Showing 1–20 of 20 results
/ Date/ Name
Feb 12, 2026Semantic-aware Adversarial Fine-tuning for CLIPOct 6, 2025DynamiQ: Unlocking the Potential of Dynamic Task Allocation in Parallel FuzzingJun 16, 2025Position: Certified Robustness Does Not (Yet) Imply Model SecurityMar 4, 2025One Stone, Two Birds: Enhancing Adversarial Defense Through the Lens of Distributional DiscrepancyMay 14, 2024RS-Reg: Probabilistic and Robust Certified Regression Through Randomized SmoothingApr 30, 2024TuBA: Cross-Lingual Transferability of Backdoor Attacks in LLMs with Instruction TuningSep 20, 2023It's Simplex! Disaggregating Measures to Improve Certified RobustnessJan 8, 2023Bayesian Graphical Entity Resolution Using Exchangeable Random Partition PriorsMay 20, 2022Getting a-Round Guarantees: Floating-Point Attacks on Certified RobustnessDec 10, 2021Are We There Yet? Timing and Floating-Point Attacks on Differential Privacy SystemsJul 18, 2021As Easy as 1, 2, 3: Behavioural Testing of NMT Systems for Numerical TranslationJun 27, 2020Invertible Concept-based Explanations for CNN Models with Non-negative Concept Activation VectorsSep 13, 2019d-blink: Distributed End-to-End Bayesian Entity ResolutionFeb 22, 2018Options for encoding names for data linking at the Australian Bureau of StatisticsDec 4, 2017Vulnerabilities in the use of similarity tables in combination with pseudonymisation to preserve data privacy in the UK Office for National Statistics' Privacy-Preserving Record LinkageFeb 18, 2017End-to-End Differentially-Private Parameter Tuning in Spatial HistogramsSep 26, 2016Differentially-Private Counting of Users' Spatial RegionsFeb 22, 2011Link Prediction by De-anonymization: How We Won the Kaggle Social Network ChallengeJul 3, 2010Query Strategies for Evading Convex-Inducing ClassifiersMar 14, 2010Near-Optimal Evasion of Convex-Inducing Classifiers