219 citations · 268 across the 17 of their papers we have counts for
19 papers
Multi-LLM Collaboration for Medication Recommendation
Huascar Sanchez, Briland Hitaj, Jules Bergmann +1
As healthcare increasingly turns to AI for scalable and trustworthy clinical decision support, ensuring reliability in model reasoning remains a critical challenge. Individual larg…
LLM Chemistry Estimation for Multi-LLM Recommendation
Huascar Sanchez, Briland Hitaj
Multi-LLM collaboration promises accurate, robust, and context-aware solutions, yet existing approaches rely on implicit selection and output assessment without analyzing whether c…
LLM in the Middle: A Systematic Review of Threats and Mitigations to Real-World LLM-based Systems
Vitor Hugo Galhardo Moia, Igor Jochem Sanz, Gabriel Antonio Fontes Rebello +3
The success and wide adoption of generative AI (GenAI), particularly large language models (LLMs), has attracted the attention of cybercriminals seeking to abuse models, steal sens…
A Case Study on the Use of Representativeness Bias as a Defense Against Adversarial Cyber Threats
Briland Hitaj, Grit Denker, Laura Tinnel +9
Cyberspace is an ever-evolving battleground involving adversaries seeking to circumvent existing safeguards and defenders aiming to stay one step ahead by predicting and mitigating…
Do You Trust Your Model? Emerging Malware Threats in the Deep Learning Ecosystem
Dorjan Hitaj, Giulio Pagnotta, Fabio De Gaspari +4
Training high-quality deep learning models is a challenging task due to computational and technical requirements. A growing number of individuals, institutions, and companies incre…
Critical Infrastructure Security Goes to Space: Leveraging Lessons Learned on the Ground
Tim Ellis, Briland Hitaj, Ulf Lindqvist +3
Space systems enable essential communications, navigation, imaging and sensing for a variety of domains, including agriculture, commerce, transportation, and emergency operations b…
PassGPT: Password Modeling and (Guided) Generation with Large Language Models
Javier Rando, Fernando Perez-Cruz, Briland Hitaj
Large language models (LLMs) successfully model natural language from vast amounts of text without the need for explicit supervision. In this paper, we investigate the efficacy of…
Automatic Measures for Evaluating Generative Design Methods for Architects
Eric Yeh, Briland Hitaj, Vidyasagar Sadhu +3
The recent explosion of high-quality image-to-image methods has prompted interest in applying image-to-image methods towards artistic and design tasks. Of interest for architects i…
CoProver: A Recommender System for Proof Construction
Eric Yeh, Briland Hitaj, Sam Owre +2
Interactive Theorem Provers (ITPs) are an indispensable tool in the arsenal of formal method experts as a platform for construction and (formal) verification of proofs. The complex…
Revisiting Variable Ordering for Real Quantifier Elimination using Machine Learning
John Hester, Briland Hitaj, Grant Passmore +3
Cylindrical Algebraic Decomposition (CAD) is a key proof technique for formal verification of cyber-physical systems. CAD is computationally expensive, with worst-case doubly-expon…
Trust in Motion: Capturing Trust Ascendancy in Open-Source Projects using Hybrid AI
Huascar Sanchez, Briland Hitaj
Open-source is frequently described as a driver for unprecedented communication and collaboration, and the process works best when projects support teamwork. Yet, open-source coope…
Adversarial Scratches: Deployable Attacks to CNN Classifiers
Loris Giulivi, Malhar Jere, Loris Rossi +4
A growing body of work has shown that deep neural networks are susceptible to adversarial examples. These take the form of small perturbations applied to the model's input which le…
TATTOOED: A Robust Deep Neural Network Watermarking Scheme based on Spread-Spectrum Channel Coding
Giulio Pagnotta, Dorjan Hitaj, Briland Hitaj +2
Watermarking of deep neural networks (DNNs) has gained significant traction in recent years, with numerous (watermarking) strategies being proposed as mechanisms that can help veri…
FedComm: Federated Learning as a Medium for Covert Communication
Dorjan Hitaj, Giulio Pagnotta, Briland Hitaj +2
Proposed as a solution to mitigate the privacy implications related to the adoption of deep learning, Federated Learning (FL) enables large numbers of participants to successfully…
Capture the Bot: Using Adversarial Examples to Improve CAPTCHA Robustness to Bot Attacks
Dorjan Hitaj, Briland Hitaj, Sushil Jajodia +1
To this date, CAPTCHAs have served as the first line of defense preventing unauthorized access by (malicious) bots to web-based services, while at the same time maintaining a troub…
Scratch that! An Evolution-based Adversarial Attack against Neural Networks
Malhar Jere, Loris Rossi, Briland Hitaj +3
We study black-box adversarial attacks for image classifiers in a constrained threat model, where adversaries can only modify a small fraction of pixels in the form of scratches on…
PassGAN: A Deep Learning Approach for Password Guessing
Briland Hitaj, Paolo Gasti, Giuseppe Ateniese +1
State-of-the-art password guessing tools, such as HashCat and John the Ripper, enable users to check billions of passwords per second against password hashes. In addition to perfor…
Deep Models Under the GAN: Information Leakage from Collaborative Deep Learning
Briland Hitaj, Giuseppe Ateniese, Fernando Perez-Cruz
Deep Learning has recently become hugely popular in machine learning, providing significant improvements in classification accuracy in the presence of highly-structured and large d…
No Place to Hide that Bytes won't Reveal: Sniffing Location-Based Encrypted Traffic to Track a User's Position
Giuseppe Ateniese, Briland Hitaj, Luigi V. Mancini +2
News reports of the last few years indicated that several intelligence agencies are able to monitor large networks or entire portions of the Internet backbone. Such a powerful adve…