Adversarial Cooperative Imitation Learning for Dynamic Treatment Regimes

/in /by

Recent developments in discovering dynamic treatment regimes (DTRs) have heightened the importance of deep reinforcement learning (DRL) which are used to recover the doctor’s treatment policies. However, existing DRL-based methods expose the following limitations: 1) supervised methods based on behavior cloning suffer from compounding errors, 2) the self-defined reward signals in reinforcement learning models are either too sparse or need clinical guidance, 3) only positive trajectories (e.g. survived patients) are considered in current imitation learning models, with negative trajectories (e.g. deceased patients) been largely ignored, which are examples of what not to do and could help the learned policy avoid repeating mistakes. To address these limitations, in this paper, we propose the adversarial cooperative imitation learning model, ACIL, to deduce the optimal dynamic treatment regimes that mimics the positive trajectories while differs from the negative trajectories. Specifically, two discriminators are used to help achieve this goal: an adversarial discriminator is designed to minimize the discrepancies between the trajectories generated from the policy and the positive trajectories, and a cooperative discriminator is used to distinguish the negative trajectories from the positive and generated trajectories. The reward signals from the discriminators are utilized to refine the policy for dynamic treatment regimes. Experiments on the publicly real-world medical data demonstrate that ACIL improves the likelihood of patient survival and provides better dynamic treatment regimes with the exploitation of information from both positive and negative trajectories.

Read more

APTrace: A Responsive System for Agile Enterprise Level Causality Analysis

/in /by

While backtracking analysis has been successful in assisting the investigation of complex security attacks, it faces a critical dependency explosion problem. To address this problem, security analysts currently need to tune backtracking analysis manually with different case-specific heuristics. However, existing systems fail to fulfill two important system requirements to achieve effective backtracking analysis. First, there need flexible abstractions to express various types of heuristics. Second, the system needs to be responsive in providing updates so that the progress of backtracking analysis can be frequently inspected, which typically involves multiple rounds of manual tuning. In this paper, we propose a novel system, APTrace, to meet both of the above requirements. As we demonstrate in the evaluation, security analysts can effectively express heuristics to reduce more than 99.5% of irrelevant events in the backtracking analysis of real-world attack cases. To improve the responsiveness of backtracking analysis, we present a novel execution-window partitioning algorithm that significantly reduces the waiting time between two consecutive updates (especially, 57 times reduction for the top 1% waiting time).

Read more

Generating Followup Questions for Interpretable Multi hop Question Answering

/in /by

We propose a framework for answering open domain multi hop questions in which partial information is read and used to generate followup questions, to finally be answered by a pretrained single hop answer extractor. This framework makes each hop interpretable, and makes the retrieval associated with later hops as flexible and specific as for the first hop. As a first instantiation of this framework, we train a pointer generator network to predict followup questions based on the question and partial information. This provides a novel application of a neural question generation network, which is applied to give weak ground truth single hop followup questions based on the final answers and their supporting facts. Learning to generate followup questions that select the relevant answer spans against downstream supporting facts, while avoiding distracting premises, poses an exciting semantic challenge for text generation. We present an evaluation using the two hop bridge questions of HotpotQA

Read more

You Are What You Do: Hunting Stealthy Malware via Data Provenance Analysis

/in /by

To subvert recent advances in perimeter and host security, the attacker community has developed and employed various attack vectors to make malware much more stealthy than before to penetrate the target system and prolong its presence. The advanced malware, or stealthy malware, impersonates or abuses benign applications and legitimate system tools to minimize its footprints in the target system. One example of such stealthy malware is fileless malware, which resides its malicious logic mostly in the memory of well-trusted processes. It is difficult for traditional detection tools, such as malware scanners, to detect it, as the malware normally does not expose its malicious payload in a file and hides its malicious behaviors among the benign behaviors of the processes.In this paper, we present PROVDETECTOR, a provenance-based approach for detecting stealthy malware. The intuition behind PROVDETECTOR is that although a stealthy malware may impersonate or abuse a benign process, it still exposes its malicious behaviors in the OS (operating system) level provenance. Based on this intuition, PROVDETECTOR first employs a novel selection algorithm to identify possibly malicious parts in the OS level provenance data of a process. Then, it applies a neural embedding and machine learning pipeline to automatically detect any behavior that deviates significantly from normal behaviors. We evaluate our approach on a large provenance dataset from an enterprise network and demonstrate that it achieves very high detection performance (an average F1 score of 0.974) of stealthy malware. Further, we conduct thorough interpretability studies to understand the internals of the learned machine learning models.

Read more

Demonstration of photonic neural network for fiber nonlinearity compensation in long-haul transmission systems

/in /by

We demonstrate the experimental implementation of photonic neural network for fiber nonlinearity compensation over a 10,080 km trans-pacific transmission link. Q-factor improvement of 0.51 dB is achieved with only 0.06 dB lower than numerical simulations.

Read more

First Proof That Geographic Location on Deployed Fiber Cable Can Be Determined by Using OTDR Distance Based on Distributed Fiber Optical Sensing Technology

/in /by

We demonstrated for the first time that geographic locations on deployed fiber cables can be determined accurately by using OTDR distances. The method involves vibration stimulation near deployed cables and distributed fiber optical sensing technology.

Read more

More Than Communications: Environment Monitoring Using Existing Data Center Network Infrastructure

/in /by

We propose reusing existing optical cables in metropolitan networks for distributed sensing using a bidirectional, dual-band architecture where communications and sensing signals can coexist with weak interaction on the same optical fiber.

Read more

Simultaneous Optical Fiber Sensing and Mobile Front-Haul Access over a Passive Optical Network

/in /by

We demonstrate a passive optical network (PON) that employs reflective semiconductor optical amplifiers (RSOAs) at optical network units (ONUs) to allow simultaneous data transmission with distributed fiber-optic sensing (DFOS) on individual distribution fibers.

Read more

Active Adversarial Domain Adaptation

/in /by

We propose an active learning approach for transferring representations across domains. Our approach, active adversarial domain adaptation (AADA), explores a duality between two related problems: adversarial domain alignment and importance sampling for adapting models across domains. The former uses a domain discriminative model to align domains, while the latter utilizes the model to weigh samples to account for distribution shifts. Specifically, our importance weight promotes unlabeled samples with large uncertainty in classification and diversity compared to la-beled examples, thus serving as a sample selection scheme for active learning. We show that these two views can be unified in one framework for domain adaptation and transfer learning when the source domain has many labeled examples while the target domain does not. AADA provides significant improvements over fine-tuning based approaches and other sampling methods when the two domains are closely related. Results on challenging domain adaptation tasks such as object detection demonstrate that the advantage over baseline approaches is retained even after hundreds of examples being actively annotated.

Read more

Coordinated Joint Multimodal Embeddings for Generalized Audio-Visual Zero-shot Classification and Retrieval of Videos

/in /by

We present an audio-visual multimodal approach for the task of zero-shot learning (ZSL) for classification and retrieval of videos. ZSL has been studied extensively in the recent past but has primarily been limited to visual modality and to images. We demonstrate that both audio and visual modalities are important for ZSL for videos. Since a dataset to study the task is currently not available, we also construct an appropriate multimodal dataset with 33 classes containing 156, 416 videos, from an existing large scale audio event dataset. We empirically show that the performance improves by adding audio modality for both tasks of zero-shot classification and retrieval, when using multi-modal extensions of embedding learning methods. We also propose a novel method to predict the `dominant’ modality using a jointly learned modality attention network. We learn the attention in a semi-supervised setting and thus do not require any additional explicit labelling for the modalities. We provide qualitative validation of the modality specific attention, which also successfully generalizes to unseen test classes.

Read more