News
Latest updates, articles, and announcements from our laboratory.
All articles
ArticleShiba AI Members Present their paper at ICML 2026 in Seoul
Shiba AI represented its research at the International Conference on Machine Learning (ICML) 2026 in Seoul, presenting new work on multi-agent coordination and engaging with the global machine learning community.
Read
ArticleShiba AI Members Alice and Ujwal Secure 3rd Place at Tokyo AI x OpenAI Hackathon
Shiba AI members Ujwal K and Alice Saito place in the B2B category with Tsunagu, an AI-powered emergency response dispatcher system.
Read
ArticleShiba AI Members Complete the Technical Alignment Research Accelerator Program (TARA)
Seven researchers from Shiba AI have completed the selective 14-week APAC accelerator, executing technical capstones across agentic safety and adversarial vulnerabilities.
Read
ArticleShiba AI Lab Joins OASec 2026 as Community Supporter: CFP Open
Shiba AI is proud to announce its role as an official Community Supporter for OASec 2026, the premier practitioner-focused AI safety and security conference in the APAC region.
Read
ArticleVulnerability Research in the Age of AI: Deconstructing Mythos
A review of automated zero-day discovery across operating systems, hypervisors, and browsers with Pwn2Own winner Thanh Do.
Read
ArticleWhy We Study Multi-Agent Coordination
A look into why multi-agent coordination is central to AI alignment research.
ReadNews
Paper accepted at ECML PKDD 2026 BIAS Workshop
The paper "Gender Bias in LLM Hiring Decisions: Evidence from a Japanese Context and Evaluation of Mitigation Strategies," authored by Serena A. Hoffstedde, Machiko Hirota, Akshara Nadayanur Sathis Kanna, Rihito Kotani, Ujwal Kumar, Gabriele Trovato, and Phan Xuan Tan, has been accepted at the 7th International Workshop on Bias and Fairness in AI (BIAS 2026) co-located with ECML PKDD 2026!
Paper accepted at ICML 2026 Workshop TAIGR
The paper "Direct Causation in International Humanitarian Law and the Challenge of AI-Mediated Civilian Cyber Operations," authored by Alice and Harold, has been accepted at the ICML 2026 Workshop TAIGR!
Paper 'Evolving Interpretable Constitutions' accepted to ICML 2026
The paper "Evolving Interpretable Constitutions for Multi-Agent Coordination," authored by Ujwal K. and co-authors Alice Saito, Hershraj Niranjani and Rayan Yessou, has been accepted as a regular paper at the ICML 2026 Main Conference!
Strahinja Janjusevic is Securing Critical Maritime Infrastructure with AI
Strahinja (Strajo) Janjusevic, a graduate researcher at the MIT Laboratory for Information and Decision Systems (LIDS), is developing AI-driven solutions to secure critical maritime infrastructure. His work bridges technical defense and policy, training AI systems to identify spoofed signals and help operators distinguish technical glitches from strategic cyberattacks.
Evolving Interpretable Constitutions for Multi-Agent Coordination
We introduce a method for evolving constitutions in multi-agent systems to improve interpretability and alignment.