Recent years have seen dramatic increase in applications of deep learning techniques to solve real world problem, range from social network to online ecommerce etc. However, the intelligence system powered by deep learning itself is vulnerable and lucrative target to attackers. In 2014, Christian Szegedy et al. firstly found that the highly accurate modern deep learning models are susceptible to adversarial samples that are derived from the original images by adding small perturbations. To address the security problem of AI system, many methods for model attack and defense have been proposed. However, the problem is far from being solved.
The IJCAI-2019 Alibaba Adversarial AI Challenge (AAAC2019) aims at providing a venue for AI practitioners to explore the security of the AI models. Our competition this year focus on image classification tasks, and includes model attacks and model defenses. The participants can play as an attacker to fool our models, or can play as a defender to provide robust model against the adversarial samples.
Three tasks are proposed in this competition including non-targeted attack, targeted attack, and model defense. Specifically,
You can download the competition material here: Download
Thursday, August 15th 14:00 - 18:00 Room 2305
The competition webpage has been released at https://tianchi.aliyun.com/markets/tianchi/ijcai2019
The Automated Negotiating Agent Competition (ANAC) brings together researchers from the negotiation community and provides a unique benchmark for evaluating practical negotiation strategies in multi-issue domains. The ANAC has the following aims:
The previous competitions have spawned novel research in AI in the field of autonomous agent design which are available to the wider research community. This year, we would like to introduce a variety of negotiation research challenges:
We expect innovative and novel agent strategies will be developed, and the submitted ANAC 2019 agents will serve as a negotiating agent repository to the negotiation community. The researchers can develop novel negotiating agents and evaluate their agents by comparing their performance with the performance of the ANAC 2019 agents.
Thursday, August 15th 14:00 - 18:00 Room 2304
For more details, please visit the competition webpage : http://web.tuat.ac.jp/~katfuji/ANAC2019/
Now that Go has been solved, the next challenge for AI is the game of Angry Birds. Unlike Go and other supposedly difficult games, Angry Birds has an infinite number of possible actions to chose from and the exact outcome of each action is unknown in advance. This makes the game very hard for computers to master. It adds to the diculty that computers have to play live games in the same way humans play them, without any additional information about the exact physics of the game. The worlds best Angry Birds AI agents will meet during the IJCAI 2019 conference and compete for the title of AIBIRDS 2019 World Champion. IJCAI 2019 will also host the annual Angry Birds Man vs Machine Challenge where we test if AI can already beat the best human players. If you want to participate in this exciting competition, please go to http://aibirds.org for more details.
Wednesday, August 14th, all day, Room 2305
For more details, please visit the competition webpage : http://aibirds.org
With the arrival of a global aging society, eldercare shows the general trend of demand greater than supply. The elderly are expected to enjoy a better quality of life through robot services. For example in the place where supervising taking medicine, a robot which can accompany the elder warmly like a nurse is far more effective than an alarm clock. When the elder encounters a dangerous situation such as falling down, timely warning by a robot can significantly reduce the risk of accidents. In fact, the abilities to moving, perceiving and serving forwardly offers a first- rate experience that no other solution can replace. Although there are more and more useful technologies of robotic developed in recent years, there is no mature and stable application in eldercare that can be truly industrialized.
The IJCAI-2019 Eldercare Robot Challenges aim at promoting the industrialization of eldercare robots in the future and speeding up product-level applications through this competition. We hope to see from the competition some concrete solutions and outcomes in real-world applications in near future.
The Robot Task Challenge Competition: 13-16 August 2019
Deadline for submitting designing report of the Elderly-Care Robot Design Challenge： Aug. 1, 2019
For more details, please visit the competition webpage: http://robo-tend.ustc.edu.cn/
In the spirit of earlier AI Video Competitions, the intention of the IJCAI 2019 AI Video Competition is to provide researchers with a showcase for demonstrating how exciting and interesting Artificial Intelligence can be, as well as offering to the public and the media accurate information crafted first-hand by researchers.
A wide range of videos related to artificial intelligence can be submitted to the competition. The topic of a video might, for example, be a general or specific area of AI, the work of a particular researcher or group (yourselves or others), or a concrete application that depends on one or several AI techniques, and that may be based entirely on software or partly on hardware. A video may concern work with different levels of maturity: you can introduce something new and interesting, describing known but ongoing research, or summarize a mature area or application, showing its impact on society. The intended audience of a video can be students learning about a topic in a classroom, researchers interested in learning more about subfields outside their own, the general public, or the media, etc.
The results of the competition will be presented at the IJCAI 2019 conference (August 10-16, 2019, in Macao, China), where the best videos will be announced. All videos will also be made available online.
For more details, please visit the competition webpage : https://www.ijcai19.org/call-for-videos.html
The goal of this challenge is to encourage AI enthusiast in Macao high schools to apply their AI skills to solve some real-world problems in order to make our city smarter. The major tasks in this challenge are (1) to design a classification algorithm that can correctly classify real-world small images of traffic signs; and (2) to design an detection algorithm that can accurately recognize traffic sign(s) from a set of photos. These skills are particularly useful in intelligent transportation systems (e.g., auto-driving and traffic accident analysis).
Tuesday, August 13th, 15:00 - 17:00, Room 2305
Leong Hou U, University of Macau
Argumentation is a major topic in the study of artificial intelligence. In particular, the problem of solving certain reasoning tasks on Dung's abstract argumentation frameworks is central to many advanced argumentation systems. The fact that problems to be solved are intractable requires efficient algorithms and solvers.
The ICCMA competition aims at nurturing research and development of implementations for computational models of argumentation. The objectives of the competition are to provide a forum for empirical comparison of solvers, to highlight challenges to the community, to propose new directions for research and to provide a core of common benchmark instances and a representation formalism that can aid in the comparison and evaluation of solvers.
The Third International Competition on Computational Models of Argumentation (ICCMA'19) focuses on reasoning tasks in abstract argumentation frameworks. Submitted solvers are tested on a selected collection of benchmark instances and wrt. a variety of problems and semantics.
The presentation of the results and the award ceremony will take place at IJCAI 2019, on Monday, August 12th, in the morning.
Time: Monday, August 12th 10:30-12:30; Venue: Room 2405
For more details, please visit the competition webpage : http://iccma2019.dmi.unipg.it