| 1. | Beyond Trust: Proving Fairness and Privacy in Machine Learning | 1 | |
|
| 2. | Data Mixture Inference: What do BPE Tokenizers Reveal about their Training Data? | 1 | |
|
| 3. | How Much Do Language Models Memorize? | 5 | |
|
| 4. | Differentially Private Prototypes for Imbalanced Transfer Learning | 5 | |
|
| 5. | Understanding LLMs Like Physicists: Observation, Hypothesis, Experimentation, and Prediction | 26 | |
|
| 6. | Stable Estimators for Fast Private Statistics | 1 | |
|
| 7. | The Limits and Possibilities of One Run Auditing | 1 | |
|
| 8. | Going Back and Beyond: Emerging (Old) Threats in LLM Privacy and Poisoning | 6 | |
|
| 9. | Differentially Private Synthetic Data without Training | 1 | |
|
| 10. | Go Meetup April 2025 - Git Bisect and Go Size Analyzer | 10 | |
|
| 11. | Privacy Auditing of Large Language Models | 2 | |
|
| 12. | Is Learning Effective in Dynamic Strategic Interactions? Evidence from Stackelberg Games | 9 | |
|
| 13. | LLM Dataset Inference: Did you train on my dataset? | 26 | |
|
| 14. | Worst-Case Membership Inference of Language Models | 1 | |
|
| 15. | The Surprising Effectiveness of Membership Inference with Simple N-Gram Coverage | 1 | |
|
| 16. | POPri: Private Federated Learning using Preference-Optimized Synthetic Data | 4 | |
|
| 17. | Leveraging Per-Instance Privacy for Machine Unlearning | 1 | |
|
| 18. | Hash Functions: Bridging the Gap from Theory to Practice | 32 | |
|
| 19. | Online Learning and Economics | 6 | |
|
| 20. | Go Meetup April 2025 - i18n Go Experiment | 17 | |
|
| 21. | Cascading Adversarial Bias from Injection to Distillation in Language Models | 3 | |
|
| 22. | Supply Chain Security with Go | 31 | |
|
| 23. | Differentially Private Multiway and k-Cut | 3 | |
|
| 24. | Chasing the Constants and its Implications in Differential Privacy | 1 | |
|
| 25. | Privacy Ripple Effects from Adding or Removing Personal Information in Language Model Training | 2 | |
|
| 26. | How I Wrote 10K Lines of Go in a Weekend | 53 | |
|
| 27. | Go Meetup April 2025 - Photobooth | 14 | |
|
| 28. | Go Meetup April 2025 - Go Protobuf | 21 | |
|
| 29. | Algorithmic Contract Design | 8 | |
|
| 30. | AI Snake Oil | 43 | |
|
| 31. | Optimistic Verifiable Training by Controlling Hardware Nondeterminism | 3 | |
|
| 32. | Private Adaptations of Large Language Models | 3 | |
|
| 33. | Code Health Guardian | 38 | |
|
| 34. | Streaming Attention Approximation via Discrepancy Theory | 12 | |
|
| 35. | Continual Release Moment Estimation with Differential Privacy | 2 | |
|
| 36. | Threat Models for Memorization: Privacy, Copyright, and Everything In-Between | 3 | |
|
| 37. | Disparate Privacy Risks from Medical AI - An Investigation into Patient-level Privacy Risk | 0 | |
|
| 38. | Proactive Agents for Multi-Turn Text-to-Image Generation Under Uncertainty | 32 | |
|
| 39. | Cascading Adversarial Bias from Injection to Distillation in Language Models | 1 | |
|
| 40. | Persistent Pre-Training Poisoning of LLMs | 3 | |
|
| 41. | A Multi Dimensional Online Contention Resolution Scheme | 11 | |
|
| 42. | Evaluating Data Misuse in LLMs: Introducing Adversarial Compression Rate as a Metric of Memorization | 2 | |
|
| 43. | Watermarking in Generative AI: Opportunities and Threats | 4 | |
|
| 44. | Streaming Private Continual Counting via Binning | 2 | |
|
| 45. | Go Meetup April 2025 - Whats New in Go 1.24? | 18 | |
|
| 46. | Theoretical Limitations of Multi layer Transformers | 25 | |
|
| 47. | Coaching Series: Leading from Strength: Making a Difference | 0 | |
|
| 48. | Workshop on Federated Learning & Analytics: Pre-recorded Talks Day 1 Track 2 Q&A Privacy/Security | 0 | |
|
| 49. | Coaching Series: Create the Career You Want: A Non-Hyped App | 0 | |
|
| 50. | CoinPress: Practical Private Mean and Covariance Estimation | 0 | |
|
| 51. | Grey-box Bayesian Optimization by Peter Frazier | 0 | |
|
| 52. | Coaching Series: Impactful Communication | 0 | Guide |
|
| 53. | FedVault: Efficient Gradient Outlier Detection for Byzantine-Resilient and Privacy-Preserving FedML | 0 | |
|
| 54. | NIPS 2011 Sparse Representation & Low-rank Approximation Workshop: Recovery of a Sparse... | 0 | |
|
| 55. | Distributed continuous quality assurance | 0 | |
|
| 56. | HCIR 2011: Human Computer Information Retrieval Introduction Session "Poster Boasters" | 0 | Guide |
|
| 57. | Workshop on Federated Learning and Analytics: Pre-recorded Talks Day 2 Track 2 Q&A Privacy/Security | 0 | |
|
| 58. | 2022 Blockly Developers Summit: Serialization | 0 | |
|
| 59. | Learning to Explore in Molecule Space by Yoshua Bengio | 0 | |
|
| 60. | GeoDec: Enabling Geospatial Decision Making | 0 | |
|
| 61. | Our Lives, Our Facebooks | 0 | |
|
| 62. | PostRank: Intelligence from the Social Web | 0 | |
|
| 63. | Distributed Testing with SmartFrog | 0 | |
|
| 64. | Testing Metro Wifi | 0 | |
|
| 65. | Resource Allocation in Multi-armed Bandits by Kirthevasan Kandasamy | 0 | |
|
| 66. | Task Specific Local Region Matching | 0 | |
|
| 67. | Combining Discriminative Features to Infer Complex... | 0 | |
|
| 68. | CaPC Learning: Confidential and Private Collaborative Learning | 0 | |
|
| 69. | NIPS 2011 Sparse Representation & Low-rank Approximation Workshop: Online Spectral... | 0 | |
|
| 70. | 2023 Blockly Developer Summit Day 2-7: How to Convince Teachers to Teach Coding | 0 | |
|
| 71. | Marginal-based Methods for Differentially Private Synthetic Data | 0 | |
|
| 72. | Academic Keynote: Differentially Private Covariance-Adaptive Mean Estimation, Adam Smith (BU) | 0 | |
|
| 73. | Experimenting w/ Local & Central Differential Privacy for Both Robustness & Privacy in Fed.Learning | 0 | |
|
| 74. | There are People in our Computers! | 0 | |
|
| 75. | GTAC 2008: Atom Publishing Protocol - Teseting Your Server Implementation | 0 | |
|
| 76. | Tactile Maps Automated Production (TMAP) | 0 | |
|
| 77. | The Gugubarra Project: Building and Evaluating User... | 0 | |
|
| 78. | Greybeard Qualification (Linux Internals) part 2 Execution, Scheduling, Processes & Threads | 0 | |
|
| 79. | Tight Accounting in the Shuffle Model of Differential Privacy | 0 | |
|
| 80. | Fast and Memory Efficient Differentially Private-SGD via JL Projections | 0 | |
|
| 81. | Beyond Gigs of Log Data | 0 | Vlog |
|
| 82. | Virtual LA: The Next Generation | 0 | |
|
| 83. | DocEng 2011: Dynamic Assistance to Adding Dimensions to Multi-structured Documents | 0 | |
|
| 84. | Are There Search Engine Disruptive Ideas? | 0 | |
|
| 85. | AutoTest: Push-button testing using contracts | 0 | |
|
| 86. | Bay Piggies Three Generations of User Interface | 0 | |
|
| 87. | Cyber Center | 0 | |
|
| 88. | A perceptual space that can explain the robustness of... | 0 | |
|
| 89. | Secure Federated Learning on Wimpy Devices | 0 | |
|
| 90. | Academic Keynote: Mean Estimation with User-level Privacy under Data Heterogeneity, Rachel Cummings | 0 | |
|
| 91. | Google Workshop on Federated Learning and Analytics: Breakout Session Closing Summaries | 0 | |
|
| 92. | 2023 Blockly Developer Summit Day 2-8: Active STEM with Unruly Splats | 0 | |
|
| 93. | Mistify: Automating DNN Model Porting for On-Device Inference at the Edge | 0 | |
|
| 94. | Greybeard Qualification (Linux Internals) part 5: Block Devices & File Systems | 0 | |
|
| 95. | Leveraging Public Data for Practical Synthetic Data Generation | 0 | |
|
| 96. | A Geometric View on Private Gradient-Based Optimization | 0 | |
|
| 97. | Locally Differentially Private Bayesian Inference | 0 | |
|
| 98. | Classifiers That Improve With Use | 0 | |
|
| 99. | BB84: Quantum Protected Cryptography | 0 | |
|
| 100. | Web Applications and the Ubiquitous Web | 0 | |
|