Publications

FETA: Fairness Enforced Verifying, Training, and Predicting Algorithms for Neural Networks
Kiarash Mohammadi
Aishwarya Sivaraman
Golnoosh Farnadi
2023-10-30
Equity and Access in Algorithms, Mechanisms, and Optimization (publié)
doi.org
arxiv.org
TorchProbe: Fuzzing Dynamic Deep Learning Compilers
Qidong Su
Chuqin Geng
Gennady G. Pekhimenko
Xujie Si
Static and dynamic computational graphs represent two distinct approaches to constructing deep learning frameworks. The former prioritizes c… (voir plus)ompiler-based optimizations, while the latter focuses on programmability and user-friendliness. The recent release of PyTorch 2.0, which supports compiling arbitrary deep learning programs in Python, signifies a new direction in the evolution of deep learning infrastructure to incorporate compiler techniques in a more dynamic manner and support more dynamic language features like dynamic control flows and closures. Given PyTorch's seamless integration with Python, its compiler aims to support arbitrary deep learning code written in Python. However, the inherent dynamism of Python poses challenges to the completeness and robustness of the compiler. While recent research has introduced fuzzing to test deep learning compilers, there is still a lack of comprehensive analysis on how to test dynamic features. To address this issue, we propose several code transformations to generate test cases involving dynamic features. These transformations preserve the program's semantics, ensuring that any discrepancy between the transformed and original programs indicates the presence of a bug. Through our approach, we have successfully identified twenty previously unknown bugs in the PyTorch compiler and its underlying tensor compiler Triton.
2023-10-30
ArXiv (prépublication)
doi.org
arxiv.org
Unraveling the Interconnected Axes of Heterogeneity in Machine Learning for Democratic and Inclusive Advancements
Maryam Molamohammadi
Afaf Taïk
Nicolas Le Roux
Golnoosh Farnadi
2023-10-30
Equity and Access in Algorithms, Mechanisms, and Optimization (publié)
doi.org
arxiv.org
Proving Linear Mode Connectivity of Neural Networks via Optimal Transport
Damien Ferbach
Baptiste Goujaud
Gauthier Gidel
Aymeric Dieuleveut
The energy landscape of high-dimensional non-convex optimization problems is crucial to understanding the effectiveness of modern deep neura… (voir plus)l network architectures. Recent works have experimentally shown that two different solutions found after two runs of a stochastic training are often connected by very simple continuous paths (e.g., linear) modulo a permutation of the weights. In this paper, we provide a framework theoretically explaining this empirical observation. Based on convergence rates in Wasserstein distance of empirical measures, we show that, with high probability, two wide enough two-layer neural networks trained with stochastic gradient descent are linearly connected. Additionally, we express upper and lower bounds on the width of each layer of two deep neural networks with independent neuron weights to be linearly connected. Finally, we empirically demonstrate the validity of our approach by showing how the dimension of the support of the weight distribution of neurons, which dictates Wasserstein convergence rates is correlated with linear mode connectivity.
2023-10-29
ArXiv (prépublication)
doi.org
arxiv.org
A Case Study of Instruction Tuning with Mixture of Parameter-Efficient Experts
Oleksiy Ostapenko
Lucas Caccia
Zhan Su
Nicolas Le Roux
Laurent Charlin
Alessandro Sordoni
We study the applicability of mixture of parameter-efficient experts (MoPEs) for instruction-tuning large decoder-only language models. Rece… (voir plus)nt literature indicates that MoPEs might enhance performance in specific multi-task instruction-following datasets. In this paper, we extend such previous results and study applicability of MoPEs in settings previously overlooked: a) with open-domain instruction-following datasets; b) with recent decoder-only models and c) with downstream out-of-distribution test sets. We build on top of LLaMA1-13B/-7B and LLaMA2-13B. We study different variants of learned routing, namely per-example routing ([PE]), and a more expensive per-token ([PT]) routing. Overall, we are unable to substantiate strong performance gains observed in related studies in our setting. We observe occasional enhancements of LLAMA2 fine-tuned on Open Platypus dataset in 0-shot SNI evaluation and TruthfulQA evaluation after fine-tuning on a subset of Flan. We shed some light on the inner workings of MoPEs by comparing different routing strategies. We find that [PE] routing tends to collapse at downstream evaluation time reducing the importance of router's application. We plan to publicly release our code.
2023-10-28
NeurIPS.cc/2023/Workshop/Instruction (publié)
openreview.net
openreview.net
Detecting Backdoors with Meta-Models
Lauro Langosco
Neel Alex
William Baker
David John Quarel
Herbie Bradley
David Scott Krueger
It is widely known that it is possible to implant backdoors into neural networks, by which an attacker can choose an input to produce a part… (voir plus)icular undesirable output (e.g.\ misclassify an image). We propose to use \emph{meta-models}, neural networks that take another network's parameters as input, to detect backdoors directly from model weights. To this end we present a meta-model architecture and train it on a dataset of approx.\ 4000 clean and backdoored CNNs trained on CIFAR-10. Our approach is simple and scalable, and is able to detect the presence of a backdoor with
2023-10-28
NeurIPS.cc/2023/Workshop/BUGS (poster)
openreview.net
openreview.net
Detecting Backdoors with Meta-Models
Lauro Langosco
Neel Alex
William Baker
David John Quarel
Herbie Bradley
David Scott Krueger
It is widely known that it is possible to implant backdoors into neural networks, by which an attacker can choose an input to produce a part… (voir plus)icular undesirable output (e.g.\ misclassify an image). We propose to use \emph{meta-models}, neural networks that take another network's parameters as input, to detect backdoors directly from model weights. To this end we present a meta-model architecture and train it on a dataset of approx.\ 4000 clean and backdoored CNNs trained on CIFAR-10. Our approach is simple and scalable, and is able to detect the presence of a backdoor with
2023-10-28
NeurIPS.cc/2023/Workshop/BUGS (poster)
openreview.net
openreview.net
Generative AI models should include detection mechanisms as a condition for public release
Alistair Knott
Dino Pedreschi
Raja Chatila
Tapabrata Chakraborti
Susan Leavy
Ricardo Baeza-Yates
D. Eyers
Andrew Trotman
Paul D. Teal
Przemyslaw Biecek
Stuart Russell
Yoshua Bengio
2023-10-28
Ethics and Information Technology (publié)
doi.org
Noisy ZSC: Breaking The Common Knowledge Assumption In Zero-Shot Coordination Games
Usman Anwar
Jia Wan
David Scott Krueger
Jakob Nicolaus Foerster
Zero-shot coordination (ZSC) is a popular setting for studying the ability of AI agents to coordinate with novel partners. Prior formulation… (voir plus)s of ZSC make the assumption that the problem setting is common knowledge i.e. each agent has the knowledge of the underlying Dec-POMDP, every agent knows the others have this knowledge, and so on ad infinitum. However, in most real-world situations, different agents are likely to have different models of the (real world) environment, thus breaking this assumption. To address this limitation, we formulate the _noisy zero-shot coordination_ (NZSC) problem, where agents observe different noisy versions of the ground truth Dec-POMDP generated by passing the true Dec-POMDP through a noise model. Only the distribution of the ground truth Dec-POMDPs and the noise model are common knowledge. We show that any noisy ZSC problem can be reformulated as a ZSC problem by designing a meta-Dec-POMDP with an augmented state space consisting of both the ground truth Dec-POMDP and its corresponding state. In our experiments, we analyze various aspects of NZSC and show that achieving good performance in NZSC requires agents to make use of both the noisy observations of ground truth Dec-POMDP, knowledge of each other's noise models and their interactions with the ground truth Dec-POMDP. Through experimental results, we further establish that ignoring the noise in problem specification can result in sub-par ZSC coordination performance, especially in iterated scenarios. On the whole, our work highlights that NZSC adds an orthogonal challenge to traditional ZSC in tackling the uncertainty about the true problem.
2023-10-28
NeurIPS.cc/2023/Workshop/ALOE (poster)
openreview.net
openreview.net
Noisy ZSC: Breaking The Common Knowledge Assumption In Zero-Shot Coordination Games
Usman Anwar
Jia Wan
David Scott Krueger
Jakob Nicolaus Foerster
Zero-shot coordination (ZSC) is a popular setting for studying the ability of AI agents to coordinate with novel partners. Prior formulation… (voir plus)s of ZSC make the assumption that the problem setting is common knowledge i.e. each agent has the knowledge of the underlying Dec-POMDP, every agent knows the others have this knowledge, and so on ad infinitum. However, in most real-world situations, different agents are likely to have different models of the (real world) environment, thus breaking this assumption. To address this limitation, we formulate the _noisy zero-shot coordination_ (NZSC) problem, where agents observe different noisy versions of the ground truth Dec-POMDP generated by passing the true Dec-POMDP through a noise model. Only the distribution of the ground truth Dec-POMDPs and the noise model are common knowledge. We show that any noisy ZSC problem can be reformulated as a ZSC problem by designing a meta-Dec-POMDP with an augmented state space consisting of both the ground truth Dec-POMDP and its corresponding state. In our experiments, we analyze various aspects of NZSC and show that achieving good performance in NZSC requires agents to make use of both the noisy observations of ground truth Dec-POMDP, knowledge of each other's noise models and their interactions with the ground truth Dec-POMDP. Through experimental results, we further establish that ignoring the noise in problem specification can result in sub-par ZSC coordination performance, especially in iterated scenarios. On the whole, our work highlights that NZSC adds an orthogonal challenge to traditional ZSC in tackling the uncertainty about the true problem.
2023-10-28
NeurIPS.cc/2023/Workshop/ALOE (poster)
openreview.net
openreview.net
OC-NMN: Object-centric Compositional Neural Module Network for Generative Visual Analogical Reasoning
Rim Assouel
Pau Rodriguez
Perouz Taslakian
David Vazquez
Yoshua Bengio
2023-10-28
ArXiv (prépublication)
doi.org
arxiv.org
Adversarial Attacks and Defenses in Large Language Models: Old and New Threats
Leo Schwinn
David Dobre
Stephan Günnemann
Gauthier Gidel
Over the past decade, there has been extensive research aimed at enhancing the robustness of neural networks, yet this problem remains vastl… (voir plus)y unsolved. Here, one major impediment has been the overestimation of the robustness of new defense approaches due to faulty defense evaluations. Flawed robustness evaluations necessitate rectifications in subsequent works, dangerously slowing down the research and providing a false sense of security. In this context, we will face substantial challenges associated with an impending adversarial arms race in natural language processing, specifically with closed-source Large Language Models (LLMs), such as ChatGPT, Google Bard, or Anthropic's Claude. We provide a first set of prerequisites to improve the robustness assessment of new approaches and reduce the amount of faulty evaluations. Additionally, we identify embedding space attacks on LLMs as another viable threat model for the purposes of generating malicious content in open-sourced models. Finally, we demonstrate on a recently proposed defense that, without LLM-specific best practices in place, it is easy to overestimate the robustness of a new approach.
2023-10-27
NeurIPS.cc/2023/Workshop/ICBINB (publié)
doi.org
openreview.net