Publications

Temporal Abstraction in Reinforcement Learning with the Successor Representation
Marlos C. Machado
Andre Barreto
Doina Precup
Michael Bowling
arxiv.org
Test-time Defense against Adversarial Attacks: Detection and Reconstruction of Adversarial Examples via Masked Autoencoder
Yun-Yun Tsai
Ju-Chin Chao
Albert Wen
Zhaoyuan Yang
Chengzhi Mao
Tapan Shah
Junfeng Yang
Existing defense methods against adversarial attacks can be categorized into training time and test time defenses. Training time defense, i.… (see more)e., adversarial training, requires a significant amount of extra time for training and is often not able to be generalized to unseen attacks. On the other hand, test time defense by test time weight adaptation requires access to perform gradient descent on (part of) the model weights, which could be infeasible for models with frozen weights. To address these challenges, we propose DRAM, a novel defense method to Detect and Reconstruct the multiple types of Adversarial attacks via Masked autoencoder (MAE). We demonstrate how to use MAE losses to build a KS-test to detect adversarial attacks. Moreover, the MAE losses can be used to repair adversarial samples from unseen attack types. In this sense, DRAM neither requires model weight updates in test time nor augments the training set with more adversarial samples. Evaluating DRAM on the large-scale ImageNet data, we achieve the best detection rate of 82% on average on eight types of adversarial attacks compared with other detection baselines. For reconstruction, DRAM improves the robust accuracy by 6% ∼ 41% for Standard ResNet50 and 3% ∼ 8% for Robust ResNet50 compared with other self-supervision tasks, such as rotation prediction and contrastive learning.
2023-01-01
(published)
www.semanticscholar.org
The Age of Ransomware: A Survey on the Evolution, Taxonomy, and Research Directions
Salwa Razaulla
Claude Fachkha
Christine Markarian
Amjad Gawanmeh
Wathiq Mansoor
Benjamin Fung
Chadi Assi
The proliferation of ransomware has become a significant threat to cybersecurity in recent years, causing significant financial, reputationa… (see more)l, and operational damage to individuals and organizations. This paper aims to provide a comprehensive overview of the evolution of ransomware, its taxonomy, and its state-of-the-art research contributions. We begin by tracing the origins of ransomware and its evolution over time, highlighting the key milestones and major trends. Next, we propose a taxonomy of ransomware that categorizes different types of ransomware based on their characteristics and behavior. Subsequently, we review the existing research over several years in regard to detection, prevention, mitigation, and prediction techniques. Our extensive analysis, based on more than 150 references, has revealed that significant research, specifically 72.8%, has focused on detecting ransomware. However, a lack of emphasis has been placed on predicting ransomware. Additionally, of the studies focused on ransomware detection, a significant portion, 70%, have utilized Machine Learning methods. This study uncovers a range of shortcomings in research pertaining to real-time protection and identifying zero-day ransomware, and two issues specific to Machine Learning models. Adversarial machine learning exploitation and concept drift have been identified as under-researched areas in the field. This survey is a constructive roadmap for researchers interested in ransomware research matters.
2023-01-01
IEEE Access (published)
doi.org
The Dormant Neuron Phenomenon in Deep Reinforcement Learning
Ghada Sokar
Rishabh Agarwal
Pablo Samuel Castro
Utku Evci
In this work we identify the dormant neuron phenomenon in deep reinforcement learning, where an agent's network suffers from an increasing n… (see more)umber of inactive neurons, thereby affecting network expressivity. We demonstrate the presence of this phenomenon across a variety of algorithms and environments, and highlight its effect on learning. To address this issue, we propose a simple and effective method (ReDo) that Recycles Dormant neurons throughout training. Our experiments demonstrate that ReDo maintains the expressive power of networks by reducing the number of dormant neurons and results in improved performance.
2023-01-01
ICML (published)
doi.org
openreview.net
On the (Im)Possibility of Estimating Various Notions of Differential Privacy (short paper)
Daniele Gorla
Louis Jalouzot
Federica Granese
Catuscia Palamidessi
Pablo Piantanida
We analyze to what extent final users can infer information about the level of protection of their data when the data obfuscation mechanism … (see more)is a priori unknown to them (the so-called “black-box" scenario). In particular, we delve into the investigation of two notions of local differential privacy (LDP), namely 𝜀 -LDP and Rényi LDP. On one hand, we prove that, without any assumption on the underlying distributions, it is not possible to have an algorithm able to infer the level of data protection with provable guarantees. On the other hand, we demonstrate that, under reasonable assumptions (namely, Lipschitzness of the involved densities on a closed interval), such guarantees exist and can be achieved by a simple histogram-based estimator.
2023-01-01
ICTCS (published)
dblp.uni-trier.de
On the Limitations of Elo: Real-World Games, are Transitive, not Additive
Quentin Bertrand
Wojciech M. Czarnecki
Gauthier Gidel
Real-world competitive games, such as chess, go, or StarCraft II, rely on Elo models to measure the strength of their players. Since these g… (see more)ames are not fully transitive, using Elo implicitly assumes they have a strong transitive component that can correctly be identified and extracted. In this study, we investigate the challenge of identifying the strength of the transitive component in games. First, we show that Elo models can fail to extract this transitive component, even in elementary transitive games. Then, based on this observation, we propose an extension of the Elo score: we end up with a disc ranking system that assigns each player two scores, which we refer to as skill and consistency. Finally, we propose an empirical validation on payoff matrices coming from real-world games played by bots and humans.
2023-01-01
AISTATS (published)
doi.org
arxiv.org
The race to understand immunopathology in COVID-19: Perspectives on the impact of quantitative approaches to understand within-host interactions
Sonia Gazeau
Xiaoyan Deng
Hsu Kiang Ooi
Fatima Mostefai
Julie Hussin
Jane Heffernan
Adrianne L. Jenner
Morgan Craig
2023-01-01
ImmunoInformatics (published)
doi.org
The StatCan Dialogue Dataset: Retrieving Data Tables through Conversations with Genuine Intents
Xing Han Lu
Siva Reddy
Harm de Vries
2023-01-01
EACL (published)
doi.org
arxiv.org
The Statistical Benefits of Quantile Temporal-Difference Learning for Value Estimation
Mark Rowland
Yunhao Tang
Clare Lyle
Remi Munos
Marc Gendron-Bellemare
Will Dabney
We study the problem of temporal-difference-based policy evaluation in reinforcement learning. In particular, we analyse the use of a distri… (see more)butional reinforcement learning algorithm, quantile temporal-difference learning (QTD), for this task. We reach the surprising conclusion that even if a practitioner has no interest in the return distribution beyond the mean, QTD (which learns predictions about the full distribution of returns) may offer performance superior to approaches such as classical TD learning, which predict only the mean return, even in the tabular setting.
2023-01-01
ICML (published)
doi.org
openreview.net
The Statistical Benefits of Quantile Temporal-Difference Learning for Value Estimation
Mark Rowland
Yunhao Tang
Clare Lyle
Remi Munos
Marc Gendron-Bellemare
Will Dabney
2023-01-01
ICML (published)
doi.org
openreview.net
A theory of continuous generative flow networks
Salem Lahlou
Tristan Deleu
Pablo Lemos
Dinghuai Zhang
Alexandra Volokhova
Alex Hernandez-Garcia
Lena Nehale Ezzine
Yoshua Bengio
Nikolay Malkin
2023-01-01
ICML (published)
doi.org
openreview.net
A theory of continuous generative flow networks
Salem Lahlou
Tristan Deleu
Pablo Lemos
Dinghuai Zhang
Alexandra Volokhova
Alex Hernandez-Garcia
Lena Nehale Ezzine
Yoshua Bengio
Nikolay Malkin
Generative flow networks (GFlowNets) are amortized variational inference algorithms that are trained to sample from unnormalized target dist… (see more)ributions over compositional objects. A key limitation of GFlowNets until this time has been that they are restricted to discrete spaces. We present a theory for generalized GFlowNets, which encompasses both existing discrete GFlowNets and ones with continuous or hybrid state spaces, and perform experiments with two goals in mind. First, we illustrate critical points of the theory and the importance of various assumptions. Second, we empirically demonstrate how observations about discrete GFlowNets transfer to the continuous case and show strong results compared to non-GFlowNet baselines on several previously studied tasks. This work greatly widens the perspectives for the application of GFlowNets in probabilistic inference and various modeling settings.
2023-01-01
ICML (published)
doi.org
openreview.net