Beyond the Safety Bundle: Auditing the Helpful and Harmless Dataset.
Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies, 2025
Beyond the Safety Bundle: Auditing the Helpful and Harmless Dataset.
CoRR, 2024
Combining Domain and Alignment Vectors to Achieve Better Knowledge-Safety Trade-offs in LLMs.
CoRR, 2024
Trust No Bot: Discovering Personal Disclosures in Human-LLM Conversations in the Wild.
CoRR, 2024
Towards More Realistic Extraction Attacks: An Adversarial Perspective.
CoRR, 2024
Efficient Causal Graph Discovery Using Large Language Models.
CoRR, 2024
Opinion Diffusion on Society Graphs Based on Approval Ballots.
Proceedings of the 23rd International Conference on Autonomous Agents and Multiagent Systems, 2024
Controlling Delegations in Liquid Democracy.
Proceedings of the 23rd International Conference on Autonomous Agents and Multiagent Systems, 2024
Finding Perfect Matching Cuts Faster.
Proceedings of the Combinatorial Algorithms - 34th International Workshop, 2023
Scotch: An Efficient Secure Computation Framework for Secure Aggregation.
CoRR, 2022
Flatee: Federated Learning Across Trusted Execution Environments.
CoRR, 2021
Poster: FLATEE: Federated Learning Across Trusted Execution Environments.
Proceedings of the IEEE European Symposium on Security and Privacy, 2021