United States

Traditional software safety techniques rely on verifying software against a deductively defined specification of how the software should behave. In the case of AI systems, however, specifications are often implicit (e.g., in the case of expert systems, linear and higher-order programs, and rules engines, where behavior is induced by describing facts, deduction rules, or objective functions and allowing an inference engine or solver to recombine them according to pre-set combination schemas) or inductively defined (e.g., in machine learning systems, the specification is derived from the data set and perhaps some parameters of the model). Data-driven methods are subject to systematic bias and are epistemically limited: practical datasets cannot describe all possible events in any open-world problem. Traditional software verification and validation approaches may not apply directly to these novel systems, complicating the operation of systems safety analysis (e.g., MIL-STD 882E). However, AI offers advanced capabilities, and these capabilities must be safe to employ. When AI is deployed in a weapon, robot, or planning system, unwanted events may occur. Several techniques can be used to support the evaluation process for understanding and making risk decisions for military employment. This research considers those techniques – including software analysis, simulation environments, and mathematical determinations – and evaluates which are most employable, useful, and correct.

NAML 2022

Understanding and Assessing Safety in Artificial Intelligence Systems

assurance

safety

evaluation

Naval Information Warfare Center Pacific is partnering with AFCEA San Diego chapter to host the workshop.

The NAML workshop is an opportunity for researchers from Navy research and development centers and our partner organizations to exchange technical ideas and to come together as a team.

The goals of NAML are:

* To spread awareness of current machine learning research relevant to Naval applications

* To connect machine learning researchers with experts in military requirements

* To build and strengthen collaborations within the defense research community

**Watch this video to hear about the AFCEA purpose.**

<iframe width=1280 height=706 frameborder="0" scrolling="no" src="https://screencast-o-matic.com/player/creleVVcvRh?v=6&ff=1&title=0&controls=1" allowfullscreen="true"></iframe>

NAML 2021

technical paper

##### For full functionality of Underline, please SHUT OFF your VPN, or use a personal device.


Naval Information Warfare Center Pacific is partnering with AFCEA San Diego chapter to host the workshop.

The NAML workshop is an opportunity for researchers from Navy research and development centers and our partner organizations to exchange technical ideas and to come together as a team.

The goals of NAML are:

To spread awareness of current machine learning research relevant to Naval applications

To connect machine learning researchers with experts in military requirements

To build and strengthen collaborations within the defense research community


<figure class="video_container">
  <iframe src="https://s3.amazonaws.com/pf-user-files-01/u-59356/uploads/2022-03-22/hk13mxo/NAML_ReceptionWithtitle.mp4" width=826  height=526  frameborder="0" allowfullscreen="true"> </iframe>
</figure>

Naval Information Warfare Center Pacific is partnering with AFCEA San Diego chapter to host the workshop. The NAML workshop is an opportunity for researchers from Navy research and development centers and our partner organizations to exchange technical ideas and to come together as a team.

The goals of NAML are:

To spread awareness of current machine learning research relevant to Naval applications

To connect machine learning researchers with experts in military requirements

To build and strengthen collaborations within the defense research community



The Navy and DoD are prioritizing the rapid adoption of AI across domains in warfare to keep the technological advantage in the United States’ favor. Machine learning, the basis of much of the recent advancement in AI, suffers from a persistent and inadequately addressed critical flaw: adversarial examples. Since the initial discovery of adversarial examples in DNN classifiers in 2013, many new forms of these attacks have been invented and many narrow and particular defenses have been proposed. None of the defenses has survived counter testing. Some researchers have suggested that such susceptibility may be an unavoidable characteristic of problem formations in the space. At this time, no one effective, computationally acceptable, general approach has been discovered
which can shore up DNNs against this and related generalization problems. It is our contention that ML model robustness and resistance to the broad class of all ML adversarial examples can be improved with approaches that seek to train models to declare the data-point-sparse latent-space between data-dense regions of a model’s classification space as a barrier class. Identifying a general approach to training neural networks such that adversarial examples are either eliminated or computationally prohibitive representsa "holy grail" in the machine learning community. While we do not claim to have discovered this holy grail, we are collecting growing evidence that our intuitions hold valuable insights into the problem space which we believe will eventually bear significant fruit in the form of a viable general defense against all evasion adversarial attacks.

VALIDnet: A General Defense against Adversarial Examples in Neural Networks

Deep learning models are pervasive for a multitude of tasks, but the complexity of these models can limit interpretation and inhibit trust in their estimates of confidence. For the classification task, we investigate the induced geometric relationships between the class conditioned data distributions with the deep learning models’ output weight vectors. We propose a simple statistic to characterize the ’confidence’ of the model given a new input, which we call Angular Margin. We compare and contrast the statistic to respective Softmax outputs. We demonstrate that angular margin provides a simple yet superior statistic for detecting minimum-perturbation adversarial attacks and/or misclassified images than standard softmax predictions.

On Dogs and Cats and Adversarial Attacks

Advances in computational technologies and Artificial Intelligence (AI) methods present new opportunities for developing automated tactical decision aids to support warfighters making weapons engagement decisions. Tactical decisions become increasingly complex and can overwhelm human decision-making as threats increase in number, speed, diversity, and lethality. The deployment of such AI-enabled decision aids must consider system safety. This study explored the potential safety risks and failure modes that may arise as automation and AI technologies are introduced and implemented to support human-machine weapons engagement decisions. The Naval Postgraduate School is studying safety risks and failure modes, root causes, and mitigation and engineering strategies to prevent, address, and recover from this new class of possible safety failures.

The study includes five research initiatives: (1) a holistic study of safety risks, root causes, and mitigation strategies related to the introduction of AI into warfare decision aids, (2) analysis of the decision risk involved in human-machine teaming for making weapon engagement decisions, (3) analysis of human-machine trust for AI-enabled weapon engagement decisions, (4) an evaluation of the safety risks in implementing AI as a decision aid for air and missile defense decisions, and (5) a study of military data gathering and management activities and how they relate to AI safety. This technical talk will discuss the five research initiatives and report on their findings to date.


Safety in Artificial Intelligence-Enabled Warfare Decision Aids

Artificial Intelligence (AI) Safety is currently an area within the field of computer science with a strong emphasis on developing safe algorithms for autonomous vehicles such as self-driving cars and unmanned aircraft. As AI is integrated into more and more systems, the hazard analysis process has to be expanded to account for potential mishaps involving these new technologies. A better understanding of the capabilities of AI is needed to create safe systems. This work will give an overview and discuss some of the current development in AI Safety across the Department of Defense.

Designing Safety into AI Enabled Systems

One of the major issues surrounding the adoption of machine learning in applications where accuracy is critical is the lack of trust in such systems due to being persistently perceived as black boxes. In this presentation, we discuss the importance of independently measuring the competency of a machine learning system and how that builds user trust. We define competency as the expected performance of a ML system for a given set of environmental conditions. We describe how to measure competency based on environmental conditions, what those conditions are and how they can be defined. We give examples of user-friendly competency statements and define competency metrics. Given that maritime environmental conditions can change rapidly, we also discuss ways to decide how often to update the user on changes in competency. We then introduce BAE System's MindfuL™ software which produces competency statements. We show results for our defined competency metrics, namely that for a given set of environmental conditions considered in a competency statement, the actual performance of the system will fall within the competency statement’s confidence interval over 99% of the time. 

The second part of the presentation will focus on the reliability of a machine learning system in the context of competency and expands on how this helps build user trust. In other words, we consider the system’s ability to behave as expected as based on the stated competency out in the real world. If there is an expected performance and set of resulting actions taken by the system for a given set of conditions, reliability is the likelihood of achieving that expected performance and resulting actions. Finally we conclude with thoughts on additional ways to build user trust via MindfuL™ software.


Measuring the competency and reliability of ML Systems

Automated spectrum spectrum management requires real-time feedback from sensors in the sensors in the networknetwork. This real-time feedback requires a large backhaul as the network scales. We employ machine learning classifiers at the edge to reduce the backhaul reduce the bandwidth requirements of the network.

Machine Learning and Radio Frequency Spectrum Management

Baselining Few-Shot Object Detection on Maritime Data

The explosion of the number of connected devices in the last 10 years has led to a considerable increase in the nature and scope of Artificial Intelligence at the Edge (EdgeAI). Furthermore, hardware, software, and mission use cases have come together to drive several advances in AI supporting Department of Defense applications. During this talk we will describe how Deloitte views EdgeAI as a domain, deployment considerations for EdgeAI technology, and how EdgeAI can impact the challenges faced by the Navy. 

Edge technologies are characterized by a combination of sensor and computation that are networked to achieve an effect. Adding Machine Learning as a software component can give these systems the ability to deliver insights in millisecond time scales. The combination of Edge technologies and deployed Machine Learning models forms an EdgeAI system. 

The Department of Defense has made considerable investment in Artificial Intelligence, and the Department of the Navy has contributed to that effort significantly. Myriad use cases in the core mission domain of the US Navy exist for EdgeAI systems. For example, computer vision models deployed to wearable technologies can provide immediate “walk-through” assistance to Sailors afloat as they work on shipboard weapons systems and power plants. Unmanned systems can similarly be equipped to find and highlight potential issues during maintenance inspections using an entire sensor array. 

Several considerations become important when conducting AI/ML development for Edge applications. Our team uses the latest compute stack for training and deploying models to Edge environments, and we will highlight some of those considerations during this talk. Finally, we will show work that our team has done to address use cases of interest to the Navy mission, demonstrating the art of the possible in the EdgeAI space.

Deployment considerations for EdgeAI Technology

Preprocessing EEG data for downstream classification tasks

Cooperative autonomous systems, such as swarms, multi-camera systems, or fleets of self-driving vehicles, can illuminate a given scene by providing multiple modalities and varying viewpoints. This redundancy and superposition of data adds robustness to a system typically burdened with obstructions and unrecognizable, distant objects. Collaborative perception is a key component of cooperative autonomous systems where modalities can include camera sensors, LiDAR, RADAR, and depth images. Meanwhile, the amount of useful information that can be shared between agents in a cooperative system is constrained by current communication technologies (e.g. bandwidth limitations). Recent developments in learned compression can enable the learning of end-to-end cooperative systems using deep learning with compressed communication in the pipeline. We explore the use of a deep learning object detector in a cooperative setting with a learned compression model facilitating communication between agents. To test our algorithm, this research will focus on object detection in the image domain as a proxy for one of the modalities used by collaborative systems.

Premium content

Understanding and Assessing Safety in Artificial Intelligence Systems

Downloads

Next from NAML 2022

VALIDnet: A General Defense against Adversarial Examples in Neural Networks

Similar lecture

NLP Application of Safety Documentation

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES