163 citations · 172 across the 10 of their papers we have counts for
3 papers · 1 filter
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…
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…