Reihaneh Rabbany

hussein.abdallah@mail.concordia.ca

Biography

Reihaneh Rabbany is an assistant professor at the School of Computer Science, McGill University, and a core academic member of Mila – Quebec Artificial Intelligence Institute. She is also a Canada CIFAR AI Chair and on the faculty of McGill’s Centre for the Study of Democratic Citizenship.

Before joining McGill, Rabbany was a postdoctoral fellow at the School of Computer Science, Carnegie Mellon University. She completed her PhD in the Department of Computing Science at the University of Alberta.

Rabbany heads McGill’s Complex Data Lab, where she conducts research at the intersection of network science, data mining and machine learning, with a focus on analyzing real-world interconnected data and social good applications.

Current Students

Hussein Abdallah

Collaborating researcher - Concordia University

Aurélien Bück-Kaeffer

Master's Research - McGill University

Jacob Chmura

Master's Research - McGill University

Principal supervisor :

PhD - McGill University

Co-supervisor :

Adriana Romero Soriano

Collaborating Alumni - McGill University

Co-supervisor :

Research Intern - McGill University

Master's Research - McGill University

Victor Livernoche

PhD - McGill University

Sitao Luan

Postdoctorate - McGill University

Principal supervisor :

Guillaume Rabusseau

Master's Research - McGill University

Co-supervisor :

Collaborating researcher - McGill University

Master's Research - McGill University

Website

Soroush Omranpour

Collaborating Alumni - McGill University

Co-supervisor :

Guillaume Rabusseau

kellin.pelrine@mila.quebec

PhD - McGill University

Website

Farimah Poursafaei

Collaborating Alumni - McGill University

Collaborating researcher

Collaborating researcher - McGill University University

Collaborating researcher - McGill University

sneheelsarangi@gmail.com

Research Intern - McGill University

Vidya Sujaya

Master's Research - McGill University

Master's Research - Université de Montréal

Principal supervisor :

jacob.mila.handle@tianshome.com

Collaborating researcher - McGill University

Collaborating researcher - Université de Montréal

Principal supervisor :

PhD - McGill University

Jie Zan

Research Intern - McGill University

jie.zan@mail.mcgill.ca

Sveta Zhuk

Master's Research - Université de Montréal

Principal supervisor :

Flight-SEIR: Incorporating Flight Data to Improve Epidemiological Modelling and Disease Outbreak Prevention

Blog Posts

August 3, 2021

Shenyang Huang

Reihaneh Rabbany

Read the article

Publications

A Simulation System Towards Solving Societal-Scale Manipulation

Maximilian Puelma Touzel

Austin Welch

Gayatri K

Dan Zhao

Hao Yu

Ethan Kosak-Hine

Tom Gibbs

Busra Tugce Gurbuz

The rise of AI-driven manipulation poses significant risks to societal trust and democratic processes. Yet, studying these effects in real-w… (see more)orld settings at scale is ethically and logistically impractical, highlighting a need for simulation tools that can model these dynamics in controlled settings to enable experimentation with possible defenses. We present a simulation environment designed to address this. We elaborate upon the Concordia framework that simulates offline, `real life' activity by adding online interactions to the simulation through social media with the integration of a Mastodon server. We improve simulation efficiency and information flow, and add a set of measurement tools, particularly longitudinal surveys. We demonstrate the simulator with a tailored example in which we track agents' political positions and show how partisan manipulation of agents can affect election results.

2024-10-17

ArXiv (preprint)

arxiv.org

A Simulation System Towards Solving Societal-Scale Manipulation

Maximilian Puelma Touzel

Austin Welch

Gayatri Krishnakumar

Dan Zhao

Hao Yu

Ethan Kosak-Hine

Tom Gibbs

Busra Tugce Gurbuz

2024-10-17

ArXiv (preprint)

arxiv.org

Epistemic Integrity in Large Language Models

Bijean Ghafouri

James Zhou

Pratheeksha Nair

Jacob-Junqi Tian

Mayank Goel

Large language models are increasingly relied upon as sources of information, but their propensity for generating false or misleading statem… (see more)ents with high confidence poses risks for users and society. In this paper, we confront the critical problem of epistemic miscalibration—where a model's linguistic assertiveness fails to reflect its true internal certainty. We introduce a new human-labeled dataset and a novel method for measuring the linguistic assertiveness of Large Language Models which cuts error rates by over 50% relative to previous benchmarks. Validated across multiple datasets, our method reveals a stark misalignment between how confidently models linguistically present information and their actual accuracy. Further human evaluations confirm the severity of this miscalibration. This evidence underscores the urgent risk of the overstated certainty Large Language Models hold which may mislead users on a massive scale. Our framework provides a crucial step forward in diagnosing and correcting this miscalibration, offering a path to safer and more trustworthy AI across domains.

2024-10-12

NeurIPS.cc/2024/Workshop/SafeGenAi (poster)

Epistemic Integrity in Large Language Models

Bijean Ghafouri

James Zhou

Pratheeksha Nair

Jacob-Junqi Tian

Mayank Goel

2024-10-12

NeurIPS.cc/2024/Workshop/SafeGenAi (poster)

Hallucination Detox: Sensitive Neuron Dropout (SeND) for Large Language Model Training

Juan David Guerra

Marco Bonizzato

Golnoosh Farnadi

As large language models (LLMs) become increasingly deployed across various industries, concerns regarding their reliability, particularly d… (see more)ue to hallucinations-outputs that are factually inaccurate or irrelevant to user input-have grown. Our research investigates the relationship between the training process and the emergence of hallucinations to address a key gap in existing research that focuses primarily on post hoc detection and mitigation strategies. Using models from the Pythia suite (70M-12B parameters) and several hallucination detection metrics, we analyze hallucination trends throughout training and explore LLM internal dynamics. We introduce SEnsitive Neuron Dropout (SeND), a novel training protocol designed to mitigate hallucinations by reducing variance during training. SeND achieves this by deterministically dropping neurons with significant variability on a dataset, referred to as Sensitive Neurons. In addition, we develop an unsupervised hallucination detection metric, Efficient EigenScore (EES), which approximates the traditional EigenScore in 2x speed. This efficient metric is integrated into our protocol, allowing SeND to be both computationally scalable and effective at reducing hallucinations. Our empirical evaluation demonstrates that our approach improves LLM reliability at test time by up to 40% compared to normal training while also providing an efficient method to improve factual accuracy when adapting LLMs to domains such as Wikipedia and Medical datasets.

2024-10-12

NeurIPS.cc/2024/Workshop/SafeGenAi (poster)

Simulation System Towards Solving Societal-Scale Manipulation

Maximilian Puelma Touzel

Austin Welch

Gayatri K

Dan Zhao

Hao Yu

Tom Gibbs

Ethan Kosak-Hine

Busra Tugce Gurbuz

The rise of AI-driven manipulation poses significant risks to societal trust and democratic processes. Yet, studying these effects in real-w… (see more)orld settings at scale is ethically and logistically impractical, highlighting a need for simulation tools that can model these dynamics in controlled settings to enable experimentation with possible defenses. We present a simulation environment designed to address this. We elaborate upon the Concordia framework that simulates offline, `real life' activity by adding online interactions to the simulation through social media with the integration of a Mastodon server. Through a variety of means we then improve simulation efficiency and information flow, and add a set of measurement tools, particularly longitudinal surveys of the agents' political positions. We demonstrate the simulator with a tailored example of how partisan manipulation of agents can affect election results.

2024-10-12

NeurIPS.cc/2024/Workshop/SafeGenAi (poster)

Simulation System Towards Solving Societal-Scale Manipulation

Maximilian Puelma Touzel

Austin Welch

Gayatri K

Dan Zhao

Hao Yu

Tom Gibbs

Ethan Kosak-Hine

Busra Tugce Gurbuz

The rise of AI-driven manipulation poses significant risks to societal trust and democratic processes. Yet, studying these effects in real-w… (see more)orld settings at scale is ethically and logistically impractical, highlighting a need for simulation tools that can model these dynamics in controlled settings to enable experimentation with possible defenses. We present a simulation environment designed to address this. We elaborate upon the Concordia framework that simulates offline, `real life' activity by adding online interactions to the simulation through social media with the integration of a Mastodon server. Through a variety of means we then improve simulation efficiency and information flow, and add a set of measurement tools, particularly longitudinal surveys of the agents' political positions. We demonstrate the simulator with a tailored example of how partisan manipulation of agents can affect election results.

2024-10-12

NeurIPS.cc/2024/Workshop/SafeGenAi (poster)

The Structural Safety Generalization Problem

Tom Gibbs

Julius Broomfield

George Ingebretsen

Ethan Kosak-Hine

Tia Nasir

Jason Zhang

Reihaneh Iranmanesh

Sara Pieri

It is widely known that AI is vulnerable to adversarial examples, from pixel perturbations to jailbreaks. We propose that there is a key, ea… (see more)sier class of problems that is also still unsolved: failures of safety to generalize over structure, despite semantic equivalence. We demonstrate this vulnerability by showing how recent AI systems are differently vulnerable both to multi-turn and multi-image attacks, compared to their single-turn and single-image counterparts with equivalent meaning. We suggest this is the same class of vulnerability as that found in yet unconnected threads of the literature: vulnerabilities to low-resource languages and indefensibility of strongly superhuman Go AIs to cyclic attacks. When viewed together, these reveal a common picture: models that are not only vulnerable to attacks, but vulnerable to attacks with near identical meaning in their benign and harmful components both, and only different in structure. In contrast to attacks with identical benign input (e.g., pictures that look like cats) but unknown semanticity of the harmful component (e.g., diverse noise that is all unintelligible to humans), these represent a class of attacks where semantic understanding and defense against one version should guarantee defense against others—yet current AI safety measures do not. This vulnerability represents a necessary but not sufficient condition towards defending against attacks whose harmful component has arbitrary semanticity. Consequently, by building on the data and approaches we highlight, we frame an intermediate problem for AI safety to solve, that represents a critical checkpoint towards safe AI while being far more tractable than trying to solve it directly and universally.

2024-10-12

NeurIPS.cc/2024/Workshop/SafeGenAi (poster)

The Structural Safety Generalization Problem

Tom Gibbs

Julius Broomfield

George Ingebretsen

Ethan Kosak-Hine

Tia Nasir

Jason Zhang

Reihaneh Iranmanesh

Sara Pieri

2024-10-12

NeurIPS.cc/2024/Workshop/SafeGenAi (poster)

Decompose, Recompose, and Conquer: Multi-modal LLMs are Vulnerable to Compositional Adversarial Attacks in Multi-Image Queries

Julius Broomfield

George Ingebretsen

Reihaneh Iranmanesh

Sara Pieri

Ethan Kosak-Hine

Tom Gibbs

Large Language Models have been extensively studied for their vulnerabilities, particularly in the context of adversarial attacks. However, … (see more)the emergence of Vision Language Models introduces new modalities of risk that have not yet been thoroughly explored, especially when processing multiple images simultaneously. In this paper, we introduce two black-box jailbreak methods that leverage multi-image inputs to uncover vulnerabilities in these models. We present a new safety evaluation dataset for multimodal LLMs called MultiBench, which is composed of these jailbreak methods. These methods can easily be applied and evaluated using our toolkit. We test these methods against six safety aligned frontier models from Google, OpenAI, and Anthropic, revealing significant safety vulnerabilities. Our findings suggest that even the most powerful language models remain vulnerable against compositional adversarial attacks, specifically those composed of multiple images.

2024-10-09

NeurIPS.cc/2024/Workshop/Red_Teaming_GenAI (poster)

TGB 2.0: A Benchmark for Learning on Temporal Knowledge Graphs and Heterogeneous Graphs

Julia Gastinger

Shenyang Huang

Mikhail Galkin

Erfan Loghmani

Ali Parviz

Farimah Poursafaei

Jacob Danovitch

Emanuele Rossi

Ioannis Koutis

Heiner Stuckenschmidt

Guillaume Rabusseau

2024-09-26

NeurIPS.cc/2024/Datasets_and_Benchmarks_Track (poster)

ToxiSight: Insights Towards Detected Chat Toxicity

Domenico Tullo

We present a comprehensive explainability dashboard designed for in-game chat toxicity. This dashboard integrates various existing explainab… (see more)le AI (XAI) techniques, including token importance analysis, model output visualization, and attribution to the training dataset. It also provides insights through the closest positive and negative examples, facilitating a deeper understanding and potential correction of the training data. Additionally, the dashboard includes word sense analysis—particularly useful for new moderators—and offers free-text explanations for both positive and negative predictions. This multi-faceted approach enhances the interpretability and transparency of toxicity detection models.

2024-09-21

EMNLP/2024/Workshop/BlackBoxNLP (accepted)