Octavian Suciu — accepted AI-conference papers

2025

Privacy Reasoning in Ambiguous Contexts

Ren Yi, Octavian Suciu, Adrian Gascon, Sarah Meiklejohn, Eugene Bagdasarian, Marco Gruteser

NeurIPS 2025poster

We study the ability of language models to reason about appropriate information disclosure - a central aspect of the evolving field of agentic privacy. Whereas previous works have focused on evaluating a model's ability to align with human decisions, we examine the role of ambiguity and missing cont…

Cited by 13 Source ↗Scholar ↗

2018

Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networks

Ali Shafahi, W. Ronny Huang, Mahyar Najibi, Octavian Suciu, Christoph Studer, Tudor Dumitras +1

NeurIPS 2018poster

Data poisoning is an attack on machine learning models wherein the attacker adds examples to the training set to manipulate the behavior of the model at test time. This paper explores poisoning attacks on neural nets. The proposed attacks use ``clean-labels''; they don't require the attacker to have…

Cited by 1414 Source ↗PDF ↗code ↗Scholar ↗