Vasilios Mavroudis

82 papers A* 6A 2B 2Journal 55Unranked 17

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Beyond Rewards in Reinforcement Learning for Cyber Defence. CoRR Elizabeth Bates, Chris Hicks, Vasilios Mavroudis
2026	A*	`conf`	Beyond Training-time Poisoning: Component-level and Post-training Backdoors in Deep Reinforcement Learning. AAAI Sanyam Vyas, Alberto Caron, Chris Hicks, Pete Burnap, Vasilios Mavroudis
2026	A*	`conf`	DRMD: Deep Reinforcement Learning for Malware Detection Under Concept Drift. AAAI Shae McFadden, Myles Foley, Mario D'Onghia, Chris Hicks, Vasilios Mavroudis, Nicola Paoletti, Fabio Pierazzi
2026	J	`jnl`	From Promise to Peril: Rethinking Cybersecurity Red and Blue Teaming in the Age of LLMs. IEEE Secur. Priv. Alsharif Abuadbba, Kristen Moore, Diksha Goel, Chris Hicks, Vasilios Mavroudis, Burak Hasircioglu, Piers Jennings
2026	J	`jnl`	Frontier AI Auditing: Toward Rigorous Third-Party Assessment of Safety and Security Practices at Leading AI Companies. CoRR Miles Brundage, Noemi Dreksler, Aidan Homewood, Sean McGregor, Patricia Paskov, Conrad Stosz, Girish Sastry, A. Feder Cooper, George Balston, Steven Adler, Stephen Casper, Markus Anderljung, Grace W. Lindsay, Sören Mindermann, Vasilios Mavroudis, Ben Bucknall, Charlotte Stix, Jonas Freund, Lorenzo Pacchiardi, José Hernández-Orallo, Matteo Pistillo, Michael Chen, Chris Painter, Dean W. Ball, Cullen O'Keefe, Gabriel Weil, Ben Harack, Graeme Finley, Ryan Hassan, Scott Emmons, Charles Foster, Anka Reuel, Bri Treece, Yoshua Bengio, Daniel Reti, Rishi Bommasani, Cristian Trout, Ali Shahin Shamsabadi, Rajiv Dattani, Adrian Weller, Robert Trager, Jaime Sevilla, Lauren Wagner, Lisa Soder, Ketan Ramakrishnan, Henry Papadatos, Malcolm Murray, Ryan Tovcimak
2026	J	`jnl`	International AI Safety Report 2026. CoRR Yoshua Bengio, Stephen Clare, Carina Prunkl, Maksym Andriushchenko, Ben Bucknall, Malcolm Murray, Rishi Bommasani, Stephen Casper, Tom Davidson, Raymond Douglas, David Duvenaud, Philip Fox, Usman Gohar, Rose Hadshar, Anson Ho, Tiancheng Hu, Cameron Jones, Sayash Kapoor, Atoosa Kasirzadeh, Sam Manning, Nestor Maslej, Vasilios Mavroudis, Conor McGlynn, Richard Moulange, Jessica Newman, Kwan Yee Ng, Patricia Paskov, Shalaleh Rismani, Girish Sastry, Elizabeth Seger, Scott Singer, Charlotte Stix, Lucia Velasco, Nicole Wheeler
2026	J	`jnl`	One Pic is All it Takes: Poisoning Visual Document Retrieval Augmented Generation with a Single Image. Trans. Mach. Learn. Res. Ezzeldin Shereen, Dan Ristea, Shae McFadden, Burak Hasircioglu, Vasilios Mavroudis, Chris Hicks
2026	J	`jnl`	SoK: The Pitfalls of Deep Reinforcement Learning for Cybersecurity. CoRR Shae McFadden, Myles Foley, Elizabeth Bates, Ilias Tsingenopoulos, Sanyam Vyas, Vasilios Mavroudis, Chris Hicks, Fabio Pierazzi
2026	J	`jnl`	The science and practice of proportionality in AI risk evaluations. CoRR Carlos Mougan, Lauritz Morlock, Jair Aguirre, James R. M. Black, Jan Brauner, Siméon Campos, Sunishchal Dev, David Fernández Llorca, Alberto Franzin, Mario Fritz, Emilia Gómez, Friederike Grosse-Holz, Eloise Hamilton, Max Hasin, José Hernández-Orallo, Dan Lahav, Luca Massarelli, Vasilios Mavroudis, Malcolm Murray, Patricia Paskov, Jaime Raldua, Wout Schellaert
2026	J	`jnl`	Towards the Deployment of Realistic Autonomous Cyber Network Defence: A Systematic Review. ACM Comput. Surv. Sanyam Vyas, Vasilios Mavroudis, Pete Burnap
2025	J	`jnl`	A Hierarchical Nearest Neighbour Approach to Contextual Bandits. Trans. Mach. Learn. Res. Stephen Pasteris, Madeleine Dwyer, Chris Hicks, Vasilios Mavroudis
2025	—	`conf`	Adversarial Evasion Against Autonomous Cyber Defence Agents. ESORICS Workshops (3) Melanie Meijer, Sanyam Vyas, Vasilios Mavroudis, Marc Juarez
2025	J	`jnl`	Analysis of Publicly Accessible Operational Technology and Associated Risks. CoRR Matthew Rodda, Vasilios Mavroudis
2025	J	`jnl`	Beyond Training-time Poisoning: Component-level and Post-training Backdoors in Deep Reinforcement Learning. CoRR Sanyam Vyas, Alberto Caron, Chris Hicks, Pete Burnap, Vasilios Mavroudis
2025	J	`jnl`	DRMD: Deep Reinforcement Learning for Malware Detection under Concept Drift. CoRR Shae McFadden, Myles Foley, Mario D'Onghia, Chris Hicks, Vasilios Mavroudis, Nicola Paoletti, Fabio Pierazzi
2025	J	`jnl`	From Promise to Peril: Rethinking Cybersecurity Red and Blue Teaming in the Age of LLMs. CoRR Alsharif Abuadbba, Chris Hicks, Kristen Moore, Vasilios Mavroudis, Burak Hasircioglu, Diksha Goel, Piers Jennings
2025	J	`jnl`	Guidelines for Applying RL and MARL in Cybersecurity Applications. CoRR Vasilios Mavroudis, Gregory Palmer, Sara Farmer, Kez Smithson Whitehead, David Foster, Adam Price, Ian Miles, Alberto Caron, Stephen Pasteris
2025	J	`jnl`	International AI Safety Report 2025: First Key Update: Capabilities and Risk Implications. CoRR Yoshua Bengio, Stephen Clare, Carina Prunkl, Shalaleh Rismani, Maksym Andriushchenko, Ben Bucknall, Philip Fox, Tiancheng Hu, Cameron Jones, Sam Manning, Nestor Maslej, Vasilios Mavroudis, Conor McGlynn, Malcolm Murray, Charlotte Stix, Lucia Velasco, Nicole Wheeler, Daniel Privitera, Sören Mindermann, Daron Acemoglu, Thomas G. Dietterich, Fredrik Heintz, Geoffrey E. Hinton, Nicholas R. Jennings, Susan Leavy, Teresa Ludermir, Vidushi Marda, Helen Margetts, John A. McDermid, Jane Munga, Arvind Narayanan, Alondra Nelson, Clara Neppel, Gopal Ramchurn, Stuart Russell, Marietje Schaake, Bernhard Schölkopf, Alavaro Soto, Lee Tiedrich, Gaël Varoquaux, Andrew Yao, Yan-Ning Zhang, Leandro Aguirre, Olubunmi Ajala, Fahad Albalawi Noora AlMalek, Christian Busch, André C. P. L. F. de Carvalho, Jonathan Collas, Amandeep Gill, Ahmet Halit Hatip, Juha Heikkilä, Chris Johnson, Gill Jolly, Ziv Katzir, Mary Kerema, Hiroaki Kitano, Antonio Krüger, Aoife McLysaght, Oleksii Molchanovskyi, Andrea Monti, Kyoung Mu Lee, Mona Nemer, Nuria Oliver, Raquel Pezoa Rivera, Audrey Plonk, José Ramón López Portillo, Balaraman Ravindran, Hammam Riza, Crystal Rugege, Haroon Sheikh, Denise Wong, Yi Zeng, Liming Zhu
2025	J	`jnl`	International AI Safety Report. CoRR Yoshua Bengio, Sören Mindermann, Daniel Privitera, Tamay Besiroglu, Rishi Bommasani, Stephen Casper, Yejin Choi, Philip Fox, Ben Garfinkel, Danielle Goldfarb, Hoda Heidari, Anson Ho, Sayash Kapoor, Leila Khalatbari, Shayne Longpre, Sam Manning, Vasilios Mavroudis, Mantas Mazeika, Julian Michael, Jessica Newman, Kwan Yee Ng, Chinasa T. Okolo, Inioluwa Deborah Raji, Girish Sastry, Elizabeth Seger, Theodora Skeadas, Tobin South, Emma Strubell, Florian Tramèr, Lucia Velasco, Nicole Wheeler, Daron Acemoglu, Olubayo Adekanmbi, David Dalrymple, Thomas G. Dietterich, Edward W. Felten, Pascale Fung, Pierre-Olivier Gourinchas, Fredrik Heintz, Geoffrey E. Hinton, Nick R. Jennings, Andreas Krause, Susan Leavy, Percy Liang, Teresa Ludermir, Vidushi Marda, Helen Margetts, John A. McDermid, Jane Munga, Arvind Narayanan, Alondra Nelson, Clara Neppel, Alice Oh, Gopal Ramchurn, Stuart Russell, Marietje Schaake, Bernhard Schölkopf, Dawn Song, Alvaro Soto, Lee Tiedrich, Gaël Varoquaux, Andrew Yao, Ya-Qin Zhang, Fahad Albalawi, Marwan Alserkal, Olubunmi Ajala, Guillaume Avrin, Christian Busch, André Carlos Ponce de Leon Ferreira de Carvalho, Bronwyn Fox, Amandeep Singh Gill, Ahmet Halit Hatip, Juha Heikkilä, Gill Jolly, Ziv Katzir, Hiroaki Kitano, Antonio Krüger, Chris Johnson, Saif M. Khan, Kyoung Mu Lee, Dominic Vincent Ligot, Oleksii Molchanovskyi, Andrea Monti, Nusu Mwamanzi, Mona Nemer, Nuria Oliver, José Ramón López Portillo, Balaraman Ravindran, Raquel Pezoa Rivera, Hammam Riza, Crystal Rugege, Ciarán Seoighe, Jerry Sheehan, Haroon Sheikh, Denise Wong, Yi Zeng
2025	J	`jnl`	Less is more? Rewards in RL for Cyber Defence. CoRR Elizabeth Bates, Chris Hicks, Vasilios Mavroudis
2025	J	`jnl`	On Efficient Bayesian Exploration in Model-Based Reinforcement Learning. CoRR Alberto Caron, Chris Hicks, Vasilios Mavroudis
2025	J	`jnl`	On Efficient Bayesian Exploration in Model-Based Reinforcement Learning. Trans. Mach. Learn. Res. Alberto Caron, Vasilios Mavroudis, Chris Hicks
2025	J	`jnl`	One Pic is All it Takes: Poisoning Visual Document Retrieval Augmented Generation with a Single Image. CoRR Ezzeldin Shereen, Dan Ristea, Burak Hasircioglu, Shae McFadden, Vasilios Mavroudis, Chris Hicks
2025	J	`jnl`	Poisoning Attacks on LLMs Require a Near-constant Number of Poison Samples. CoRR Alexandra Souly, Javier Rando, Ed Chapman, Xander Davies, Burak Hasircioglu, Ezzeldin Shereen, Carlos Mougan, Vasilios Mavroudis, Erik Jones, Chris Hicks, Nicholas Carlini, Yarin Gal, Robert Kirk
2025	J	`jnl`	Quantifying Mix Network Privacy Erosion with Generative Models. CoRR Vasilios Mavroudis, Tariq Elahi
2025	J	`jnl`	Toward Quantitative Modeling of Cybersecurity Risks Due to AI Misuse. CoRR Steve Barrett, Malcolm Murray, Otter Quarks, Matthew Smith, Jakub Krys, Siméon Campos, Alejandro Tlaie Boria, Chloé Touzet, Sevan Hayrapet, Fred Heiding, Omer Nevo, Adam Swanda, Jair Aguirre, Asher Brass Gershovich, Eric Clay, Ryan Fetterman, Mario Fritz, Marc Juarez, Vasilios Mavroudis, Henry Papadatos
2025	B	`conf`	Towards Autonomous Cyber Defence: Applying Systems Theoretic Process Analysis to Human-Machine Teaming. IJCNN Shu-Jui Chang, Chris Hicks, Vasilios Mavroudis, Iain Phillips, Tim Watson
2025	J	`jnl`	Towards Causal Model-Based Policy Optimization. CoRR Alberto Caron, Vasilios Mavroudis, Chris Hicks
2025	J	`jnl`	What if we could hot swap our Biometrics? CoRR Jon Crowcroft, Anil Madhavapeddy, Chris Hicks, Richard Mortier, Vasilios Mavroudis
2024	J	`jnl`	A View on Out-of-Distribution Identification from a Statistical Testing Theory Perspective. CoRR Alberto Caron, Chris Hicks, Vasilios Mavroudis
2024	J	`jnl`	Autonomous Network Defence using Reinforcement Learning. CoRR Myles Foley, Chris Hicks, Kate Highnam, Vasilios Mavroudis
2024	J	`jnl`	Benchmarking OpenAI o1 in Cyber Security. CoRR Dan Ristea, Vasilios Mavroudis, Chris Hicks
2024	J	`jnl`	CybORG++: An Enhanced Gym for the Development of Autonomous Cyber Agents. CoRR Harry Emerson, Liz Bates, Chris Hicks, Vasilios Mavroudis
2024	—	`conf`	Empirical Mixnet Design. GameSec (2) Yongzhao Wang, Tariq Elahi, Vasilios Mavroudis, Edward Plumb, Rahul Savani, Theodore L. Turocy
2024	—	`conf`	Entity-based Reinforcement Learning for Autonomous Cyber Defence. AutonomousCyber@CCS Isaac Symes Thompson, Alberto Caron, Chris Hicks, Vasilios Mavroudis
2024	J	`jnl`	Entity-based Reinforcement Learning for Autonomous Cyber Defence. CoRR Isaac Symes Thompson, Alberto Caron, Chris Hicks, Vasilios Mavroudis
2024	J	`jnl`	Environment Complexity and Nash Equilibria in a Sequential Social Dilemma. CoRR Mustafa Yasir, Andrew Howes, Vasilios Mavroudis, Chris Hicks
2024	J	`jnl`	Fair Exploration and Exploitation. CoRR Stephen Pasteris, Chris Hicks, Vasilios Mavroudis
2024	J	`jnl`	Fusion Encoder Networks. CoRR Stephen Pasteris, Chris Hicks, Vasilios Mavroudis
2024	—	`conf`	Inherently Interpretable and Uncertainty-Aware Models for Online Learning in Cyber-Security Problems. ACSAC Workshops Benjamin Kolicic, Alberto Caron, Vasilios Mavroudis, Chris Hicks
2024	J	`jnl`	Inherently Interpretable and Uncertainty-Aware Models for Online Learning in Cyber-Security Problems. CoRR Benjamin Kolicic, Alberto Caron, Chris Hicks, Vasilios Mavroudis
2024	J	`jnl`	International Scientific Report on the Safety of Advanced AI (Interim Report). CoRR Yoshua Bengio, Sören Mindermann, Daniel Privitera, Tamay Besiroglu, Rishi Bommasani, Stephen Casper, Yejin Choi, Danielle Goldfarb, Hoda Heidari, Leila Khalatbari, Shayne Longpre, Vasilios Mavroudis, Mantas Mazeika, Kwan Yee Ng, Chinasa T. Okolo, Inioluwa Deborah Raji, Theodora Skeadas, Florian Tramèr, Bayo Adekanmbi, Paul F. Christiano, David Dalrymple, Thomas G. Dietterich, Edward W. Felten, Pascale Fung, Pierre-Olivier Gourinchas, Nick R. Jennings, Andreas Krause, Percy Liang, Teresa Ludermir, Vidushi Marda, Helen Margetts, John A. McDermid, Arvind Narayanan, Alondra Nelson, Alice Oh, Gopal Ramchurn, Stuart Russell, Marietje Schaake, Dawn Song, Alvaro Soto, Lee Tiedrich, Gaël Varoquaux, Andrew Yao, Ya-Qin Zhang
2024	—	`conf`	Mitigating Deep Reinforcement Learning Backdoors in the Neural Activation Space. SP (Workshops) Sanyam Vyas, Chris Hicks, Vasilios Mavroudis
2024	J	`jnl`	Mitigating Deep Reinforcement Learning Backdoors in the Neural Activation Space. CoRR Sanyam Vyas, Chris Hicks, Vasilios Mavroudis
2024	A*	`conf`	Online Convex Optimisation: The Optimal Switching Regret for all Segmentations Simultaneously. NeurIPS Stephen Pasteris, Chris Hicks, Vasilios Mavroudis, Mark Herbster
2024	J	`jnl`	Online Convex Optimisation: The Optimal Switching Regret for all Segmentations Simultaneously. CoRR Stephen Pasteris, Chris Hicks, Vasilios Mavroudis, Mark Herbster
2024	J	`jnl`	SoK: On Closing the Applicability Gap in Automated Vulnerability Detection. CoRR Ezzeldin Shereen, Dan Ristea, Sanyam Vyas, Shae McFadden, Madeleine Dwyer, Chris Hicks, Vasilios Mavroudis
2024	—	`conf`	WENDIGO: Deep Reinforcement Learning for Denial-of-Service Query Discovery in GraphQL. SP (Workshops) Shae McFadden, Marcello Maugeri, Chris Hicks, Vasilios Mavroudis, Fabio Pierazzi
2024	J	`jnl`	Zero-Trust Network Access (ZTNA). CoRR Vasilios Mavroudis
2023	J	`jnl`	A Hierarchical Nearest Neighbour Approach to Contextual Bandits. CoRR Stephen Pasteris, Chris Hicks, Vasilios Mavroudis
2023	A	`conf`	Adaptive Webpage Fingerprinting from TLS Traces. DSN Vasilios Mavroudis, Jamie Hayes
2023	—	`conf`	Canaries and Whistles: Resilient Drone Communication Networks with (or without) Deep Reinforcement Learning. AISec@CCS Chris Hicks, Vasilios Mavroudis, Myles Foley, Thomas Davies, Kate Highnam, Tim Watson
2023	J	`jnl`	Canaries and Whistles: Resilient Drone Communication Networks with (or without) Deep Reinforcement Learning. CoRR Chris Hicks, Vasilios Mavroudis, Myles Foley, Thomas Davies, Kate Highnam, Tim Watson
2023	J	`jnl`	Inroads into Autonomous Network Defence using Explained Reinforcement Learning. CoRR Myles Foley, Mia Wang, Zoe M, Chris Hicks, Vasilios Mavroudis
2023	A*	`conf`	Nearest Neighbour with Bandit Feedback. NeurIPS Stephen Pasteris, Chris Hicks, Vasilios Mavroudis
2023	J	`jnl`	Nearest Neighbour with Bandit Feedback. CoRR Stephen Pasteris, Chris Hicks, Vasilios Mavroudis
2023	—	`conf`	Reward Shaping for Happier Autonomous Cyber Security Agents. AISec@CCS Elizabeth Bates, Vasilios Mavroudis, Chris Hicks
2023	J	`jnl`	Reward Shaping for Happier Autonomous Cyber Security Agents. CoRR Elizabeth Bates, Vasilios Mavroudis, Chris Hicks
2022	A	`conf`	Autonomous Network Defence using Reinforcement Learning. AsiaCCS Myles Foley, Chris Hicks, Kate Highnam, Vasilios Mavroudis
2022	—	`conf`	Inroads into Autonomous Network Defence using Explained Reinforcement Learning. CAMLIS Myles Foley, Mia Wang, Zoe M, Chris Hicks, Vasilios Mavroudis
2022	—	`conf`	SIMple ID: QR Codes for Authentication Using Basic Mobile Phones in Developing Countries. STM Chris Hicks, Vasilios Mavroudis, Jon Crowcroft
2021	—	`conf`	An Interface Between Legacy and Modern Mobile Devices for Digital Identity. ETAA Vasilios Mavroudis, Chris Hicks, Jon Crowcroft
2021	J	`jnl`	An Interface between Legacy and Modern Mobile Devices for Digital Identity. CoRR Vasilios Mavroudis, Chris Hicks, Jon Crowcroft
2020	J	`jnl`	Adaptive Traffic Fingerprinting: Large-scale Inference under Realistic Assumptions. CoRR Vasilios Mavroudis, Jamie Hayes
2020	—	`conf`	JCMathLib: Wrapper Cryptographic Library for Transparent and Certifiable JavaCard Applets. EuroS&P Workshops Vasilios Mavroudis, Petr Svenda
2020	A*	`conf`	Snappy: Fast On-chain Payments with Practical Collaterals. NDSS Vasilios Mavroudis, Karl Wüst, Aritra Dhar, Kari Kostiainen, Srdjan Capkun
2020	J	`jnl`	Snappy: Fast On-chain Payments with Practical Collaterals. CoRR Vasilios Mavroudis, Karl Wüst, Aritra Dhar, Kari Kostiainen, Srdjan Capkun
2019	—	`conf`	Bounded Temporal Fairness for FIFO Financial Markets (Transcript of Discussion). Security Protocols Workshop Vasilios Mavroudis
2019	—	`conf`	Bounded Temporal Fairness for FIFO Financial Markets. Security Protocols Workshop Vasilios Mavroudis
2019	B	`conf`	Libra: Fair Order-Matching for Electronic Financial Exchanges. AFT Vasilios Mavroudis, Hayden Melton
2019	J	`jnl`	Libra: Fair Order-Matching for Electronic Financial Exchanges. CoRR Vasilios Mavroudis, Hayden Melton
2019	—	`conf`	Location, Location, Location: Revisiting Modeling and Exploitation for Location-Based Side Channel Leakages. ASIACRYPT (3) Christos Andrikos, Lejla Batina, Lukasz Chmielewski, Liran Lerman, Vasilios Mavroudis, Kostas Papagiannopoulos, Guilherme Perin, Giorgos Rassias, Alberto Sonnino
2019	J	`jnl`	Location, location, location: Revisiting modeling and exploitation for location-based side channel leakages. IACR Cryptol. ePrint Arch. Christos Andrikos, Lejla Batina, Lukasz Chmielewski, Liran Lerman, Vasilios Mavroudis, Kostas Papagiannopoulos, Guilherme Perin, Giorgos Rassias, Alberto Sonnino
2019	J	`jnl`	Market Manipulation as a Security Problem. CoRR Vasilios Mavroudis
2019	—	`conf`	Market Manipulation as a Security Problem: Attacks and Defenses. EuroSec@EuroSys Vasilios Mavroudis
2018	J	`jnl`	Eavesdropping Whilst You're Shopping: Balancing Personalisation and Privacy in Connected Retail Spaces. CoRR Vasilios Mavroudis, Michael Veale
2018	J	`jnl`	Towards Low-level Cryptographic Primitives for JavaCards. CoRR Vasilios Mavroudis, Petr Svenda
2018	J	`jnl`	VAMS: Verifiable Auditing of Access to Confidential Data. CoRR Alexander Hicks, Vasilios Mavroudis, Mustafa Al-Bassam, Sarah Meiklejohn, Steven J. Murdoch
2017	A*	`conf`	A Touch of Evil: High-Assurance Cryptographic Hardware from Untrusted Components. CCS Vasilios Mavroudis, Andrea Cerulli, Petr Svenda, Dan Cvrcek, Dusan Klinec, George Danezis
2017	J	`jnl`	A Touch of Evil: High-Assurance Cryptographic Hardware from Untrusted Components. CoRR Vasilios Mavroudis, Andrea Cerulli, Petr Svenda, Dan Cvrcek, Dusan Klinec, George Danezis
2017	J	`jnl`	On the Privacy and Security of the Ultrasound Ecosystem. Proc. Priv. Enhancing Technol. Vasilios Mavroudis, Shuang Hao, Yanick Fratantonio, Federico Maggi, Christopher Kruegel, Giovanni Vigna
2014	—	`conf`	Visual Analytics for Enhancing Supervised Attack Attribution in Mobile Networks. ISCIS Stavros Papadopoulos, Vasilios Mavroudis, Anastasios Drosou, Dimitrios Tzovaras