Drones: Instructional Materials
Drones over New Jersey: Latest updates on what we know, what we don't
There are some mysterious flying objects hovering over New Jersey and, days after the first drones were spotted, we still don't know much about what they are, where they're from, and what they're doing up there. Folks with eyes on New Jersey have been reporting mysterious drone sightings -- over houses, military installations, and Trump's Bedminster golf club, to name a few -- since mid-November. The FBI, Department of Homeland Security, and Federal Aviation Administration have all investigated the origins but don't yet have any answers for us. The Pentagon says the mystery drones are not military and are probably not foreign. New Jersey Gov. Phil Murphy and U.S. Sen. Andy Kim have gone on their own drone hunts, too, but have come back empty-handed.
The Malicious Use of Artificial Intelligence: Forecasting, Prevention, and Mitigation
Brundage, Miles, Avin, Shahar, Clark, Jack, Toner, Helen, Eckersley, Peter, Garfinkel, Ben, Dafoe, Allan, Scharre, Paul, Zeitzoff, Thomas, Filar, Bobby, Anderson, Hyrum, Roff, Heather, Allen, Gregory C., Steinhardt, Jacob, Flynn, Carrick, hÉigeartaigh, Seán Ó, Beard, SJ, Belfield, Haydn, Farquhar, Sebastian, Lyle, Clare, Crootof, Rebecca, Evans, Owain, Page, Michael, Bryson, Joanna, Yampolskiy, Roman, Amodei, Dario
This report surveys the landscape of potential security threats from malicious uses of AI, and proposes ways to better forecast, prevent, and mitigate these threats. After analyzing the ways in which AI may influence the threat landscape in the digital, physical, and political domains, we make four high-level recommendations for AI researchers and other stakeholders. We also suggest several promising areas for further research that could expand the portfolio of defenses, or make attacks less effective or harder to execute. Finally, we discuss, but do not conclusively resolve, the long-term equilibrium of attackers and defenders.
Introduction to AI Safety, Ethics, and Society
Artificial Intelligence is rapidly embedding itself within militaries, economies, and societies, reshaping their very foundations. Given the depth and breadth of its consequences, it has never been more pressing to understand how to ensure that AI systems are safe, ethical, and have a positive societal impact. This book aims to provide a comprehensive approach to understanding AI risk. Our primary goals include consolidating fragmented knowledge on AI risk, increasing the precision of core ideas, and reducing barriers to entry by making content simpler and more comprehensible. The book has been designed to be accessible to readers from diverse backgrounds. You do not need to have studied AI, philosophy, or other such topics. The content is skimmable and somewhat modular, so that you can choose which chapters to read. We introduce mathematical formulas in a few places to specify claims more precisely, but readers should be able to understand the main points without these.
Using Helium Balloon Flying Drones for Introductory CS Education
Cao, Stanley, Gregg, Christopher
In the rapidly evolving field of computer science education, novel approaches to teaching fundamental concepts are crucial for engaging a diverse student body. Given the growing demand for a computing-skilled workforce, it is essential to adapt educational methods to capture the interest of a broader audience than what current computing education typically targets. Engaging educational experiences have been shown to have a positive impact on learning outcomes and examination performance, especially within computing education. Moreover, physical computing devices have been shown to correlate with increased student motivation when students are studying computer science.
Foundational Challenges in Assuring Alignment and Safety of Large Language Models
Anwar, Usman, Saparov, Abulhair, Rando, Javier, Paleka, Daniel, Turpin, Miles, Hase, Peter, Lubana, Ekdeep Singh, Jenner, Erik, Casper, Stephen, Sourbut, Oliver, Edelman, Benjamin L., Zhang, Zhaowei, Günther, Mario, Korinek, Anton, Hernandez-Orallo, Jose, Hammond, Lewis, Bigelow, Eric, Pan, Alexander, Langosco, Lauro, Korbak, Tomasz, Zhang, Heidi, Zhong, Ruiqi, hÉigeartaigh, Seán Ó, Recchia, Gabriel, Corsi, Giulio, Chan, Alan, Anderljung, Markus, Edwards, Lilian, Bengio, Yoshua, Chen, Danqi, Albanie, Samuel, Maharaj, Tegan, Foerster, Jakob, Tramer, Florian, He, He, Kasirzadeh, Atoosa, Choi, Yejin, Krueger, David
This work identifies 18 foundational challenges in assuring the alignment and safety of large language models (LLMs). These challenges are organized into three different categories: scientific understanding of LLMs, development and deployment methods, and sociotechnical challenges. Based on the identified challenges, we pose $200+$ concrete research questions.
Domain Adaptive Detection of MAVs: A Benchmark and Noise Suppression Network
Zhang, Yin, Deng, Jinhong, Liu, Peidong, Li, Wen, Zhao, Shiyu
Visual detection of Micro Air Vehicles (MAVs) has attracted increasing attention in recent years due to its important application in various tasks. The existing methods for MAV detection assume that the training set and testing set have the same distribution. As a result, when deployed in new domains, the detectors would have a significant performance degradation due to domain discrepancy. In this paper, we study the problem of cross-domain MAV detection. The contributions of this paper are threefold. 1) We propose a Multi-MAV-Multi-Domain (M3D) dataset consisting of both simulation and realistic images. Compared to other existing datasets, the proposed one is more comprehensive in the sense that it covers rich scenes, diverse MAV types, and various viewing angles. A new benchmark for cross-domain MAV detection is proposed based on the proposed dataset. 2) We propose a Noise Suppression Network (NSN) based on the framework of pseudo-labeling and a large-to-small training procedure. To reduce the challenging pseudo-label noises, two novel modules are designed in this network. The first is a prior-based curriculum learning module for allocating adaptive thresholds for pseudo labels with different difficulties. The second is a masked copy-paste augmentation module for pasting truly-labeled MAVs on unlabeled target images and thus decreasing pseudo-label noises. 3) Extensive experimental results verify the superior performance of the proposed method compared to the state-of-the-art ones. In particular, it achieves mAP of 46.9%(+5.8%), 50.5%(+3.7%), and 61.5%(+11.3%) on the tasks of simulation-to-real adaptation, cross-scene adaptation, and cross-camera adaptation, respectively.
Using Programmable Drone in Educational Projects and Competitions
Petrovič, Pavel, Verčimák, Peter
The mainstream of educational robotics platforms orbits the various versions of versatile robotics sets and kits, while interesting outliers add new opportunities and extend the possible learning situations. Examples of such are reconfigurable robots, rolling sphere robots, humanoids, swimming, or underwater robots. Another kind within this category are flying drones. While remotely controlled drones were a very attractive target for hobby model makers for quite a long time already, they were seldom used in educational scenarios as robots that are programmed by children to perform various simple tasks. A milestone was reached with the introduction of the educational drone Tello, which can be programmed even in Scratch, or some general-purpose languages such as Node.js or Python. The programs can even have access to the robot sensors that are used by the underlying layers of the controller. In addition, they have the option to acquire images from the drone camera and perform actions based on processing the frames applying computer vision algorithms. We have been using this drone in an educational robotics competition for three years without camera, and after our students have developed several successful projects that utilized a camera, we prepared a new competition challenge that requires the use of the camera. In the article, we summarize related efforts and our experiences with educational drones, and their use in the student projects and competition.
DeepInception: Hypnotize Large Language Model to Be Jailbreaker
Li, Xuan, Zhou, Zhanke, Zhu, Jianing, Yao, Jiangchao, Liu, Tongliang, Han, Bo
Despite remarkable success in various applications, large language models (LLMs) are vulnerable to adversarial jailbreaks that make the safety guardrails void. However, previous studies for jailbreaks usually resort to brute-force optimization or extrapolations of a high computation cost, which might not be practical or effective. In this paper, inspired by the Milgram experiment w.r.t. the authority power for inciting harmfulness, we disclose a lightweight method, termed DeepInception, which can easily hypnotize LLM to be a jailbreaker. Specifically, DeepInception leverages the personification ability of LLM to construct a novel nested scene to behave, which realizes an adaptive way to escape the usage control in a normal scenario. Empirically, our DeepInception can achieve competitive jailbreak success rates with previous counterparts and realize a continuous jailbreak in subsequent interactions, which reveals the critical weakness of self-losing on both open and closed-source LLMs like Falcon, Vicuna-v1.5, Llama-2, and GPT-3.5-turbo/4. Our investigation appeals to people to pay more attention to the safety aspects of LLMs and develop a stronger defense against their misuse risks. The code is publicly available at: https://github.com/tmlr-group/DeepInception.
MADRL-based UAVs Trajectory Design with Anti-Collision Mechanism in Vehicular Networks
Spampinato, Leonardo, Testi, Enrico, Buratti, Chiara, Marini, Riccardo
In upcoming 6G networks, unmanned aerial vehicles (UAVs) are expected to play a fundamental role by acting as mobile base stations, particularly for demanding vehicle-to-everything (V2X) applications. In this scenario, one of the most challenging problems is the design of trajectories for multiple UAVs, cooperatively serving the same area. Such joint trajectory design can be performed using multi-agent deep reinforcement learning (MADRL) algorithms, but ensuring collision-free paths among UAVs becomes a critical challenge. Traditional methods involve imposing high penalties during training to discourage unsafe conditions, but these can be proven to be ineffective, whereas binary masks can be used to restrict unsafe actions, but naively applying them to all agents can lead to suboptimal solutions and inefficiencies. To address these issues, we propose a rank-based binary masking approach. Higher-ranked UAVs move optimally, while lower-ranked UAVs use this information to define improved binary masks, reducing the number of unsafe actions. This approach allows to obtain a good trade-off between exploration and exploitation, resulting in enhanced training performance, while maintaining safety constraints.
Shaping and Being Shaped by Drones: Supporting Perception-Action Loops
Sondoqah, Mousa, Abdesslem, Fehmi Ben, Popova, Kristina, McGregor, Moira, La Delfa, Joseph, Garrett, Rachael, Lampinen, Airi, Mottola, Luca, Höök, Kristina
We report on a three-day challenge during which five teams each programmed a nanodrone to be piloted through an obstacle course using bodily movement, in a 3D transposition of the '80s video-game Pacman. Using a bricolage approach to analyse interviews, field notes, video recordings, and inspection of each team's code revealed how participants were shaping and, in turn, became shaped in bodily ways by the drones' limitations. We observed how teams adapted to compete by: 1) shifting from aiming for seamless human-drone interaction, to seeing drones as fragile, wilful, and prone to crashes; 2) engaging with intimate, bodily interactions to more precisely understand, probe, and delimit each drone's capabilities; 3) adopting different strategies, emphasising either training the drone or training the pilot. We contribute with an empirical, somaesthetically focused account of current challenges in HDI and call for programming environments that support action-feedback loops for design and programming purposes.