Robust Multi-bit Text Watermark with LLM-based Paraphrasers.
CoRR, 2024
ACC-Debate: An Actor-Critic Approach to Multi-Agent Debate.
CoRR, 2024
Toward Optimal LLM Alignments Using Two-Player Games.
,
,
,
,
,
,
,
,
,
,
,
,
CoRR, 2024
Label Smoothing Improves Machine Unlearning.
CoRR, 2024
Learning to Watermark LLM-generated Text via Reinforcement Learning.
CoRR, 2024
Improving Reinforcement Learning from Human Feedback Using Contrastive Rewards.
CoRR, 2024
Fair Classifiers Without Fair Training: An Influence-Guided Data Sampling Approach.
CoRR, 2024
Measuring and Reducing LLM Hallucination without Gold-Standard Answers via Expertise-Weighting.
CoRR, 2024
Rethinking Machine Unlearning for Large Language Models.
,
,
,
,
,
,
,
,
,
,
,
,
CoRR, 2024
Human-Instruction-Free LLM Self-Alignment with Limited Samples.
CoRR, 2024
Large Language Model Unlearning.
Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024
Fairness without Harm: An Influence-Guided Active Sampling Approach.
Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024
Fair Classifiers that Abstain without Harm.
Proceedings of the Twelfth International Conference on Learning Representations, 2024
"My face, my rules": Enabling Personalized Protection Against Unacceptable Face Editing.
Proc. Priv. Enhancing Technol., July, 2023
Large Language Model Unlearning.
CoRR, 2023
Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment.
CoRR, 2023
Understanding Unfairness via Training Concept Influence.
CoRR, 2023
Label Inference Attack against Split Learning under Regression Setting.
CoRR, 2023
Weak Proxies are Sufficient and Preferable for Fairness with Missing Sensitive Attributes.
Proceedings of the International Conference on Machine Learning, 2023
DPAUC: Differentially Private AUC Computation in Federated Learning.
Proceedings of the Thirty-Seventh AAAI Conference on Artificial Intelligence, 2023
Learning to Counterfactually Explain Recommendations.
CoRR, 2022
Evaluating Fairness Without Sensitive Attributes: A Framework Using Only Auxiliary Models.
CoRR, 2022
Differentially Private AUC Computation in Vertical Federated Learning.
CoRR, 2022
Differentially Private Label Protection in Split Learning.
CoRR, 2022
Label Leakage and Protection from Forward Embedding in Vertical Federated Learning.
CoRR, 2022
Counterfactually Evaluating Explanations in Recommender Systems.
CoRR, 2022
Differentially private multi-party data release for linear regression.
Proceedings of the Uncertainty in Artificial Intelligence, 2022
Defending against Reconstruction Attack in Vertical Federated Learning.
CoRR, 2021
Vertical Federated Learning without Revealing Intersection Membership.
CoRR, 2021
Backdoor Attacks Against Deep Learning Systems in the Physical World.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2021
Backdoor Attacks on Facial Recognition in the Physical World.
CoRR, 2020
Regula Sub-rosa: Latent Backdoor Attacks on Deep Neural Networks.
CoRR, 2019
Neural Cleanse: Identifying and Mitigating Backdoor Attacks in Neural Networks.
Proceedings of the 2019 IEEE Symposium on Security and Privacy, 2019
Latent Backdoor Attacks on Deep Neural Networks.
Proceedings of the 2019 ACM SIGSAC Conference on Computer and Communications Security, 2019
With Great Training Comes Great Vulnerability: Practical Attacks against Transfer Learning.
Proceedings of the 27th USENIX Security Symposium, 2018
Identifying Value in Crowdsourced Wireless Signal Measurements.
Proceedings of the 26th International Conference on World Wide Web, 2017
Object Recognition and Navigation using a Single Networking Device.
Proceedings of the 15th Annual International Conference on Mobile Systems, 2017
Complexity vs. performance: empirical analysis of machine learning as a service.
Proceedings of the 2017 Internet Measurement Conference, 2017
Automated Crowdturfing Attacks and Defenses in Online Review Systems.
Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security, 2017
A general framework to increase the robustness of model-based change point detection algorithms to outliers and noise.
Proceedings of the 2016 SIAM International Conference on Data Mining, 2016