2023 IEEE International Conference on Assured Autonomy (ICAA)最新文献_第3页

Explanation Through Reward Model Reconciliation using POMDP Tree Search 基于POMDP树搜索的奖励模型调和解释

2023 IEEE International Conference on Assured Autonomy (ICAA) Pub Date : 2023-05-01 DOI: 10.1109/ICAA58325.2023.00027

Benjamin D. Kraske, Anshu Saksena, A. Buczak, Zachary Sunberg

引用次数: 0

Leveraging Compositional Methods for Modeling and Verification of an Autonomous Taxi System 利用组合方法建模和验证自动出租车系统

2023 IEEE International Conference on Assured Autonomy (ICAA) Pub Date : 2023-04-26 DOI: 10.1109/ICAA58325.2023.00013

A. Pinto, Anthony Corso, E. Schmerling

引用次数: 0

Causal Repair of Learning-Enabled Cyber-Physical Systems 学习型网络物理系统的因果修复

2023 IEEE International Conference on Assured Autonomy (ICAA) Pub Date : 2023-04-06 DOI: 10.1109/ICAA58325.2023.00009

Pengyuan Lu, I. Ruchkin, Matthew Cleaveland, O. Sokolsky, Insup Lee

{"title":"Causal Repair of Learning-Enabled Cyber-Physical Systems","authors":"Pengyuan Lu, I. Ruchkin, Matthew Cleaveland, O. Sokolsky, Insup Lee","doi":"10.1109/ICAA58325.2023.00009","DOIUrl":"https://doi.org/10.1109/ICAA58325.2023.00009","url":null,"abstract":"Models of actual causality leverage domain knowledge to generate convincing diagnoses of events that caused an outcome. It is promising to apply these models to diagnose and repair run-time property violations in cyber-physical systems (CPS) with learning-enabled components (LEC). However, given the high diversity and complexity of LECs, it is challenging to encode domain knowledge (e.g., the CPS dynamics) in a scalable actual causality model that could generate useful repair suggestions. In this paper, we focus causal diagnosis on the input/output behaviors of LECs. Specifically, we aim to identify which subset of I/O behaviors of the LEC is an actual cause for a property violation. An important by-product is a counterfactual version of the LEC that repairs the run-time property by fixing the identified problematic behaviors. Based on this insights, we design a two-step diagnostic pipeline: (1) construct and Halpern-Pearl causality model that reflects the dependency of property outcome on the component’s I/O behaviors, and (2) perform a search for an actual cause and corresponding repair on the model. We prove that our pipeline has the following guarantee: if an actual cause is found, the system is guaranteed to be repaired; otherwise, we have high probabilistic confidence that the LEC under analysis did not cause the property violation. We demonstrate that our approach successfully repairs learned controllers on a standard OpenAI Gym benchmark.","PeriodicalId":190198,"journal":{"name":"2023 IEEE International Conference on Assured Autonomy (ICAA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129632467","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

Novelty Detection in Network Traffic: Using Survival Analysis for Feature Identification 网络流量中的新颖性检测:利用生存分析进行特征识别

2023 IEEE International Conference on Assured Autonomy (ICAA) Pub Date : 2023-01-16 DOI: 10.1109/ICAA58325.2023.00010

Taylor Bradley, Elie Alhajjar, Nathaniel D. Bastian

引用次数: 1

Detecting Trojaned DNNs Using Counterfactual Attributions 利用反事实归因检测木马dnn

2023 IEEE International Conference on Assured Autonomy (ICAA) Pub Date : 2020-12-03 DOI: 10.1109/ICAA58325.2023.00019

Karan Sikka, Indranil Sur, Susmit Jha, Anirban Roy, Ajay Divakaran

{"title":"Detecting Trojaned DNNs Using Counterfactual Attributions","authors":"Karan Sikka, Indranil Sur, Susmit Jha, Anirban Roy, Ajay Divakaran","doi":"10.1109/ICAA58325.2023.00019","DOIUrl":"https://doi.org/10.1109/ICAA58325.2023.00019","url":null,"abstract":"We target the problem of detecting Trojans or backdoors in DNNs. Such models behave normally with typical inputs but produce targeted mispredictions for inputs poisoned with a Trojan trigger. Our approach is based on a novel intuition that the trigger behavior is dependent on a few ghost neurons that are activated for both input classes and trigger pattern. We use counterfactual explanations, implemented as neuron attributions, to measure significance of each neuron in switching predictions to a counter-class. We then incrementally excite these neurons and observe that the model’s accuracy drops sharply for Trojaned models as compared to benign models. We support this observation through a theoretical result that shows the attributions for a Trojaned model are concentrated in a small number of features. We encode the accuracy patterns by using a deep temporal set encoder for trojan detection that enables invariance to model architecture and a number of classes. We evaluate our approach on four US IARPA/NIST-TrojAI benchmarks with high diversity in model architectures and trigger patterns. We show consistent gains over state-of-the-art adversarial attack based model diagnosis (+5.8%absolute) and trigger reconstruction based methods (+23.5%), which often require strong assumptions on the nature of the attack.","PeriodicalId":190198,"journal":{"name":"2023 IEEE International Conference on Assured Autonomy (ICAA)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127209070","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 8