Search

With the popularity of virtual assistants (e.g., Siri, Alexa), the use of speech recognition is now becoming more and more widespread.However, speech signals contain a lot of sensitive information, such as the speaker's identity, which raises privacy concerns.The presented experiments show that the representations extracted by the deep layers of speech recognition networks contain speaker information.This paper aims to produce an anonymous representation while preserving speech recognition performance.To this end, we propose to use vector quantization to constrain the representation space and induce the network to suppress the speaker identity.The choice of the quantization dictionary size allows to configure the trade-off between utility (speech recognition) and privacy (speaker identity concealment)., Journ{\'e}es d'{\'E}tudes sur la Parole - JEP2022, Jun 2022, {\^I}le de Noirmoutier, France

Generating user activity is a key capability for both evaluating security monitoring tools as well as improving the credibility of attacker analysis platforms (e.g., honeynets). In this paper, to generate this activity, we instrument each machine by means of an external agent. This agent combines both deterministic and deep learning based methods to adapt to different environment (e.g., multiple OS, software versions, etc.), while maintaining high performances. We also propose conditional text generation models to facilitate the creation of conversations and documents to accelerate the definition of coherent, system-wide, life scenarios., in French

Recent advancements in Artificial Intelligence (AI) have brought new capabilities to behavioural analysis (UEBA) for cyber-security consisting in the detection of hostile action based on the unusual nature of events observed on the Information System.In our previous work (presented at C\&ESAR 2018 and FIC 2019), we have associated deep neural networks auto-encoders for anomaly detection and graph-based events correlation to address major limitations in UEBA systems. This resulted in reduced false positive and false negative rates, improved alert explainability, while maintaining real-time performances and scalability. However, we did not address the natural evolution of behaviours through time, also known as concept drift. To maintain effective detection capabilities, an anomaly-based detection system must be continually trained, which opens a door to an adversary that can conduct the so-called "frog-boiling" attack by progressively distilling unnoticed attack traces inside the behavioural models until the complete attack is considered normal. In this paper, we present a solution to effectively mitigate this attack by improving the detection process and efficiently leveraging human expertise. We also present preliminary work on adversarial AI conducting deception attack, which, in term, will be used to help assess and improve the defense system. These defensive and offensive AI implement joint, continual and active learning, in a step that is necessary in assessing, validating and certifying AI-based defensive solutions., in French. European Cyber Week - CESAR/IAD Conference - Artificial Intelligence and Defence, French Ministry of Defence, Nov 2019, Rennes, France

Wireless Sensor Network (WSN) is consisting of independent and distributed sensors to monitor physical or environmental conditions, such as temperature, sound, pressure, etc. The most crucial and fundamental challenge facing WSN is security. Due to minimum capacity in-term of memory cost, processing and physical accessibility to sensors devices the security attacks are problematic. They are mostly deployed in open area, which expose them to different kinds of attacks. In this paper, we present an illustration of different attacks and vulnerabilities in WSN. Then we proposed a new lightweight cryptography algorithm for identifying compromised node in WSN called Leap Enhanced. Our evaluations on TOSSIM give a precise and detailed idea of the extra cost of consumption of resources needed to ensure the high level of expected security compared to other cryptography schemes in literature., in French