163 citations · 172 across the 10 of their papers we have counts for
11 papers
IConMark: Robust Interpretable Concept-Based Watermark For AI Images
Vinu Sankar Sadasivan, Mehrdad Saberi, Soheil Feizi
With the rapid rise of generative AI and synthetic media, distinguishing AI-generated images from real ones has become crucial in safeguarding against misinformation and ensuring d…
Attacker's Noise Can Manipulate Your Audio-based LLM in the Real World
Vinu Sankar Sadasivan, Soheil Feizi, Rajiv Mathews +1
This paper investigates the real-world vulnerabilities of audio-based large language models (ALLMs), such as Qwen2-Audio. We first demonstrate that an adversary can craft stealthy…
Adversarial Paraphrasing: A Universal Attack for Humanizing AI-Generated Text
Yize Cheng, Vinu Sankar Sadasivan, Mehrdad Saberi +2
The increasing capabilities of Large Language Models (LLMs) have raised concerns about their misuse in AI-generated plagiarism and social engineering. While various AI-generated te…
DREW : Towards Robust Data Provenance by Leveraging Error-Controlled Watermarking
Mehrdad Saberi, Vinu Sankar Sadasivan, Arman Zarei +2
Identifying the origin of data is crucial for data provenance, with applications including data ownership protection, media forensics, and detecting AI-generated content. A standar…
Fast Adversarial Attacks on Language Models In One GPU Minute
Vinu Sankar Sadasivan, Shoumik Saha, Gaurang Sriramanan +3
In this paper, we introduce a novel class of fast, beam search-based adversarial attack (BEAST) for Language Models (LMs). BEAST employs interpretable parameters, enabling attacker…
Exploring Geometry of Blind Spots in Vision Models
Sriram Balasubramanian, Gaurang Sriramanan, Vinu Sankar Sadasivan +1
Despite the remarkable success of deep neural networks in a myriad of settings, several works have demonstrated their overwhelming sensitivity to near-imperceptible perturbations,…
Robustness of AI-Image Detectors: Fundamental Limits and Practical Attacks
Mehrdad Saberi, Vinu Sankar Sadasivan, Keivan Rezaei +4
In light of recent advancements in generative AI models, it has become essential to distinguish genuine content from AI-generated one to prevent the malicious usage of fake materia…
Provable Robustness for Streaming Models with a Sliding Window
Aounon Kumar, Vinu Sankar Sadasivan, Soheil Feizi
The literature on provable robustness in machine learning has primarily focused on static prediction problems, such as image classification, in which input samples are assumed to b…
CUDA: Convolution-based Unlearnable Datasets
Vinu Sankar Sadasivan, Mahdi Soltanolkotabi, Soheil Feizi
Large-scale training of modern deep learning models heavily relies on publicly available data on the web. This potentially unauthorized usage of online data leads to concerns regar…
Can AI-Generated Text be Reliably Detected?
Vinu Sankar Sadasivan, Aounon Kumar, Sriram Balasubramanian +2
Large Language Models (LLMs) perform impressively well in various applications. However, the potential for misuse of these models in activities such as plagiarism, generating fake…
Statistical Measures For Defining Curriculum Scoring Function
Vinu Sankar Sadasivan, Anirban Dasgupta
Curriculum learning is a training strategy that sorts the training examples by some measure of their difficulty and gradually exposes them to the learner to improve the network per…