Gaurav Dixit

Raghav Thakar, Gaurav Dixit, Kagan Tumer

Agents in the real world must often balance multiple objectives, such as speed, stability, and energy efficiency in continuous control. To account for changing conditions and preferences, an agent must ideally learn a Pareto frontier of policies representing multiple optimal trade-offs. Recent advances in multi-policy multi-objective reinforcement learning (MORL) enable learning a Pareto front directly, but require full multi-objective consideration from the start of training. In practice, multi-objective preferences often arise after a policy has already been trained on a single specialised objective. Existing MORL methods cannot leverage these pre-trained `specialists' to learn Pareto fronts and avoid incurring the sample costs of retraining. We introduce Mixed Advantage Pareto Extraction (MAPEX), an offline MORL method that constructs a frontier of policies by reusing pre-trained specialist policies, critics, and replay buffers. MAPEX combines evaluations from specialist critics into a mixed advantage signal, and weights a behaviour cloning loss with it to train new policies that balance multiple objectives. MAPEX's post hoc Pareto front extraction preserves the simplicity of single-objective off-policy RL, and avoids retrofitting these algorithms into complex MORL frameworks. We formally describe the MAPEX procedure and evaluate MAPEX on five multi-objective MuJoCo environments. Given the same starting policies, MAPEX produces comparable fronts at $0.001\%$ the sample cost of established baselines.

Matthew L. Olson, Thuy-Vy Nguyen, Gaurav Dixit et al.

Identifying covariate shift is crucial for making machine learning systems robust in the real world and for detecting training data biases that are not reflected in test data. However, detecting covariate shift is challenging, especially when the data consists of high-dimensional images, and when multiple types of localized covariate shift affect different subspaces of the data. Although automated techniques can be used to detect the existence of covariate shift, our goal is to help human users characterize the extent of covariate shift in large image datasets with interfaces that seamlessly integrate information obtained from the detection algorithms. In this paper, we design and evaluate a new visual interface that facilitates the comparison of the local distributions of training and test data. We conduct a quantitative user study on multi-attribute facial data to compare two different learned low-dimensional latent representations (pretrained ImageNet CNN vs. density ratio) and two user analytic workflows (nearest-neighbor vs. cluster-to-cluster). Our results indicate that the latent representation of our density ratio model, combined with a nearest-neighbor comparison, is the most effective at helping humans identify covariate shift.

Mengmeng Ge, Jin-Hee Cho, Dong Seong Kim et al.

Resource constrained Internet-of-Things (IoT) devices are highly likely to be compromised by attackers because strong security protections may not be suitable to be deployed. This requires an alternative approach to protect vulnerable components in IoT networks. In this paper, we propose an integrated defense technique to achieve intrusion prevention by leveraging cyberdeception (i.e., a decoy system) and moving target defense (i.e., network topology shuffling). We verify the effectiveness and efficiency of our proposed technique analytically based on a graphical security model in a software defined networking (SDN)-based IoT network. We develop four strategies (i.e., fixed/random and adaptive/hybrid) to address "when" to perform network topology shuffling and three strategies (i.e., genetic algorithm/decoy attack path-based optimization/random) to address "how" to perform network topology shuffling on a decoy-populated IoT network, and analyze which strategy can best achieve a system goal such as prolonging the system lifetime, maximizing deception effectiveness, maximizing service availability, or minimizing defense cost. Our results demonstrate that a software defined IoT network running our intrusion prevention technique at the optimal parameter setting prolongs system lifetime, increases attack complexity of compromising critical nodes, and maintains superior service availability compared with a counterpart IoT network without running our intrusion prevention technique. Further, when given a single goal or a multi-objective goal (e.g., maximizing the system lifetime and service availability while minimizing the defense cost) as input, the best combination of "how" and "how" strategies is identified for executing our proposed technique under which the specified goal can be best achieved.