paper-with-me

Papers

Provably Robust Detection of Out-of-distribution Data (almost) for free

2021-06-08 · Alexander Meinke, Julian Bitterwolf, Matthias Hein

The application of machine learning in safety-critical systems requires a reliable assessment of uncertainty. However, deep neural networks are known to produce highly overconfident predictions on out-of-distribution (OOD) data. Even if trained to be non-confident on OOD data, one can still adversarially manipulate OOD data so that the classifier again assigns high confidence to the manipulated samples. We show that two previously published defenses can be broken by better adapted attacks, highlighting the importance of robustness guarantees around OOD data. Since the existing method for this task is hard to train and significantly limits accuracy, we construct a classifier that can simultaneously achieve provably adversarially robust OOD detection and high clean accuracy. Moreover, by slightly modifying the classifier's architecture our method provably avoids the asymptotic overconfidence problem of standard neural networks. We provide code for all our experiments.

📄 PDF Abstract BibTeX arXiv:2106.04260

Code (1)

AlexMeinke/Provable-OOD-Detection 공식 구현 pytorch

Tasks

Out of Distribution (OOD) Detection

Methods 이 논문이 사용한 방법론

AWARE We propose to theoretically and empirically examine the effect of incorporating weighting schemes into walk-aggregating GNNs. To this end, we propose a simple, interpretable, and…

Similar Papers 제목 키워드 기반

LLM Jailbreak Detection for (Almost) Free!

2025-09-18 · Guorui Chen, Yifan Xia, Xiaojun Jia, Zhijiang Li 외 arxiv

Large language models (LLMs) enhance security through alignment when widely used, but remain susceptible to jailbreak attacks capable of producing inappropriate content. Jailbreak detection methods show promise in mitiga…

(Almost) Free Incentivized Exploration from Decentralized Learning Agents

2021-10-27 · NeurIPS 2021 12 · Chengshuai Shi, Haifeng Xu, Wei Xiong, Cong Shen

Incentivized exploration in multi-armed bandits (MAB) has witnessed increasing interests and many progresses in recent years, where a principal offers bonuses to agents to do explorations on her behalf. However, almost a…

Multi-Armed Bandits

A Dimension-Insensitive Algorithm for Stochastic Zeroth-Order Optimization

2021-04-22 · Hongcheng Liu, Yu Yang

This paper concerns a convex, stochastic zeroth-order optimization (S-ZOO) problem. The objective is to minimize the expectation of a cost function whose gradient is not directly accessible. For this problem, traditional…

Provably Powerful Graph Neural Networks for Directed Multigraphs

2023-06-20 · Béni Egressy, Luc von Niederhäusern, Jovan Blanusa, Erik Altman 외

This paper analyses a set of simple adaptations that transform standard message-passing Graph Neural Networks (GNN) into provably powerful directed multigraph neural networks. The adaptations include multigraph port numb…

One Policy is Enough: Parallel Exploration with a Single Policy is Near-Optimal for Reward-Free Reinforcement Learning

2022-05-31 · Pedro Cisneros-Velarde, Boxiang Lyu, Sanmi Koyejo, Mladen Kolar

Although parallelism has been extensively used in reinforcement learning (RL), the quantitative effects of parallel exploration are not well understood theoretically. We study the benefits of simple parallel exploration …

Reinforcement Learning (RL)