no code implementations • 4 Jan 2024 • Jai Prakash Veerla, Poojitha Thota, Partha Sai Guttikonda, Shirin Nilizadeh, Jacob M. Luber
In the dynamic landscape of medical artificial intelligence, this study explores the vulnerabilities of the Pathology Language-Image Pretraining (PLIP) model, a Vision Language Foundation model, under targeted adversarial conditions.
no code implementations • 29 Oct 2023 • Sayak Saha Roy, Poojitha Thota, Krishna Vamsi Naragam, Shirin Nilizadeh
As a countermeasure, we build a BERT-based automated detection tool that can be used for the early detection of malicious prompts to prevent LLMs from generating phishing content.
no code implementations • 9 May 2023 • Sayak Saha Roy, Krishna Vamsi Naragam, Shirin Nilizadeh
The ability of ChatGPT to generate human-like responses and understand context has made it a popular tool for conversational agents, content creation, data analysis, and research and innovation.
no code implementations • 5 Dec 2022 • Seyyed Mohammad Sadegh Moosavi Khorzooghi, Shirin Nilizadeh
In this paper, for the first time, we also performed a carefully designed user study to examine both privacy and utility-preserving properties of StyleGAN0-3, 0-4, and 0-5, as well as CIAGAN and DeepPrivacy from the human observers' perspectives.
no code implementations • 13 Nov 2021 • Sayak Saha Roy, Unique Karanjit, Shirin Nilizadeh
Moreover, nearly 31% of these URLs were still active even after a week of them being reported, with 27% of them being detected by very few anti-phishing tools, suggesting that a large majority of these reports remain undiscovered, despite the majority of the follower base of these accounts being security focused users.
no code implementations • EMNLP (BlackboxNLP) 2021 • Anahita Samadi, Debapriya Banerjee, Shirin Nilizadeh
We also found that attacks against TF IDF is more successful compared to USE.
no code implementations • 14 Jun 2021 • Rodrigo dos Santos, Shirin Nilizadeh
We show that an adversary can focus on audio adversarial inputs to cause AED systems to misclassify, achieving high success rates, even when we use small levels of a given type of noisy disturbance.
2 code implementations • 16 Nov 2018 • Shirin Nilizadeh, Yannic Noller, Corina S. Pasareanu
For this paper, we present an implementation that targets analysis of Java programs, and uses and extends the Kelinci and AFL fuzzers.
Cryptography and Security Software Engineering
no code implementations • 25 May 2018 • Hojjat Aghakhani, Aravind Machiry, Shirin Nilizadeh, Christopher Kruegel, Giovanni Vigna
These results indicate that GANs can be effective for text classification tasks.