arXiv subjects

Alexandre Maurer

Publications and source records attributed to Alexandre Maurer.

15 recordsLinked to original sources

arXiv2024

Auditing health-related recommendations in social media: A Case Study of Abortion on YouTube

Recommendation algorithms (RS) used by social media, like YouTube, significantly shape our information consumption across various domains, especially in healthcare. Hence, algorithmic auditing becomes crucial to uncover their potential bias and misinformation, particularly in the context of controversial topics like abortion. We introduce a simple yet effective sock puppet auditing approach to investigate how YouTube recommends abortion-related videos to individuals with different backgrounds. Our framework allows for efficient auditing of RS, regardless of the complexity of the underlying algorithms

cs.SI↗

arXiv2021

FEBR: Expert-Based Recommendation Framework for beneficial and personalized content

So far, most research on recommender systems focused on maintaining long-term user engagement and satisfaction, by promoting relevant and personalized content. However, it is still very challenging to evaluate the quality and the reliability of this content. In this paper, we propose FEBR (Expert-Based Recommendation Framework), an apprenticeship learning framework to assess the quality of the recommended content on online platforms. The framework exploits the demonstrated trajectories of an expert (assumed to be reliable) in a recommendation evaluation environment, to recover an unknown utility function. This function is used to learn an optimal policy describing the expert's behavior, which is then used in the framework to provide high-quality and personalized recommendations. We evaluate the performance of our solution through a user interest simulation environment (using RecSim). We simulate interactions under the aforementioned expert policy for videos recommendation, and compare its efficiency with standard recommendation methods. The results show that our approach provides a significant gain in terms of content quality, evaluated by experts and watched by users, while maintaining almost the same watch time as the baseline approaches.

cs.IR↗

arXiv2021

Tournesol: A quest for a large, secure and trustworthy database of reliable human judgments

Today's large-scale algorithms have become immensely influential, as they recommend and moderate the content that billions of humans are exposed to on a daily basis. They are the de-facto regulators of our societies' information diet, from shaping opinions on public health to organizing groups for social movements. This creates serious concerns, but also great opportunities to promote quality information. Addressing the concerns and seizing the opportunities is a challenging, enormous and fabulous endeavor, as intuitively appealing ideas often come with unwanted {\it side effects}, and as it requires us to think about what we deeply prefer. Understanding how today's large-scale algorithms are built is critical to determine what interventions will be most effective. Given that these algorithms rely heavily on {\it machine learning}, we make the following key observation: \emph{any algorithm trained on uncontrolled data must not be trusted}. Indeed, a malicious entity could take control over the data, poison it with dangerously manipulative fabricated inputs, and thereby make the trained algorithm extremely unsafe. We thus argue that the first step towards safe and ethical large-scale algorithms must be the collection of a large, secure and trustworthy dataset of reliable human judgments. To achieve this, we introduce \emph{Tournesol}, an open source platform available at \url{https://tournesol.app}. Tournesol aims to collect a large database of human judgments on what algorithms ought to widely recommend (and what they ought to stop widely recommending). We outline the structure of the Tournesol database, the key features of the Tournesol platform and the main hurdles that must be overcome to make it a successful project. Most importantly, we argue that, if successful, Tournesol may then serve as the essential foundation for any safe and ethical large-scale algorithm.

cs.HC↗

arXiv2019

Gathering with extremely restricted visibility

We consider the classical problem of making mobile processes gather or converge at a same position (as performed by swarms of animals in Nature). Existing works assume that each process can see all other processes, or all processes within a certain radius. In this paper, we introduce a new model with an extremely restricted visibility: each process can only see one other process (its closest neighbor). Our goal is to see if (and to what extent) the gathering and convergence problems can be solved in this setting. We first show that, surprisingly, the problem can be solved for a small number of processes (at most 5), but not beyond. This is due to indeterminacy in the case where there are several closest neighbors for a same process. By removing this indeterminacy with an additional hypothesis (choosing the closest neighbor according to an order on the positions of processes), we then show that the problem can be solved for any number of processes. We also show that up to one crash failure can be tolerated for the convergence problem.

cs.DC↗

arXiv2018

Limiting the Spread of Fake News on Social Media Platforms by Evaluating Users' Trustworthiness

Today's social media platforms enable to spread both authentic and fake news very quickly. Some approaches have been proposed to automatically detect such "fake" news based on their content, but it is difficult to agree on universal criteria of authenticity (which can be bypassed by adversaries once known). Besides, it is obviously impossible to have each news item checked by a human. In this paper, we a mechanism to limit the spread of fake news which is not based on content. It can be implemented as a plugin on a social media platform. The principle is as follows: a team of fact-checkers reviews a small number of news items (the most popular ones), which enables to have an estimation of each user's inclination to share fake news items. Then, using a Bayesian approach, we estimate the trustworthiness of future news items, and treat accordingly those of them that pass a certain "untrustworthiness" threshold. We then evaluate the effectiveness and overhead of this technique on a large Twitter graph. We show that having a few thousands users exposed to one given news item enables to reach a very precise estimation of its reliability. We thus identify more than 99% of fake news items with no false positives. The performance impact is very small: the induced overhead on the 90th percentile latency is less than 3%, and less than 8% on the throughput of user operations.

cs.SI↗

arXiv2018

Removing Algorithmic Discrimination (With Minimal Individual Error)

We address the problem of correcting group discriminations within a score function, while minimizing the individual error. Each group is described by a probability density function on the set of profiles. We first solve the problem analytically in the case of two populations, with a uniform bonus-malus on the zones where each population is a majority. We then address the general case of n populations, where the entanglement of populations does not allow a similar analytical solution. We show that an approximate solution with an arbitrarily high level of precision can be computed with linear programming. Finally, we address the inverse problem where the error should not go beyond a certain value and we seek to minimize the discrimination.

cs.AI↗

arXiv2018

Virtuously Safe Reinforcement Learning

We show that when a third party, the adversary, steps into the two-party setting (agent and operator) of safely interruptible reinforcement learning, a trade-off has to be made between the probability of following the optimal policy in the limit, and the probability of escaping a dangerous situation created by the adversary. So far, the work on safely interruptible agents has assumed a perfect perception of the agent about its environment (no adversary), and therefore implicitly set the second probability to zero, by explicitly seeking a value of one for the first probability. We show that (1) agents can be made both interruptible and adversary-resilient, and (2) the interruptibility can be made safe in the sense that the agent itself will not seek to avoid it. We also solve the problem that arises when the agent does not go completely greedy, i.e. issues with safe exploration in the limit. Resilience to perturbed perception, safe exploration in the limit, and safe interruptibility are the three pillars of what we call \emph{virtuously safe reinforcement learning}.

cs.LG↗

arXiv2018

Learning to Gather without Communication

A standard belief on emerging collective behavior is that it emerges from simple individual rules. Most of the mathematical research on such collective behavior starts from imperative individual rules, like always go to the center. But how could an (optimal) individual rule emerge during a short period within the group lifetime, especially if communication is not available. We argue that such rules can actually emerge in a group in a short span of time via collective (multi-agent) reinforcement learning, i.e learning via rewards and punishments. We consider the gathering problem: several agents (social animals, swarming robots...) must gather around a same position, which is not determined in advance. They must do so without communication on their planned decision, just by looking at the position of other agents. We present the first experimental evidence that a gathering behavior can be learned without communication in a partially observable environment. The learned behavior has the same properties as a self-stabilizing distributed algorithm, as processes can gather from any initial state (and thus tolerate any transient failure). Besides, we show that it is possible to tolerate the brutal loss of up to 90\% of agents without significant impact on the behavior.

q-bio.PE↗

arXiv2017

Dynamic Safe Interruptibility for Decentralized Multi-Agent Reinforcement Learning

In reinforcement learning, agents learn by performing actions and observing their outcomes. Sometimes, it is desirable for a human operator to \textit{interrupt} an agent in order to prevent dangerous situations from happening. Yet, as part of their learning process, agents may link these interruptions, that impact their reward, to specific states and deliberately avoid them. The situation is particularly challenging in a multi-agent context because agents might not only learn from their own past interruptions, but also from those of other agents. Orseau and Armstrong defined \emph{safe interruptibility} for one learner, but their work does not naturally extend to multi-agent systems. This paper introduces \textit{dynamic safe interruptibility}, an alternative definition more suited to decentralized learning problems, and studies this notion in two learning frameworks: \textit{joint action learners} and \textit{independent learners}. We give realistic sufficient conditions on the learning algorithm to enable dynamic safe interruptibility in the case of joint action learners, yet show that these conditions are not sufficient for independent learners. We show however that if agents can detect interruptions, it is possible to prune the observations to ensure dynamic safe interruptibility even for independent learners.

cs.AI↗

arXiv2015

Reliable Communication in a Dynamic Network in the Presence of Byzantine Faults

We consider the following problem: two nodes want to reliably communicate in a dynamic multihop network where some nodes have been compromised, and may have a totally arbitrary and unpredictable behavior. These nodes are called Byzantine. We consider the two cases where cryptography is available and not available. We prove the necessary and sufficient condition (that is, the weakest possible condition) to ensure reliable communication in this context. Our proof is constructive, as we provide Byzantine-resilient algorithms for reliable communication that are optimal with respect to our impossibility results. In a second part, we investigate the impact of our conditions in three case studies: participants interacting in a conference, robots moving on a grid and agents in the subway. Our simulations indicate a clear benefit of using our algorithms for reliable communication in those contexts.

cs.DC↗

arXiv2013

Parameterizable Byzantine Broadcast in Loosely Connected Networks

We consider the problem of reliably broadcasting information in a multihop asynchronous network, despite the presence of Byzantine failures: some nodes are malicious and behave arbitrarly. We focus on non-cryptographic solutions. Most existing approaches give conditions for perfect reliable broadcast (all correct nodes deliver the good information), but require a highly connected network. A probabilistic approach was recently proposed for loosely connected networks: the Byzantine failures are randomly distributed, and the correct nodes deliver the good information with high probability. A first solution require the nodes to initially know their position on the network, which may be difficult or impossible in self-organizing or dynamic networks. A second solution relaxed this hypothesis but has much weaker Byzantine tolerance guarantees. In this paper, we propose a parameterizable broadcast protocol that does not require nodes to have any knowledge about the network. We give a deterministic technique to compute a set of nodes that always deliver authentic information, for a given set of Byzantine failures. Then, we use this technique to experimentally evaluate our protocol, and show that it significantely outperforms previous solutions with the same hypotheses. Important disclaimer: these results have NOT yet been published in an international conference or journal. This is just a technical report presenting intermediary and incomplete results. A generalized version of these results may be under submission.

cs.DC↗

arXiv2013

On Byzantine Broadcast in Planar Graphs

We consider the problem of reliably broadcasting information in a multihop asynchronous network in the presence of Byzantine failures: some nodes may exhibit unpredictable malicious behavior. We focus on completely decentralized solutions. Few Byzantine-robust algorithms exist for loosely connected networks. A recent solution guarantees reliable broadcast on a torus when D > 4, D being the minimal distance between two Byzantine nodes. In this paper, we generalize this result to 4-connected planar graphs. We show that reliable broadcast can be guaranteed when D > Z, Z being the maximal number of edges per polygon. We also show that this bound on D is a lower bound for this class of graphs. Our solution has the same time complexity as a simple broadcast. This is also the first solution where the memory required increases linearly (instead of exponentially) with the size of transmitted information. Important disclaimer: these results have NOT yet been published in an international conference or journal. This is just a technical report presenting intermediary and incomplete results. A generalized version of these results may be under submission.

cs.DS↗

arXiv2012

A Scalable Byzantine Grid

Modern networks assemble an ever growing number of nodes. However, it remains difficult to increase the number of channels per node, thus the maximal degree of the network may be bounded. This is typically the case in grid topology networks, where each node has at most four neighbors. In this paper, we address the following issue: if each node is likely to fail in an unpredictable manner, how can we preserve some global reliability guarantees when the number of nodes keeps increasing unboundedly ? To be more specific, we consider the problem or reliably broadcasting information on an asynchronous grid in the presence of Byzantine failures -- that is, some nodes may have an arbitrary and potentially malicious behavior. Our requirement is that a constant fraction of correct nodes remain able to achieve reliable communication. Existing solutions can only tolerate a fixed number of Byzantine failures if they adopt a worst-case placement scheme. Besides, if we assume a constant Byzantine ratio (each node has the same probability to be Byzantine), the probability to have a fatal placement approaches 1 when the number of nodes increases, and reliability guarantees collapse. In this paper, we propose the first broadcast protocol that overcomes these difficulties. First, the number of Byzantine failures that can be tolerated (if they adopt the worst-case placement) now increases with the number of nodes. Second, we are able to tolerate a constant Byzantine ratio, however large the grid may be. In other words, the grid becomes scalable. This result has important security applications in ultra-large networks, where each node has a given probability to misbehave.

cs.DC↗

arXiv2012

On Byzantine Broadcast in Loosely Connected Networks

We consider the problem of reliably broadcasting information in a multihop asynchronous network that is subject to Byzantine failures. Most existing approaches give conditions for perfect reliable broadcast (all correct nodes deliver the authentic message and nothing else), but they require a highly connected network. An approach giving only probabilistic guarantees (correct nodes deliver the authentic message with high probability) was recently proposed for loosely connected networks, such as grids and tori. Yet, the proposed solution requires a specific initialization (that includes global knowledge) of each node, which may be difficult or impossible to guarantee in self-organizing networks - for instance, a wireless sensor network, especially if they are prone to Byzantine failures. In this paper, we propose a new protocol offering guarantees for loosely connected networks that does not require such global knowledge dependent initialization. In more details, we give a methodology to determine whether a set of nodes will always deliver the authentic message, in any execution. Then, we give conditions for perfect reliable broadcast in a torus network. Finally, we provide experimental evaluation for our solution, and determine the number of randomly distributed Byzantine failures than can be tolerated, for a given correct broadcast probability.

cs.DC↗

arXiv2012

Limiting Byzantien Influence in Multihop Asynchronous Networks

We consider the problem of reliably broadcasting information in a multihop asyn- chronous network that is subject to Byzantine failures. That is, some nodes of the network can exhibit arbitrary (and potentially malicious) behavior. Existing solutions provide de- terministic guarantees for broadcasting between all correct nodes, but require that the communication network is highly-connected (typically, 2k + 1 connectivity is required, where k is the total number of Byzantine nodes in the network). In this paper, we investigate the possibility of Byzantine tolerant reliable broadcast be- tween most correct nodes in low-connectivity networks (typically, networks with constant connectivity). In more details, we propose a new broadcast protocol that is specifically designed for low-connectivity networks. We provide sufficient conditions for correct nodes using our protocol to reliably communicate despite Byzantine participants. We present experimental results that show that our approach is especially effective in low-connectivity networks when Byzantine nodes are randomly distributed.

cs.DS↗