At the invitation of the School of Management and Economics, Chai Yidong, a researcher from the School of Management of Hefei University of Technology, gave an academic report entitled "Research on Robust Artificial Intelligence Methods Considering Anti attack Threats" at the meeting room 317 of the main building at 11:00 a.m. on March 18, 2023. The presentation was presided over by Secretary Yan Zhijun, and many teachers and students from the college participated in the presentation.
At the beginning of the report, Chai Yidong first revealed the security vulnerabilities of current intelligent model methods through cases such as image recognition and text recognition. Among them, Adversarial Attack generates Adversarial Samples by slightly perturbing the original samples to deceive the intelligent model, thereby posing a serious threat to the security of the intelligent model. Therefore, Chai Yidong elaborated on how to evaluate the ability of intelligent models to resist adversarial attacks (adversarial robustness) and how to improve the adversarial robustness of intelligent models based on the Technology Threat Avoidance Theory (TTAT).
柴一棟簡介：
柴一棟，合肥工業(yè)大學(xué)研究員，博士生導(dǎo)師。博士畢業(yè)于清華大學(xué)經(jīng)管學(xué)院管理科學(xué)與工程系，本科畢業(yè)于偉德國際1946bv官網(wǎng)信息管理與信息系統(tǒng)專業(yè)，主要關(guān)注如何設(shè)計創(chuàng)新性的人工智能方法，更好地服務(wù)于個人、組織和社會的現(xiàn)代科學(xué)化管理，研究領(lǐng)域包括信息系統(tǒng)安全與網(wǎng)絡(luò)空間管理（醫(yī)聯(lián)網(wǎng)安全等）、智慧醫(yī)療管理、商務(wù)智能管理等。以第一作者或通訊作者發(fā)表研究成果于MISQ、ISR、JMIS、IEEE TDSC、IEEE TPAMI等國際管理學(xué)/計算機(jī)科學(xué)頂刊。榮獲國際信息系統(tǒng)權(quán)威會議WITS 2021 best paper award、清華大學(xué)優(yōu)秀博士論文等榮譽(yù)。
Finally, Chai Yidong summarized the application of intelligent models in resisting adversarial attacks in management, and pointed out that management organizations should improve the confidentiality of model design information and training datasets of intelligent models, and improve the ability of intelligent models to resist adversarial attacks by limiting access times.
After the report, the attending teachers and students had a positive discussion with Chai Yidong, which received a lot of inspiration. The report received a warm response and received unanimous praise from teachers and students.
Chai Yidong pointed out that evaluating the ability of intelligent models to resist adversarial attacks (adversarial robustness) can start with the design of indicators and sample selection. The indicators can be designed through relative robustness (PerformanceRatio) and Area Under the Performance-perturbation Curve, and a new interpretable adversarial sample generation framework (XATA) is proposed for sample selection. In terms of improving the adversarial robustness of intelligent models, Chai Yidong designed a Bayesian based integrated model by integrating multiple models, which can resist most adversarial attacks.
