Presentation at The Eleventh International Conference on Learning Representations (ICLR) reveals new findings in end-to-end neural network Trojan removal technology
Los Alamitos, California, May 5, 2023 /PRNewswire/ — Virtual Today Backdoor attacks and defenses in machine learning (BANDS) 11th International Conference on Learning Expressions (ICLR) during workshop, participants IEEE Trojan Removal Contest Published research and success rates on effectively and efficiently mitigating the impact of neural Trojans while maintaining high performance.Harbin Institute of Technology’s winning team evaluated by clean accuracy, poison accuracy, and attack success rate Shenzhen, using a set of HZZQ defenses, formulated a highly effective solution, resulting in a 98.14% poison accuracy rate and a meager 0.12% attack success rate. This group $5,000 USD.
Professor Meikang Qiu, chair of the IEEE Smart Computing Special Technical Committee (SCSTC) and full professor at the Beacom College of Computer and Cyber said:science in Dakota State University, Madison, South DakotaUSA He has also been named a 2021 IEEE Computer Society Distinguished Contributor.
In 2022, IEEE CS will establish the Emerging Technology Fund, the first $25,000 USD Awarded to the IEEE SCSTC for the “Annual Competition on Emerging Issues in Data Security and Privacy (EDISP)” which resulted in the IEEE Trojan Removal Competition (TRC ’22). This proposal offered a fresh take on cyber topics as it encouraged participants to explore solutions that could enhance the security of neural networks, unlike most existing contests that only focused on backdoor model detection. provided. By developing a common, effective, and efficient white-box Trojan removal technique, participants will be able to develop specifically pre-trained models that are essential for protecting artificial intelligence from potential attacks. has helped build trust in deep learning and artificial intelligence when using it in practice.
With 1,706 valid submissions from 44 teams around the world, 6 groups successfully developed the technique, outperforming state-of-the-art baseline metrics published in major machine learning forums. Achieved. A benchmark summarizing the models and attacks used during the competition has been released to allow for additional research and evaluation.
“We hope this benchmark will provide diverse and easy access to model settings for those coming up with new AI security techniques,” he shared. Yi ZenCompetition Chair, IEEE TRC’22, Research Assistant, Bradley Department of Electrical and Computer Engineering, Virginia Tech, Blacksburg, VirginiaU.S. “This competition yielded new datasets consisting of pre-trained, poisoned and pre-trained models of different architectures and trained on different types of data distributions with very high attack success rates.” Now developers can explore new defenses and weed out those remaining vulnerabilities.”
Two important findings emerged from the overall results of the participants during the competition.
- Many classical techniques for mitigating the effects of backdoors, which can overcorrect if they do not “learn” key elements of the code, have been proposed and emphasized throughout IEEE TRC’22. Model performance suffers because we typically ignore the new metric, a measure of impact on tainted accuracy. .
- Many existing techniques have low generalizability, which means that some methods are only valid for specific data sets or specific machine learning model architectures.
These findings demonstrate the fact that general approaches to mitigating attacks on neural networks are not recommended for the foreseeable future. Zeng emphasized the urgent need for a comprehensive AI security solution. The competition, coupled with the release of benchmarks, will galvanize the community to develop more robust and adaptable security measures for AI systems. “
“As the world becomes more and more dependent on AI and machine learning, it is important to address the security and privacy issues these technologies pose,” said Qiu. “His IEEE TRC ’22 competition in EDISP has brought about a great change in this field. A colleague on the Steering Committee, he would like to express his special thanks to Professor Ruoxi Jia. Virginia Tech, Neil Gong from duke, Chan Tien Wei from Nanyang Technological University, Shu Tao Xia from Tsinghua University, Bo Lee from University of Illinois at Urbana-Champaign — for their help and support.”
Ideas and insights from this event, along with publicly available benchmark data, will help make the future of machine learning and artificial intelligence safer and more reliable. The team plans to conduct his second year of the contest, and these findings will further strengthen the security parameters of neural networks.
“This is exactly the kind of work that the Emerging Technology Fund wants to promote,” he said. Nita Patel, President of the IEEE Computer Society in 2023. “As technology advances, it will go a long way in enhancing the iterative development that strengthens the security of machine learning and AI platforms.”
For more information on the entire Emerging Technology Grants Program, please visit: https://www.computer.org/communities/emerging-technology-fund.
About the IEEE Trojan Removal Contest
IEEE TRC’22 aims to encourage the development of innovative end-to-end neural network backdoor removal techniques to combat backdoor attacks. For more information, see: https://www.trojan-removal.com/.
About the IEEE Computer Society
The IEEE Computer Society is the world’s hub for computer science, engineering, and technology. A world leader in providing access to computer science research, analysis, and information, the IEEE Computer Society offers unparalleled products, services, and opportunities to professionals and individuals at all stages of their careers. We offer comprehensive. Recognized as the premier organization for empowering those who advance technology, the IEEE Computer Society offers international conferences, peer-reviewed publications, a unique digital library, and training programs.visit computer.org for more information.
View original content and download multimedia: https://www.prnewswire.com/news-releases/ieee-computer-society-emerging-technology-fund-recipient-introduces-machine-learning-cybersecurity-benchmarks- 301817424.html
Source IEEE Computer Society
