SaTML 2024 - Javier Rando - Find the Trojan: Universal Backdoor Detection in Aligned LLMs Nicolas Papernot 812 подписчиков Скачать
SaTML 2024 - Chris Leckie - Shattering the Illusion of Unexploitable Data using Diffusion Models Скачать
SaTML 2024 - Yiwei Lu - Indiscriminate Data Poisoning Attacks on Pre-trained Feature Extractors Скачать
SaTML 2024 - Quentin Le Roux - Black-Box Defense against DNN Backdoors with Rare Event Simulation Скачать
SaTML 2024 - Sheila McIlraith - Tutorial - (Formal) Languages Help AI agents Learn and Reason Скачать
SaTML 2024 - Ashutosh Kumar Nirala - Fast Certification Using Incremental Randomized Smoothing Скачать
SaTML 2024 - Kamala Varma - Understanding and Mitigating the Causes of Inference Slowdown for LMs Скачать
SaTML 2024 - Lea Schönherr - CodeLMSec: Finding Security Vulnerabilities in Black-Box Code LMs Скачать
SaTML 2024 - Judy Hanwen Shen - SoK: Unifying Corroborative and Contributive Attributions in LLMs Скачать
SaTML 2024 - Yves-Alexandre de Montjoye - Tutorial - Detecting the use of copyright content by LLMs Скачать
SaTML 2024 - Patrick Vossler - Conventional Fairness Metrics With Probabilistic Protected Features Скачать
SaTML 2024 - Andrew Geng - Model Reprogramming Outperforms Fine-tuning on OOD in Text-Image Encoders Скачать
SaTML 2024- Audra McMillan - Differentially Private Heavy Hitter Detection using Federated Analytics Скачать
SaTML 2024 - Amol Khanna - SoK: Differentially Private Linear Models For High Dimensional Data Скачать
SaTML 2024 - Zhangheng Li - Shake to Leak: Amplifying the Generative Privacy Risk through Finetuning Скачать
SaTML 2023 - Xiaojun Xu - EDoG: Adversarial Edge Detection For Graph Neural Networks (virtual) Скачать
SaTML 2023 - Sanghyun Hong - Publishing Efficient On-device Models Increases Adversarial Vuln. Скачать
SaTML 2023 - Katharina Beckh - SoK: Harnessing Prior Knowledge for Explainable Machine Learning Скачать
SaTML 2023 - Washington Garcia - Less is More: Dimension Reduction Finds On-Manifold Adversarial Ex Скачать
SaTML 2023 - J. Zhang - CARE: Certifiably Robust Learning with Reasoning via Variational Inference Скачать
SaTML 2023 - Reza Nasirigerdeh - Kernel Normalized Convolutional Networks for Privacy-Preserving ML Скачать
SaTML 2023 - Julien Ferry - Exploiting Fairness to Enhance Sensitive Attributes Reconstruction Скачать
SaTML 2023 - Lorenzo Cazzaro - Explainable Global Fairness Verification of Tree-Based Classifiers Скачать
SaTML 2023 - Arif - Reprogrammable-FL: Improving Utility-Priv Tradeoff in FL via Model Reprogramming Скачать
SaTML 2023 - Nandakumar - PolyKervNets: Activation-free Neural Networks For Private Interference Скачать
SaTML 2023 - Liu - Towards Transferable Unrestricted Adversarial Examples with Minimum Changes Скачать
SaTML 2023 - Carlini & Jagielski - Improving train data extraction attacks on large language models Скачать
SaTML 2023 - Yingyan Zeng - ModelPred: A Framework for Predicting Trained Model from Training Data Скачать
SaTML 2023 - Kenfack - Learning Fair Representations thr. Uniformly Distributed Sensitive Attributes Скачать
SaTML 2023 - Guy Heller - Can Stochastic Grad Langevin Dynamics Provide Differential Privacy for DL? Скачать
SaTML 2023 - Harsh Chaudhari - SafeNet: The Unreasonable Effectiveness of Ensembles in Private CL Скачать
SaTML 2023 - Kawakami - Validity Perspec on Evaluating Justified Use of Data-driven Decision-making Скачать
SaTML 2023 - Korbinian Koch - Machine Unlearning with SISA Comes at the Expense of Minority Classes Скачать
SaTML 2023 - Stephen Casper - SoK: Toward Transparent AI: Interpreting the Inner Structures of DNNs Скачать
SaTML 2023 - Hartmann - Distribution inference risks: Identifying and mitigating sources of leakage Скачать
SaTML 2023 - Wu and Tagomori - Toward Certified Robustness Against Real-World Distribution Shift Скачать
SecML18: Marta Kwiatkowska on Safety verification for neural networks with provable guarantees Скачать