Deep Learning
Dhruva Kartik, Ekraam Sabir, Urbashi Mitra +1
Information theory has been very successful in obtaining performance limits for various problems such as communication, compression and hypothesis testing. Likewise, stochastic con…
Deep Multimodal Image-Repurposing Detection
Ekraam Sabir, Wael AbdAlmageed, Yue Wu +1
Nefarious actors on social media and other platforms often spread rumors and falsehoods through images whose metadata (e.g., captions) have been modified to provide visual substant…
Implicit Language Model in LSTM for OCR
Ekraam Sabir, Stephen Rawls, Prem Natarajan
Neural networks have become the technique of choice for OCR, but many aspects of how and why they deliver superior performance are still unknown. One key difference between current…
Multimedia Semantic Integrity Assessment Using Joint Embedding Of Images And Text
Ayush Jaiswal, Ekraam Sabir, Wael AbdAlmageed +1
Real world multimedia data is often composed of multiple modalities such as an image or a video with associated text (e.g. captions, user comments, etc.) and metadata. Such multimo…