Artificial Intelligence Security Competition (AISC)
It tackles AI security challenges for researchers and practitioners, but is incremental as it focuses on organizing a competition rather than novel research.
The paper introduces the Artificial Intelligence Security Competition (AISC), which was organized to accelerate research on AI security by addressing problems in deepfake, autonomous driving, and face recognition through competitive tracks, with results including top-ranking team solutions.
The security of artificial intelligence (AI) is an important research area towards safe, reliable, and trustworthy AI systems. To accelerate the research on AI security, the Artificial Intelligence Security Competition (AISC) was organized by the Zhongguancun Laboratory, China Industrial Control Systems Cyber Emergency Response Team, Institute for Artificial Intelligence, Tsinghua University, and RealAI as part of the Zhongguancun International Frontier Technology Innovation Competition (https://www.zgc-aisc.com/en). The competition consists of three tracks, including Deepfake Security Competition, Autonomous Driving Security Competition, and Face Recognition Security Competition. This report will introduce the competition rules of these three tracks and the solutions of top-ranking teams in each track.