Antonio Cinà

Exciting news! Together with @LorenzoCazz, our tutorial Towards Adversarially Robust ML in The Age of The AI Act is accepted at ECAI 2025! Learn how to secure AI in high-risk settings & meet new EU rules. 📅 Bologna, Oct 25–30 🔗 sites.google.com/view/robust-ai… #ECAI2025 #TrustworthyAI

Joint collaboration with @jerome_rony @maurapintor @zangobot @ambrademontis @biggiobattista @IsmailBenAyed1 @fabiogroli

🌟 AttackBench is open-source, allowing researchers to contribute and update the leaderboard of existing attacks. 📜 Paper: arxiv.org/pdf/2404.19460 🧑‍💻 GitHub: github.com/attackbench/at… 🏆 Online LeaderBoard: attackbench.github.io #OpenSource #ResearchCommunity #Robustness

🚨 New research alert! AttackBench introduces a fair comparison benchmark for gradient-based attacks, addressing limitations in current evaluation methods. 📜Paper: arxiv.org/pdf/2404.19460 🏆LeaderBoard: attackbench.github.io #MLSecurity #AdversarialAttacks #AI #adversarial

@thorstenholz @piraxtor @leaschnherr @OestAdam @pvadrevu Thank you @thorstenholz, it was a great pleasure to work with such an exceptional team!

This work was a great collaboration with @piraxtor, Saad, @cinofix, @leaschnherr, Dai, @OestAdam, and @pvadrevu

In the paper "Conning the Crypto Conman: End-to-End Analysis of Cryptocurrency-based Technical Support Scams" (arxiv.org/abs/2401.09824), we perform a comprehensive study of cryptocurrency-based technical support scams via creating honey tweets on X. We show a technique on how...

@piraxtor @IEEESSP @5_aad_ @leaschnherr @hdainguyen @OestAdam @pvadrevu @thorstenholz Thank you @piraxtor, it was a great pleasure working with the whole amazing team! This is the starting point of a long collaboration ;-)

(1/5) Super excited that I will be presenting Conning the Crypto Conman: End-to-End Analysis of Cryptocurrency-based Technical Support Scams on May 20 @IEEESSP - collaboration with fabulous researchers- @5_aad_,@cinofix,@leaschnherr,@hdainguyen,@OestAdam,@pvadrevu,@thorstenholz

📢 Call for Papers: Workshop on "Human Aligned AI: Towards Algorithms that Humans Can Trust." Discuss trustworthiness in AI, exploring strategies to ensure alignment with human values. Submit by July 31st! ➡️ Conference: icmla-conference.org/icmla24/ ➡️ CFP: icmla-conference.org/icmla24/worksh…