About this role

Overview <div>The Microsoft Security Response Center (MSRC) works to protect customers and Microsoft from current and emerging threats to security and privacy. Within MSRC, our AI Vulnerabilities and Mitigations team analyzes all reported security vulnerabilities in Microsoft’s AI and agentic systems and develops new mitigations through deep research. Some of our team’s recent research and collaborations include: </div><div><ul style="list-style-type: disc;"><li style="font-size: 10pt;">The Nine Dimensions of Prompt Injection Attacks: <a href="https://arxiv.org/pdf/2611.04672" target="_blank" rel="noreferrer noopener">https://arxiv.org/pdf/2611.04672</a> </li></ul></div><div><ul style="list-style-type: disc;"><li style="font-size: 10pt;">Securing AI Agents with Information-Flow Control (NeurIPS’26): <a href="https://arxiv.org/abs/2505.23643" target="_blank" rel="noreferrer noopener">https://arxiv.org/abs/2505.23643</a> </li></ul></div><div><ul style="list-style-type: disc;"><li style="font-size: 10pt;">VerifiableFL: Verifiable Claims for Federated Learning using Exclaves (SoCC’26): <a href="https://arxiv.org/abs/2412.10537" target="_blank" rel="noreferrer noopener">https://arxiv.org/abs/2412.10537</a> </li></ul></div><div><ul style="list-style-type: disc;"><li style="font-size: 10pt;">LLMail-Inject: A Dataset from a Realistic Adaptive Prompt Injection Challenge (EMNLP’26): <a href="https://arxiv.org/abs/2506.09956" target="_blank" rel="noreferrer noopener">https://arxiv.org/abs/2506.09956</a> </li></ul></div><div><ul style="list-style-type: disc;"><li style="font-size: 10pt;">Optimizing Agent Planning for Security and Autonomy (ICLR’26) <a href="https://openreview.net/forum?id=g0aVCDY3gS" target="_blank" rel="noreferrer noopener">https://openreview.net/forum?id=g0aVCDY3gS</a> </li></ul></div><div><ul style="list-style-type: disc;"><li style="font-size: 10pt;">Implicit Memory as a Hidden Channel in LLMs (SaTML’26): <a href="https://arxiv.org/pdf/2602.08563" target="_blank" rel="noreferrer noopener">https://arxiv.org/pdf/2602.08563</a> </li></ul></div><div><ul style="list-style-type: disc;"><li style="font-size: 10pt;">Highlight & Summarize: RAG without the Jailbreaks: <a href="https://arxiv.org/abs/2508.02872" target="_blank" rel="noreferrer noopener">https://arxiv.org/abs/2508.02872</a> </li></ul></div><div><ul style="list-style-type: disc;"><li style="font-size: 10pt;">The Hawthorne effect in reasoning models: Evaluating and steering test awareness (NeurIPS’25): <a href="https://arxiv.org/abs/2505.14617" target="_blank" rel="noreferrer noopener">https://arxiv.org/abs/2505.14617</a> </li></ul></div><div><ul style="list-style-type: disc;"><li style="font-size: 10pt;">TaskTracker: Catching LLM Task Drift with Activation Deltas (SaTML’25): <a href="https://arxiv.org/abs/2406.00799" target="_blank" rel="noreferrer noopener">https://arxiv.org/abs/2406.00799</a> </li></ul></div><div>We are looking for research interns to work with us on projects such as: identifying new classes of vulnerabilities in AI or agentic AI systems; detecting vulnerabilities in real systems; automating security vulnerability response using agents; and developing new mitigations that can be deployed at scale. </div><div>Our team is uniquely placed to solve real-world security and privacy challenges, through cutting-edge scientific research, informed by vulnerability data from production systems.<ul><li>Contract Length: 12 weeks </li><li>Location: Cambridge, UK </li></ul></div> Responsibilities <div><ul><li>Conduct cutting-edge research in AI security and privacy by proposing, exploring, and evaluating new ideas. </li><li>Develop and implement prototypes to validate concepts and demonstrate real-world applicability. </li><li>Collaborate with cross-functional teams to integrate security and privacy solutions into products and services. </li><li>Publish findings and present insights to internal stakeholders and external conferences to advance industry knowledge. </li></ul></div> Qualifications <div>Required/Minimum Qualifications:   </div><div><ul><li>Students enrolled in a PhD program or outstanding undergraduate/master’s students with research experience (e.g., published research papers). </li></ul></div><div> Preferred/Additional Qualifications: <ul><li>One or more papers at top security conferences (e.g., USENIX, CCS, S&P, NDSS) or papers focusing on security, safety, or privacy at top machine learning conferences (e.g., NeurIPS, ICML, ICLR). </li></ul></div> The base pay for this internship is £ 4,853.00 per month. Certain roles may be eligible for benefits and other compensation. Find additional benefits and pay information here: <a href="https://careers.microsoft.com/v2/global/en/corporate-pay/interns-corporate-pay.html">https://careers.microsoft.com/v2/global/en/corporate-pay/interns-corporate-pay.html</a> This position will be open for a minimum of 5 days, with applications accepted on an ongoing basis until the position is filled. <hr> Microsoft is an equal opportunity employer. All qualified applicants will receive consideration for employment without regard to age, ancestry, citizenship, color, family or medical care leave, gender identity or expression, genetic information, immigration status, marital status, medical condition, national origin, physical or mental disability, political affiliation, protected veteran or military status, race, ethnicity, religion, sex (including pregnancy), sexual orientation, or any other characteristic protected by applicable local laws, regulations and ordinances. If you need assistance with religious accommodations and/or a reasonable accommodation due to a disability during the application process, read more about <a href="https://careers.microsoft.com/v2/global/en/accessibility.html">requesting accommodations.</a>