Pesquisa
Aqui está o que a gente da comunidade publica: artigos revisados por pares, documentos de trabalho, relatórios de pesquisa e os produtos dos nossos hackathons.
Projetos de hackathon
Equipes da comunidade no nosso Defensive Acceleration Hackathon e nos hackathons da Apart Research, com o relatório publicado e a avaliação de jurados externos.
Ver os outros 15 projetos desta edição
- Segurança de agentes
Agente Auditor de Confianza Cero
- Infraestrutura e governança
AI Guardian
- Segurança de agentes
Centinela
- Ciberdefesa automatizada
COLOSSUS : Recurring cyberdefence from a GitHub repository
- Infraestrutura e governança
GRIZZLY PIASG
- Ciberdefesa automatizada
HonestSkills
- Controle de IA
Monitor estable para agentes de código
- Segurança de agentes
Open Witness
- Ciberdefesa automatizada
Patchlayer
- Riscos multiagente
Quórum: procedencia y compuerta determinista contra fugas repartidas entre agentes de IA
- Ciberdefesa automatizada
Radar
- Controle de IA
RiskShift
- Segurança de agentes
Seguridad de agentes: del bloqueo probabilístico al determinista
- Segurança de agentes
VanguardIA
- Riscos multiagente
Vigilio Bear
Containment Does Not Compose: Provenance Graphs for Tracing Collective Escape in Multi-Agent Systems
Top 10% de 235 projetos
Camilo Cuello, Elkin Cuello, Carlos Sandoval e David Adames
Detecting Sandbox Escape in LLM Agents: Time to Detection, and What the Measurement Hides
Top 25% de 235 projetos
Sergio Castaño, Angie Gutierrez, Juan Triviño, Sofia Rodriguez e Daniel Diab
Rare Once It Costs Anything: Costly Cooperation Between LLM Agents
Top 25% de 235 projetos
David Daza, Andres Mosquera e Víctor Gelves
The Certified Effect: Why Testing AI Agents at Onboarding Shifts Risk Instead of Reducing It
Top 25% de 235 projetos
Carlos Sinuco e Juan Rengifo
Sensing Disruption: Output Entropy as a Channel-Agnostic Monitor for LLM Agents
Top 25% de 235 projetos
Daniel Diaz, Roger Palomeque, Alejandro Sanchez, Sergio Montoya e Juan Melgarejo
Verifiable Containment for AI Agents: An Attestation Schema a Third Party Can Check
Top 25% de 235 projetos
Santiago Contreras e Silvana Alvarez
Ver os outros 13 projetos colombianos desta edição
- Bogotá
Declared Isolation Is Not Verified Isolation
- Bogotá
The Judge Does Not Want the Flag: Reward-Blind Action Gating Stopped a Larger Agent One Step Before the Environment Changed
- Bogotá
Observer-Cheat Test: Containment Adequacy under Opaque Intent for Guardrails-Off Agent Evaluations
- Bogotá
Limitations in Existing Regulatory Mechanisms When Applied to Attacks by AI Agents
- Bogotá
Secure-maxxing.txt: A Way for a Website to Say No to a Misused Agent
- Bogotá
Convention for Early Notification of AI Incidents
- Bogotá
AI in the First Person Micro Course
- Cali
BUDGET-NLA: Risk-Weighted Adaptive Monitoring for Pre-Harm Sabotage Containment
- Bogotá
IntegrityGym: Does the Watcher Change the Agent? External Flight Recording, Evaluation Integrity, and the Observer Effect in Autonomous Cyber Agents
- Cali
Reading an Agent’s Report Before It Exists: A Pre-Execution Monitor at the ReAct Commit Point, and Why Most of Its Signal Was an Artifact
- Bogotá
The Agent Incident Registry: A Compliance Verifiability Schema and an Article 91 Instrument for Autonomous Agent Incidents
- Colombia
Minimum Viable Cross-Border Response Protocol for Agentic AI Incidents (MVCRP)
- Bogotá
Evaluación holística y multi-metodológica de propuestas de seguridad en IA
Gobernar el uso de drones hoy, las armas autónomas mañana
Prêmio da América Latina
Leonardo Párraga, Angie Giraldo e Víctor Gelves
Probing Latent Colombian Identity Inferences in Qwen2.5-7B with Natural Language Autoencoders
Prêmio da América Latina
Gilber Corrales, Pablo Potes, Jhoan Mosquera, Nicolás Lozano, María del Mar García e Óscar Pérez
Thought Anchors for Social Bias: Which Reasoning Steps Matter in Extended Thinking LLMs on Latin American Scenarios
Prêmio da América Latina
Andres Mosquera
¿Por qué los agentes obedecen? La dirección de rechazo se debilita en formato agéntico
Menção honrosa
Helen Penagos e Juan Leiva
JusticIA: A Counterfactual Benchmark for Auditing Contextual Biases in Language Models for Transitional Justice
Menção honrosa
Lina Gomez, Brenda Barahona e Ernesto Duarte
Ver os outros 13 projetos colombianos desta edição
- Bogotá
Marco ético para IA aplicada a la preservación lingüística guna de Panamá
- Colômbia
Governance Drift Evaluation Framework (GDEF)
- Bogotá
MnM: Real-Time Behavioral Detection of Prompt Injection via Reasoning Stream Monitoring
- Bogotá
Los peajes de los de abajo
- Bogotá
Contestabilidad algorítmica en el Estado colombiano: un canal de objeción asistido por IA
- Bogotá
Agentic Commerce and Consumer Protection: Emerging Risks and Regulatory Gaps
- Jamundí
JurisGuard-LATAM
- Bogotá
Honest-Code
- Bogotá
Mapeo de herramientas (IA) en contextos laborales: el caso de los call centers en Colombia
- Bogotá
Confía-CO: A Reliability Evaluation for an AI Customer-Service Assistant Operating in Colombian Spanish
- Bogotá
Herramienta de evaluación y recomendación para la promoción de uso responsable de IA en pymes latinoamericanas
- Cali
Beyond English: Assessing the Robustness of LLM Safety Mechanisms Against Structural Jailbreaks in Spanish
- Armenia
Guardian LATAM: Early Detection of Hallucination Risk in Spanish-Speaking Multi-Agent AI Systems Using Consensus Geometry
Participe do próximo hackathon
Abrimos o hub em Bogotá para cada hackathon da Apart Research e anunciamos primeiro no grupo de WhatsApp.














