Meta tags:
author=Jingwei Yi;

Headings (most frequently used words):

jingwei, yi, awards, selected, publications,

Text of the page (most frequently used words):
and (19), the (18), #jingwei (15), for (13), xie (13), code (12), paper (12), xing (11), federated (10), efficient (10), fangzhao (10), propose (9), 2023 (8), guangzhong (8), sun (8), learning (7), large (7), language (7), models (7), news (6), effective (6), recommendation (6), attacks (6), science (6), attack (5), bin (5), zhu (5), chen (5), from (4), security (4), model (4), fedrec (4), zhang (4), robust (4), supervised (4), wang (4), self (4), risks (4), based (3), first (3), track (3), 2022 (3), chuhan (3), emnlp (3), method (3), quantity (3), untargeted (3), aware (3), extraction (3), llms (3), reverse (3), alignment (3), methods (3), research (3), reminders (3), against (3), intelligence (3), misuse (3), documents (2), prize (2), information (2), leaderboard (2), hetero (2), task (2), are (2), heterogeneous (2), cikm (2), competition (2), red (2), teaming (2), awards (2), liu (2), 2021 (2), framework (2), yang (2), tiny (2), newsrec (2), knowledge (2), improve (2), plm (2), tao (2), aggregation (2), arxiv (2), binxing (2), jiao (2), query (2), snippet (2), web (2), search (2), peng (2), lingjuan (2), lyu (2), tong (2), backdoor (2), watermark (2), defend (2), acl (2), via (2), called (2), kdd (2), fine (2), tuning (2), value (2), 2024 (2), semi (2), non (2), iid (2), yueqi (2), further (2), system (2), jailbreak (2), defending (2), control (2), artificial (2), indirect (2), prompt (2), injection (2), vision (2), google (2), scholar (2), university (2), technology (2), china (2), ustc (2), problems (2), design, source, jon, barron, website, implement, font, watermarking, algorithm, digital, national, college, student, contest, project, provide, solution, where, tasks, across, multiple, clients, analyticup, runners, optimize, gcg, llm, nips, tdc, third, ruixuan, new, privacy, preserving, atwo, stage, distillation, efficiency, huishuai, which, enhanced, xiaolong, huang, deepqse, wenjun, shangxi, embmarker, againt, embedding, services, area, chair, award, nlp, application, you, copying, protecting, copyright, eaas, jing, yao, zhulin, study, this, problem, proposing, rui, qisi, siheng, defu, lian, reveal, vulnerabilities, introduce, rsft, preference, optimization, rpo, our, underscores, limitations, current, emphasizes, need, solutions, counteract, malicious, findings, vulnerability, open, access, chao, derong, jindong, yidong, enhong, fedloke, under, settings, always, bad, with, local, enhancement, jiawei, shao, justin, curl, qifeng, draw, inspiration, psychological, concept, mode, reminder, nature, machine, chatgpt, jiyan, weitao, feng, yaosen, min, kunsheng, tang, shuai, jie, kejiang, wenbo, zhou, weiming, nenghai, shuxin, zheng, itemize, posed, scientific, contexts, then, demonstrate, highlighting, real, world, examples, chemical, sciguard, risk, potential, keegan, hines, emre, kiciman, systematically, evaluate, robustness, several, defense, techniques, mitigate, benchmarking, junhao, yin, bao, yongliang, wei, fan, hao, investigated, ability, comprehend, reference, images, within, rag, developed, automated, evaluation, methodology, imageref, enabling, contextual, image, referencing, indicates, joint, authors, full, publication, list, can, found, selected, publications, linkedin, github, email, have, bachelor, degree, focusing, responsible, especially, societal, safety, related, recently, obtained, currently, researcher, center, baai, beijing, academy, prof, microsoft, asia, publicaitons, home, toggle, navigation,

Text of the page (random words):
jingwei yi toggle navigation jingwei yi home publicaitons awards jingwei yi i recently obtained my ph d from microsoft research asia and university of science and technology of china ustc supervised by dr xing xie and prof guangzhong sun i am currently a researcher at the large language model security center of baai beijing academy of artificial intelligence i am focusing on responsible ai research problems especially the societal safety and security problems related to large language models i have a bachelor s degree in information security from university of science and technology of china ustc email github google scholar linkedin selected publications indicates joint first authors full publication list can be found on google scholar imageref vl enabling contextual image referencing in vision language models jingwei yi junhao yin ju xu peng bao yongliang wang wei fan hao wang arxiv 2024 paper code we investigated methods to improve vision language models ability to comprehend and reference images within rag documents and developed an effective automated evaluation methodology benchmarking and defending against indirect prompt injection attacks on large language models jingwei yi yueqi xie bin zhu keegan hines emre kiciman guangzhong sun xing xie fangzhao wu kdd 2023 paper code we systematically evaluate the robustness of llms to indirect prompt injection attacks and propose several defense techniques to mitigate the risks control risk for potential misuse of artificial intelligence in science jiyan he weitao feng yaosen min jingwei yi kunsheng tang shuai li jie zhang kejiang chen wenbo zhou xing xie weiming zhang nenghai yu shuxin zheng ai for science 2023 paper we itemize the risks posed by ai in scientific contexts then demonstrate the risks by highlighting real world examples of misuse in chemical science we further propose a system called sciguard to control misuse risks for ai models in science self reminders defending chatgpt against jailbreak attack via self reminders yueqi xie jingwei yi jiawei shao justin curl lingjuan lyu qifeng chen xing xie fangzhao wu nature machine intelligence 2023 paper code we draw inspiration from the psychological concept of self reminders and further propose system mode self reminder to defend against jailbreak attacks non iid always bad semi supervised heterogeneous federated learning with local knowledge enhancement chao zhang fangzhao wu jingwei yi derong xu yang yu jindong wang yidong wang tong xu xing xie enhong chen cikm 2023 paper code we propose fedloke and effective semi supervised federated learning under non iid settings on the vulnerability of value alignment in open access llms jingwei yi rui ye qisi chen bin zhu siheng chen defu lian guangzhong sun xing xie fangzhao wu acl 2024 findings 2023 paper we reveal the vulnerabilities of large language models llms to reverse alignment attacks and introduce reverse supervised fine tuning rsft and reverse preference optimization rpo as efficient attack methods our research underscores the limitations of current value alignment methods and emphasizes the need for robust solutions to counteract malicious fine tuning ua fedrec untargeted attack on federated news recommendation jingwei yi fangzhao wu bin zhu jing yao zhulin tao guangzhong sun xing xie kdd 2023 paper code we study this problem by proposing an untargeted attack on federated news recommendation called ua fedrec are you copying my model protecting the copyright of large language models for eaas via backdoor watermark wenjun peng jingwei yi fangzhao wu shangxi wu bin zhu lingjuan lyu binxing jiao tong xu guangzhong sun xing xie acl 2023 area chair award of nlp application track paper code we propose embmarker a backdoor watermark to defend againt model extraction attacks to embedding services effective and efficient query aware snippet extraction for web search jingwei yi fangzhao wu chuhan wu xiaolong huang binxing jiao guangzhong sun xing xie emnlp 2022 paper code we propose efficient deepqse an effective and efficient query aware snippet extraction method for web search robust quantity aware aggregation for federated learning jingwei yi fangzhao wu huishuai zhang bin zhu tao qi guangzhong sun xing xie arxiv 2022 paper we propose a quantity robust aggregation method for federated learning which is robust to the quantity enhanced untargeted attacks tiny newsrec effective and efficient plm based news recommendation yang yu fangzhao wu chuhan wu jingwei yi qi liu emnlp 2021 paper code we propose tiny newsrec atwo stage knowledge distillation method to improve the efficiency of the large plm based news recommendation efficient fedrec efficient federated learning framework for privacy preserving news recommendation jingwei yi fangzhao wu chuhan wu ruixuan liu guangzhong sun xing xie emnlp 2021 paper code we propose efficient fedrec an efficient federated new recommendation framework awards nips 2023 tdc red teaming competition large model track the third prize we optimize the gcg attack for efficient and effective llm red teaming leaderboard code cikm 2022 analyticup competition federated hetero task learning first runners up we provide a solution for federated hetero task learning where the tasks are heterogeneous across multiple clients leaderboard code first prize of national college student information security contest project track we implement a font based watermarking algorithm for digital documents news design and source code from jon barron s website