Resultats de la cerca - Evans, David

One Neuron to Fool Them All per Suri, Anshuman, Evans, David

Obtenir text complet
Obtenir text complet

Formalizing Distribution Inference Risks per Suri, Anshuman, Evans, David

Obtenir text complet
Obtenir text complet

Understanding Intrinsic Robustness Using Label Uncertainty per Zhang, Xiao, Evans, David

Obtenir text complet
Obtenir text complet

Formalizing and Estimating Distribution Inference Risks per Suri, Anshuman, Evans, David

Obtenir text complet
Obtenir text complet

Are Attribute Inference Attacks Just Imputation? per Jayaraman, Bargav, Evans, David

Obtenir text complet
Obtenir text complet

Evaluating Google's Protected Audience Protocol per Long, Minjun, Evans, David

Obtenir text complet
Obtenir text complet

Steering the CensorShip: Uncovering Representation Vectors for LLM "Thought" Control per Cyberey, Hannah, Evans, David

Obtenir text complet
Obtenir text complet

Evolution of Log-Based Detection Rules in Public Repositories per Long, Minjun, Evans, David

Obtenir text complet
Obtenir text complet

NoisyCoconut: Counterfactual Consensus via Latent Space Reasoning per Jerge, Michael, Evans, David

Obtenir text complet
Obtenir text complet

Certifying Joint Adversarial Robustness for Model Ensembles per Jonas, Mainuddin Ahmad, Evans, David

Obtenir text complet
Obtenir text complet

Learning Adversarially Robust Representations via Worst-Case Mutual Information Maximization per Zhu, Sicheng, Zhang, Xiao, Evans, David

Obtenir text complet
Obtenir text complet

Pointwise Paraphrase Appraisal is Potentially Problematic per Chen, Hannah, Ji, Yangfeng, Evans, David

Obtenir text complet
Obtenir text complet

Finding Friends and Flipping Frenemies: Automatic Paraphrase Dataset Augmentation Using Graph Theory per Chen, Hannah, Ji, Yangfeng, Evans, David

Obtenir text complet
Obtenir text complet

Improved Estimation of Concentration Under $\ell_p$-Norm Distance Metrics Using Half Spaces per Prescott, Jack, Zhang, Xiao, Evans, David

Obtenir text complet
Obtenir text complet

Balanced Adversarial Training: Balancing Tradeoffs between Fickleness and Obstinacy in NLP Models per Chen, Hannah, Ji, Yangfeng, Evans, David

Obtenir text complet
Obtenir text complet

Understanding Variation in Subpopulation Susceptibility to Poisoning Attacks per Rose, Evan, Suya, Fnu, Evans, David

Obtenir text complet
Obtenir text complet

Addressing Both Statistical and Causal Gender Fairness in NLP Models per Chen, Hannah, Ji, Yangfeng, Evans, David

Obtenir text complet
Obtenir text complet

DP-RuL: Differentially-Private Rule Learning for Clinical Decision Support Systems per Lamp, Josephine, Feng, Lu, Evans, David

Obtenir text complet
Obtenir text complet

Do Parameters Reveal More than Loss for Membership Inference? per Suri, Anshuman, Zhang, Xiao, Evans, David

Obtenir text complet
Obtenir text complet

Do Prevalent Bias Metrics Capture Allocational Harms from LLMs? per Cyberey, Hannah, Ji, Yangfeng, Evans, David

Obtenir text complet
Obtenir text complet