News
This year's accepted papers, SAIL seminars and other lab news. RSS feed.
2026
- Oct 2026Pawan Kumar gave the SAIL seminar “Red teaming frontier AI at the UK AI Security Institute”
- Jun 2026Mykel Kochenderfer gave the SAIL seminar “Decision making for safety critical systems”
- 2026“Verifying the Verifier: What a Guardrail Certificate Pays For” was accepted at a NeurIPS 2026 workshop
- 2026“Intent-Preserving Adversarial User Simulation for Multi-Turn Agent Evaluation” was accepted at a NeurIPS 2026 workshop
- 2026“End-to-End Verification of Neuro-symbolic Automata via Contrastive Logit-Gaps” was accepted at NeurIPS 2026
- 2026“Eliciting Intrinsic Hallucinations in LLMs via Semantically Equivalent Adversarial Attacks” was accepted at COLM 2026
- 2026“IoUCert: Robustness Verification for Anchor-Based Object Detectors” was accepted at ECCV 2026
- 2026“Hybrid Robustness Verification for Spatio-Temporal Neural Networks” was accepted at SAIV 2026
- 2026“A Robust Out-of-Distribution Detection Framework via Synergistic Smoothing” was accepted at CVPR Findings 2026
- 2026“Lipschitz Optimization for Formal Verification of Homographies” was accepted at CVPR 2026
- 2026“Out-of-Distribution Detection using Counterfactual Distance” was accepted at an IJCAI 2026 workshop
- 2026“Scalable and Safe Multi-Agent Coordination with Reconstructed Level-k Monte Carlo Tree Search” was accepted at AAMAS 2026
- 2026“Certified Background-Invariant Training via Latent Generative Models” was accepted at an AAAI 2026 workshop
- 2026“Certified Training for Convolutional Perturbations” was accepted at an AAAI 2026 workshop