Security & Privacy

Defending Against Backdoor Attacks by Layer-wise Feature Analysis (Extended Abstract) IJCAI 2024 De-Identification of Sensitive Personal Data in Datasets Derived from IIT-CDIP EMNLP 2024 Deidentifying a Norwegian Clinical Corpus - an Effort to Create a Privacy-preserving Norwegian Large Clinical Language Model EACL 2024 Demystifying Verbatim Memorization in Large Language Models EMNLP 2024 DeRDaVa: Deletion-Robust Data Valuation for Machine Learning AAAI 2024 Detecting Personal Identifiable Information in Swedish Learner Essays EACL 2024 Differentially Private Data Release for Mixed-type Data via Latent Factor Models JMLR 2024 Differentially Private Equivalence Testing for Continuous Distributions and Applications NeurIPS 2024 Differentially Private Graph Diffusion with Applications in Personalized PageRanks NeurIPS 2024 Differentially private methods for managing model uncertainty in linear regression JMLR 2024 Differentially Private No-regret Exploration in Adversarial Markov Decision Processes UAI 2024 Differentially Private Optimization with Sparse Gradients NeurIPS 2024 Differentially Private Reinforcement Learning with Self-Play NeurIPS 2024 Differentially Private Reward Estimation with Preference Feedback AISTATS 2024 Differentially Private Set Representations NeurIPS 2024 Differentially Private SGD Without Clipping Bias: An Error-Feedback Approach ICLR 2024 Differentially Private Synthetic Data via Foundation Model APIs 1: Images ICLR 2024 Differentially Private Video Activity Recognition WACV 2024 Differential Privacy in Scalable General Kernel Learning via K-means Nystr\"om Random Features NeurIPS 2024 Dissect Black Box: Interpreting for Rule-Based Explanations in Unsupervised Anomaly Detection NeurIPS 2024 Don’t forget private retrieval: distributed private similarity search for large language models ACL 2024 DOPPLER: Differentially Private Optimizers with Low-pass Filter for Privacy Noise Reduction NeurIPS 2024 Downstream Trade-offs of a Family of Text Watermarks EMNLP 2024 DP-AdamBC: Your DP-Adam Is Actually DP-SGD (Unless You Apply Bias Correction) AAAI 2024 Dual Defense: Enhancing Privacy and Mitigating Poisoning Attacks in Federated Learning NeurIPS 2024