Description
Recent research efforts on adversarial ML have investigated problem-space attacks, focusing on the generation of real evasive objects in domains where, unlike images, there is no clear inverse mapping to the feature space (e.g., software). However, the design, comparison, and real-world implications of problem-space attacks remain underexplored. In this talk, I will present two major contributions from our recent IEEE Symp. S&P 2020 paper [1]. First, I will present our novel reformulation of adversarial ML evasion attacks for the problem-space, with more constraints to consider than the feature-space and with more light shed on the relationship between feature-space and problem-space attacks. Second, building on our reformulation, I will present our novel problem-space attack for generating end-to-end evasive Android malware, showing that it is feasible to generative evasive malware at scale that also evade feature-space defenses.[1] Fabio Pierazzi*, Feargus Pendlebury*, Jacopo Cortellazzi, Lorenzo Cavallaro. “Intriguing Properties of Adversarial ML Attacks in the Problem Space”. IEEE Symp. Security & Privacy (Oakland), 2020.Trailer of the talkhttps://www.youtube.com/watch?v=lLrnHwrvYiQ
Infos pratiques
Prochains exposés
-
The Battle Against Bots: Current Threats and New Directions to Counter Automated Attacks
Orateur : Elisa Chiapponi - Amadeus IT Group
In today's digital landscape, the battle between industry and automated bots is an ever-evolving challenge. Attackers are leveraging advanced techniques such as residential proxies, CAPTCHA farms, and AI-enhanced fingerprint rotations to evade detection and execute functional abuse attacks, including web scraping, denial of inventory, and SMS pumping. This talk will explore ongoing efforts[…]-
SoSysec
-
Détection d'intrusion
-
-
Un protocole SMPC de curation de données d'entrainement et sa fragilité aux hypothèses de sécurité...
Orateur : Marc-Olivier Killijian - Université du Québec à Montréal
... ou "Sécurité et insécurité - dans quel état j’erre, ai-je bien rangé mon modèle de sécurité ?" De nos jours, les sources de données, et leurs curateurs, sont répartis à travers le monde. Il arrive que les propriétaires de ces données souhaitent collaborer entre eux afin d’augmenter la qualité de ces données, particulièrement avant d’entrainer des modèles d’apprentissage machine.Dans cet exposé[…]-
SoSysec
-
Respect de la vie privée
-
Apprentissage machine
-
Systèmes distribués
-
-
Safety-Security Convergence of Industrial Control Systems
Orateur : Maxime Puys - Université Clermont Auvergne - IUT de Clermont-Ferrand
Industrial Control Systems (ICS) are designed to provide a service, such as power generation or water treatment, while protecting people, assets, and the environment against hazards. However, ICS now integrate Information Technology (IT) and are interconnected with the outside world such as the Internet, thereby exposing their infrastructures to cyberattacks. Cyberattacks have thus become new[…]-
SoSysec
-
Détection d'intrusion
-