Picture for Poojitha Thota

Poojitha Thota

Attacks against Abstractive Text Summarization Models through Lead Bias and Influence Functions

Add code
Oct 26, 2024
Viaarxiv icon

Vulnerabilities Unveiled: Adversarially Attacking a Multimodal Vision Language Model for Pathology Imaging

Add code
Jan 08, 2024
Viaarxiv icon

From Chatbots to PhishBots? -- Preventing Phishing scams created using ChatGPT, Google Bard and Claude

Add code
Oct 29, 2023
Viaarxiv icon