Alejandro MosqueraDetecting LLM hallucinations and overgeneration mistakes @ SemEval 2024The modern NLG landscape is plagued by two interlinked problems: On the one hand, our current neural models have a propensity to produce…5 min read·20 hours ago----
Alejandro MosqueraHackaprompt-2023 @ AICrowd write upHackAPrompt was a prompt hacking competition aimed at enhancing AI safety and education by challenging participants to outsmart large…3 min read·21 hours ago----
Alejandro MosqueraAI Village Capture the Flag @ DEFCON 30 write upIn August 2022 I had the chance to participate in an AI-themed CTF collocated with the DEF CON 30 security (hacking) conference. This was…3 min read·Feb 16, 2023----
Alejandro MosqueraDefending and attacking ML Malware Classifiers for Fun and Profit: 2x prize winner at MLSEC-2021MLSEC (Machine Learning Security Evasion Competition) is an initiative sponsored by Microsoft and partners CUJO AI, NVIDIA, VMRay, and MRG…4 min read·Feb 16, 2023----
Alejandro MosqueraRevisiting the Microsoft Malware Classification Challenge (BIG 2015) in 2023In 2015, Microsoft provided the data science community with an unprecedented malware dataset and encouraging open-source progress on…2 min read·Feb 16, 2023----
Alejandro MosqueraPretrained Models with Adversarial Training for Online Sexism Detection @ SemEval 2023Abstract5 min read·Feb 16, 2023----
Alejandro MosqueraOn the Intriguing Properties of Backdoored Neural NetworksIntroduction8 min read·Dec 26, 2022----