1,000+ Opportunities
Find the right grant
Search federal, foundation, and corporate grants with AI — or browse by agency, topic, and state.
This listing may be outdated. Verify details at the official source before applying.
Find similar grantsDefending Machine Learning Models from Adversarial Threats via Unified Interpretability and Attribution (NSF CAREER Award) is sponsored by National Science Foundation (NSF). This NSF CAREER Award project focuses on enhancing the safety, resilience, and accountability of machine learning systems.
Get alerted about grants like this
Get emailed when new opportunities from “National Science Foundation (NSF)” or related funders appear. Free, weekly, unsubscribe anytime.
Or search similar grants →Extracted from the official opportunity page/RFP to help you evaluate fit faster.
Professor earns NSF CAREER Award to defend AI models from attackers | RIT Professor earns NSF CAREER Award to defend AI models from attackers Weijie Zhao’s research aims to enhance machine learning safety, resilience, and accountability Weijie Zhao, assistant professor of computer science, recently received an NSF CAREER Award to build machine learning models that are more secure and interpretable.
Artificial intelligence has become a powerful tool for critical systems in healthcare, finance, and national security. However, these complex machine learning systems can also be targets for attackers. Weijie Zhao , an assistant professor of computer science at RIT, wants to shine a light on AI design and make sure that machine learning models are not embedded with hidden vulnerabilities or dangerous exploits.
His research will help build machine learning models that are more secure and interpretable. “As we use AI and agentic AI more, this really is a public concern,” said Zhao. “We want to make sure that there is no false information or misinformation and that decisions are not being manipulated.
” Zhao recently earned a prestigious National Science Foundation Faculty Early Career Development (CAREER) award and grant for his work. His five-year project is titled “ Defending Machine Learning Models from Adversarial Threats via Unified Interpretability and Attribution .
” The main problem stems from the fact that complex machine learning behaviors are like a black box—while the outputs might be visible, the AI’s internal decision-making process is incomprehensible to humans. The result is a lot of unknowns about the AI system. For example, an AI agent could be trained using a model that unintentionally has false information.
Attackers could also build large language models that have a backdoor or watermark. “Attackers don’t even need to steal your data,” explained Zhao. “They could make a model that influences decision generation in some way.
” Zhao noted that on OpenClaw, the popular free and open-source AI agent, threat actors have been caught using third-party extensions to essentially distribute malware. In February, researchers found 341 malicious ClawHub skills that were stealing data from users .
Making machine learning models transparent The CAREER Award project seeks to enhance the safety, resilience, and accountability of machine learning systems that are deployed in high-stakes environments. Through his research, Zhao hopes to bridge the gap between modern AI systems and classical machine learning frameworks that scientists already understand.
With these tools, defenders would be able to trace the origin of failures and repair vulnerabilities. Zhao plans to: Develop techniques to identify how adversarial inputs or training data components lead to harmful outputs. Design fast strategies to remove harmful behavior without full retraining, utilizing surrogate models to semantically validate that repairs are localized and verifiable.
Build automated pipelines for training data auditing, provenance tracking, and security-aware valuation to detect data poisoning and instability. Create an interface where users can explore suspicious outputs and interactively remediate vulnerabilities. “Essentially, we want to find that malicious data in the inference time, correct it without having to retrain the model, and provide proof that it’s fixed,” said Zhao.
At RIT, Zhao is working with five computing and information sciences Ph. D. students.
He hopes that future practitioners will use this defense framework to create more resilient, transparent, and trustworthy machine learning tools. “This is very important, because right now, many developers are chasing the best AI performer,” said Zhao. “But they should also be chasing the security and guardrails for responsible AI systems.
” The prestigious CAREER Award program recognizes and supports junior faculty who exemplify the role of teacher-scholars through integrated research and educational activities. RIT has more than a dozen NSF CAREER award winners working at the university.
Ke Xu earns NSF CAREER Award to research edge computing and AI technology Dimah Dera and students to develop trustworthy AI through NSF CAREER Award RIT launches hands-on Bachelor of Science degree in artificial intelligence
According to the current listing, eligibility includes: Early career university faculty (assistant professors) are eligible to apply for NSF CAREER awards. Confirm the full requirements in the official notice before applying.
Defending Machine Learning Models from Adversarial Threats via Unified Interpretability and Attribution (NSF CAREER Award) is funded by National Science Foundation (NSF). Verify program details on the funder's official page before applying.
Start from the official opportunity page linked in this listing — it carries the sponsor's submission instructions.
The UKRI Policy Fellowships 2025, funded by the Economic and Social Research Council, offer 18-month placements for academics to co-design research with UK government and What Works Network host organizations. Awards range from £180,000 to £280,000 and support three fellowship tracks: core policy fellows, Natural Hazards and Resilience policy fellows, and What Works Innovation fellows. Applicants must hold a PhD or equivalent research experience, be based at a UKRI-eligible UK organization, and possess relevant subject matter or methodological expertise. Government-hosted positions target early to mid-career academics, while What Works fellowships welcome all career stages. Fellows work directly with policymakers to bridge academic research and policy development on pressing national and global challenges. The application deadline is July 15, 2025.
The Smart Data Research UK Fellowships provide up to £200,000 per project for researchers using smart data to address real-world challenges across the United Kingdom. Funded by UKRI through Smart Data Research UK, this program supports up to ten projects lasting 18 months, with start dates by February 2026. Applicants must be based at eligible UK organizations and demonstrate strong data skills with a compelling research question aligned to one of four SDR UK themes: productivity and prosperity, health and wellbeing, sustainability, or communities and places. Researchers at all career stages may apply, with early career researchers particularly encouraged. Projects may use smart datasets from SDR UK's six national data services or combine smart data with administrative and survey data sources.
On July 22, 2026, NSF announced $83 million in Integrated Data Systems and Services awards and launched a companion program, Unlocking Dataset Value for AI-Enabled Scientific Discovery, offering up to $100 million in $2M-$5M awards. Together they fund the least glamorous and most decisive part of the AI-for-science stack: the data. Here is what each program funds, who won the first round, how the two fit the Genesis Mission, and the concrete strategy for research teams that missed the first cohort.
Read articleNSF's Growing Convergence Research program (NSF 24-527) offers up to $1.2 million in a two-year Phase I and up to $2.4 million more in a three-year Phase II — $3.6 million across five years — with a $16 million pool funding just 6 to 10 projects and a February 8, 2027 deadline. But GCR is not a bigger version of an interdisciplinary grant. It funds a specific team architecture, and the proposals that lose are usually the ones that mistake multidisciplinary collaboration for convergence. Here is what NSF actually means by convergence, how the two-phase gate works, and how to build a team that survives the Phase I review.
Read articleNSF's NAIRR Operations Center solicitation (NSF 25-546) will make a single award of up to $35 million over five years to the organization that will run the National AI Research Resource — the shared computing, data, and model infrastructure that has already connected over 400 U.S. research teams. This is a rare winner-take-all federal competition where the prize is not funding for your own research but the mandate to operate national infrastructure. Here is what the NAIRR is, why its transition from pilot to permanent program matters, and what kind of organization can credibly win it.
Read article