news

한어Русский языкEnglishFrançaisIndonesianSanskrit日本語DeutschPortuguêsΕλληνικάespañolItalianoSuomalainenLatina

it home reported on september 6 that on the morning of september 6, at the 2024 inclusion bund conference "using ai to protect the offense and defense in the era of ai big models" forum, the country's first big model offense and defense themed technology event "global ai offense and defense challenge" was officially launched.

this competition focuses on the industrial practice of ai big models, and has designed a two-way track of attack and defense. it invites various "white hat hackers" (it home note: programmers who attack their own systems from the perspective of hackers to detect security vulnerabilities) and technical talents to conduct practical attack and defense drills on "data poisoning" of wenshengtu big models, as well as anti-counterfeiting detection competitions for content generated by big models of financial scenarios.

the "attack track" focuses on the actual application risk issues of the large model of raw images. contestants can use a variety of dynamic attack induction techniques such as target hijacking, scenario introduction, and logical nesting to induce the large model to output risk images, thereby activating the potential weaknesses and vulnerabilities of the large model and enhancing the security immunity of the large model raw images.

the "defense track" focuses on the detection of credential tampering in financial scenarios in ai authentication to cope with the increasingly severe risks of deepfake and aigc fake certificates. the competition provides a training set of millions of credential tampering data. participants need to develop and train models, and use the corresponding test sets to evaluate the effectiveness of the models and give the probability value of data forgery.

the event is co-organized by the chinese society of image and graphics, ant group, and cloud security alliance (csa) greater china, and is supported by c9 universities such as shanghai jiao tong university and zhejiang university, as well as a number of industry-university-research organizations.

the competition has set up a prize pool of nearly 1 million yuan, and invited many well-known experts from academia and industry to serve as judges. wang yaonan, academician of the chinese academy of engineering and chairman of the chinese society of image and graphics, and li yuhang, chairman of the greater china region of the cloud security alliance (csa), serve as experts on the steering committee of this competition. nearly 30 well-known scholars from tsinghua university, shanghai jiaotong university, shanghai artificial intelligence laboratory, chinese society of image and graphics and other institutions will participate in the organization and evaluation of the competition.

the competition officially started registration on september 6, and the competition review will be completed in early november. from now on, contestants can register through the official website of the chinese society of image and graphics, the official website of alibaba cloud tianchi big data crowd intelligence platform, and other channels.