5 papers
TROPT: An Open Framework for Unifying and Advancing Discrete Text Optimization
Matan Ben-Tov, Mahmood Sharif
Discrete text-trigger optimization -- searching for text sequences that, when ingested by a model, steer it toward a specified objective -- underpins model red-teaming (e.g., LLM j…
Exploring Membership Inference Vulnerabilities in Clinical Large Language Models
Alexander Nemecek, Zebin Yun, Zahra Rahmani +4
As large language models (LLMs) become progressively more embedded in clinical decision-support, documentation, and patient-information systems, ensuring their privacy and trustwor…
Redesigning Traffic Signs to Mitigate Machine-Learning Patch Attacks
Tsufit Shua, Liron David, Mahmood Sharif
Traffic-Sign Recognition (TSR) is a critical safety component for autonomous driving. Unfortunately, however, past work has highlighted the vulnerability of TSR models to physical-…
The Ultimate Combo: Boosting Adversarial Example Transferability by Composing Data Augmentations
Zebin Yun, Achi-Or Weingarten, Eyal Ronen +1
To help adversarial examples generalize from surrogate machine-learning (ML) models to targets, certain transferability-based black-box evasion attacks incorporate data augmentatio…
Privacy-Preserving Collaborative Genomic Research: A Real-Life Deployment and Vision
Zahra Rahmani, Nahal Shahini, Nadav Gat +7
The data revolution holds significant promise for the health sector. Vast amounts of data collected from individuals will be transformed into knowledge, AI models, predictive syste…