Titlebook: Decision and Game Theory for Security; 9th International Co Linda Bushnell,Radha Poovendran,Tamer Başar Conference proceedings 2018 Springe

连词

Training Set Camouflage,llicit machine learning classification task. Alice wants Bob (a machine learning system) to learn the task. However, sending either the training set or the trained model to Bob can raise suspicion if the communication is monitored. Training set camouflage allows Alice to compute a second training se

folliculitis

Multi-stage Dynamic Information Flow Tracking Game,ersary gathers more privileges, resources, and information about the system and uses this information to gain access to the targeted data of the next stage to reach the final goal. APTs are not only persistent but also stealthy and hence difficult to detect. The persistent nature of APTs, however, c

拘留

Less is More: Culling the Training Set to Improve Robustness of Deep Neural Networks, architecture or augmenting the training set with adversarial examples, but both have inherent limitations. Motivated by recent research that shows outliers in the training set have a high negative influence on the trained model, we studied the relationship between model robustness and the quality o

间接

syncope

Perfectly Secure Message Transmission Against Rational Timid Adversaries,r using multiple channels. It is assumed that an adversary corrupts a subset of the channels, and makes eavesdropping and tampering over the corrupted channels. In this work, we consider a game-theoretic security model for SMT. Specifically, we introduce a rational adversary who has the preference f

Meander

Coma704

全国性

Data Poisoning Attacks in Contextual Bandits,endation and adaptive medical treatment, among others. We provide a general attack framework based on convex optimization and show that by slightly manipulating rewards in the data, an attacker can force the bandit algorithm to pull a target arm for a target contextual vector. The target arm and tar

袭击

Analysis and Computation of Adaptive Defense Strategies Against Advanced Persistent Threats for Cybthe attack. The multi-stage Bayesian game captures the incomplete information of the players’ type, and enables an adaptive belief update according to the observable history of the other player’s actions. The solution concept of perfect Bayesian Nash equilibrium (PBNE) under the proactive and reacti

grounded